mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-05-22 21:32:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

python-3.6.zip added from Github

Browse source 
README.cosmo contains the necessary links.
This commit is contained in:
ahgamut 2021-08-08 09:38:33 +05:30 • committed by Justine Tunney
parent 75fc601ff5
commit 0c4c56ff39
4219 changed files with 1968626 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

62
third_party/python/Lib/email/__init__.py vendored Normal file
View file

@ -0,0 +1,62 @@
# Copyright (C) 2001-2007 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""A package for parsing, handling, and generating email messages."""
__all__ = [
'base64mime',
'charset',
'encoders',
'errors',
'feedparser',
'generator',
'header',
'iterators',
'message',
'message_from_file',
'message_from_binary_file',
'message_from_string',
'message_from_bytes',
'mime',
'parser',
'quoprimime',
'utils',
]
# Some convenience routines. Don't import Parser and Message as side-effects
# of importing email since those cascadingly import most of the rest of the
# email package.
def message_from_string(s, *args, **kws):
"""Parse a string into a Message object model.
Optional _class and strict are passed to the Parser constructor.
"""
from email.parser import Parser
return Parser(*args, **kws).parsestr(s)
def message_from_bytes(s, *args, **kws):
"""Parse a bytes string into a Message object model.
Optional _class and strict are passed to the Parser constructor.
"""
from email.parser import BytesParser
return BytesParser(*args, **kws).parsebytes(s)
def message_from_file(fp, *args, **kws):
"""Read a file and parse its contents into a Message object model.
Optional _class and strict are passed to the Parser constructor.
"""
from email.parser import Parser
return Parser(*args, **kws).parse(fp)
def message_from_binary_file(fp, *args, **kws):
"""Read a binary file and parse its contents into a Message object model.
Optional _class and strict are passed to the Parser constructor.
"""
from email.parser import BytesParser
return BytesParser(*args, **kws).parse(fp)

233
third_party/python/Lib/email/_encoded_words.py vendored Normal file
View file

@ -0,0 +1,233 @@
""" Routines for manipulating RFC2047 encoded words.
This is currently a package-private API, but will be considered for promotion
to a public API if there is demand.
"""
# An ecoded word looks like this:
#
# =?charset[*lang]?cte?encoded_string?=
#
# for more information about charset see the charset module. Here it is one
# of the preferred MIME charset names (hopefully; you never know when parsing).
# cte (Content Transfer Encoding) is either 'q' or 'b' (ignoring case). In
# theory other letters could be used for other encodings, but in practice this
# (almost?) never happens. There could be a public API for adding entries
# to the CTE tables, but YAGNI for now. 'q' is Quoted Printable, 'b' is
# Base64. The meaning of encoded_string should be obvious. 'lang' is optional
# as indicated by the brackets (they are not part of the syntax) but is almost
# never encountered in practice.
#
# The general interface for a CTE decoder is that it takes the encoded_string
# as its argument, and returns a tuple (cte_decoded_string, defects). The
# cte_decoded_string is the original binary that was encoded using the
# specified cte. 'defects' is a list of MessageDefect instances indicating any
# problems encountered during conversion. 'charset' and 'lang' are the
# corresponding strings extracted from the EW, case preserved.
#
# The general interface for a CTE encoder is that it takes a binary sequence
# as input and returns the cte_encoded_string, which is an ascii-only string.
#
# Each decoder must also supply a length function that takes the binary
# sequence as its argument and returns the length of the resulting encoded
# string.
#
# The main API functions for the module are decode, which calls the decoder
# referenced by the cte specifier, and encode, which adds the appropriate
# RFC 2047 "chrome" to the encoded string, and can optionally automatically
# select the shortest possible encoding. See their docstrings below for
# details.
import re
import base64
import binascii
import functools
from string import ascii_letters, digits
from email import errors
__all__ = ['decode_q',
'encode_q',
'decode_b',
'encode_b',
'len_q',
'len_b',
'decode',
'encode',
]
#
# Quoted Printable
#
# regex based decoder.
_q_byte_subber = functools.partial(re.compile(br'=([a-fA-F0-9]{2})').sub,
lambda m: bytes([int(m.group(1), 16)]))
def decode_q(encoded):
encoded = encoded.replace(b'_', b' ')
return _q_byte_subber(encoded), []
# dict mapping bytes to their encoded form
class _QByteMap(dict):
safe = b'-!*+/' + ascii_letters.encode('ascii') + digits.encode('ascii')
def __missing__(self, key):
if key in self.safe:
self[key] = chr(key)
else:
self[key] = "={:02X}".format(key)
return self[key]
_q_byte_map = _QByteMap()
# In headers spaces are mapped to '_'.
_q_byte_map[ord(' ')] = '_'
def encode_q(bstring):
return ''.join(_q_byte_map[x] for x in bstring)
def len_q(bstring):
return sum(len(_q_byte_map[x]) for x in bstring)
#
# Base64
#
def decode_b(encoded):
# First try encoding with validate=True, fixing the padding if needed.
# This will succeed only if encoded includes no invalid characters.
pad_err = len(encoded) % 4
missing_padding = b'==='[:4-pad_err] if pad_err else b''
try:
return (
base64.b64decode(encoded + missing_padding, validate=True),
[errors.InvalidBase64PaddingDefect()] if pad_err else [],
)
except binascii.Error:
# Since we had correct padding, this is likely an invalid char error.
#
# The non-alphabet characters are ignored as far as padding
# goes, but we don't know how many there are. So try without adding
# padding to see if it works.
try:
return (
base64.b64decode(encoded, validate=False),
[errors.InvalidBase64CharactersDefect()],
)
except binascii.Error:
# Add as much padding as could possibly be necessary (extra padding
# is ignored).
try:
return (
base64.b64decode(encoded + b'==', validate=False),
[errors.InvalidBase64CharactersDefect(),
errors.InvalidBase64PaddingDefect()],
)
except binascii.Error:
# This only happens when the encoded string's length is 1 more
# than a multiple of 4, which is invalid.
#
# bpo-27397: Just return the encoded string since there's no
# way to decode.
return encoded, [errors.InvalidBase64LengthDefect()]
def encode_b(bstring):
return base64.b64encode(bstring).decode('ascii')
def len_b(bstring):
groups_of_3, leftover = divmod(len(bstring), 3)
# 4 bytes out for each 3 bytes (or nonzero fraction thereof) in.
return groups_of_3 * 4 + (4 if leftover else 0)
_cte_decoders = {
'q': decode_q,
'b': decode_b,
}
def decode(ew):
"""Decode encoded word and return (string, charset, lang, defects) tuple.
An RFC 2047/2243 encoded word has the form:
=?charset*lang?cte?encoded_string?=
where '*lang' may be omitted but the other parts may not be.
This function expects exactly such a string (that is, it does not check the
syntax and may raise errors if the string is not well formed), and returns
the encoded_string decoded first from its Content Transfer Encoding and
then from the resulting bytes into unicode using the specified charset. If
the cte-decoded string does not successfully decode using the specified
character set, a defect is added to the defects list and the unknown octets
are replaced by the unicode 'unknown' character \\uFDFF.
The specified charset and language are returned. The default for language,
which is rarely if ever encountered, is the empty string.
"""
_, charset, cte, cte_string, _ = ew.split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
_cte_encoders = {
'q': encode_q,
'b': encode_b,
}
_cte_encode_length = {
'q': len_q,
'b': len_b,
}
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{}{}?{}?{}?=".format(charset, lang, encoding, encoded)

2832
third_party/python/Lib/email/_header_value_parser.py vendored Normal file
View file

File diff suppressed because it is too large Load diff

549
third_party/python/Lib/email/_parseaddr.py vendored Normal file
View file

@ -0,0 +1,549 @@
# Copyright (C) 2002-2007 Python Software Foundation
# Contact: email-sig@python.org
"""Email address parsing code.
Lifted directly from rfc822.py. This should eventually be rewritten.
"""
__all__ = [
'mktime_tz',
'parsedate',
'parsedate_tz',
'quote',
]
import time, calendar
SPACE = ' '
EMPTYSTRING = ''
COMMASPACE = ', '
# Parse a date field
_monthnames = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul',
'aug', 'sep', 'oct', 'nov', 'dec',
'january', 'february', 'march', 'april', 'may', 'june', 'july',
'august', 'september', 'october', 'november', 'december']
_daynames = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun']
# The timezone table does not include the military time zones defined
# in RFC822, other than Z. According to RFC1123, the description in
# RFC822 gets the signs wrong, so we can't rely on any such time
# zones. RFC1123 recommends that numeric timezone indicators be used
# instead of timezone names.
_timezones = {'UT':0, 'UTC':0, 'GMT':0, 'Z':0,
'AST': -400, 'ADT': -300, # Atlantic (used in Canada)
'EST': -500, 'EDT': -400, # Eastern
'CST': -600, 'CDT': -500, # Central
'MST': -700, 'MDT': -600, # Mountain
'PST': -800, 'PDT': -700 # Pacific
}
def parsedate_tz(data):
"""Convert a date string to a time tuple.
Accounts for military timezones.
"""
res = _parsedate_tz(data)
if not res:
return
if res[9] is None:
res[9] = 0
return tuple(res)
def _parsedate_tz(data):
"""Convert date to extended time tuple.
The last (additional) element is the time zone offset in seconds, except if
the timezone was specified as -0000. In that case the last element is
None. This indicates a UTC timestamp that explicitly declaims knowledge of
the source timezone, as opposed to a +0000 timestamp that indicates the
source timezone really was UTC.
"""
if not data:
return
data = data.split()
# The FWS after the comma after the day-of-week is optional, so search and
# adjust for this.
if data[0].endswith(',') or data[0].lower() in _daynames:
# There's a dayname here. Skip it
del data[0]
else:
i = data[0].rfind(',')
if i >= 0:
data[0] = data[0][i+1:]
if len(data) == 3: # RFC 850 date, deprecated
stuff = data[0].split('-')
if len(stuff) == 3:
data = stuff + data[1:]
if len(data) == 4:
s = data[3]
i = s.find('+')
if i == -1:
i = s.find('-')
if i > 0:
data[3:] = [s[:i], s[i:]]
else:
data.append('') # Dummy tz
if len(data) < 5:
return None
data = data[:5]
[dd, mm, yy, tm, tz] = data
mm = mm.lower()
if mm not in _monthnames:
dd, mm = mm, dd.lower()
if mm not in _monthnames:
return None
mm = _monthnames.index(mm) + 1
if mm > 12:
mm -= 12
if dd[-1] == ',':
dd = dd[:-1]
i = yy.find(':')
if i > 0:
yy, tm = tm, yy
if yy[-1] == ',':
yy = yy[:-1]
if not yy[0].isdigit():
yy, tz = tz, yy
if tm[-1] == ',':
tm = tm[:-1]
tm = tm.split(':')
if len(tm) == 2:
[thh, tmm] = tm
tss = '0'
elif len(tm) == 3:
[thh, tmm, tss] = tm
elif len(tm) == 1 and '.' in tm[0]:
# Some non-compliant MUAs use '.' to separate time elements.
tm = tm[0].split('.')
if len(tm) == 2:
[thh, tmm] = tm
tss = 0
elif len(tm) == 3:
[thh, tmm, tss] = tm
else:
return None
try:
yy = int(yy)
dd = int(dd)
thh = int(thh)
tmm = int(tmm)
tss = int(tss)
except ValueError:
return None
# Check for a yy specified in two-digit format, then convert it to the
# appropriate four-digit format, according to the POSIX standard. RFC 822
# calls for a two-digit yy, but RFC 2822 (which obsoletes RFC 822)
# mandates a 4-digit yy. For more information, see the documentation for
# the time module.
if yy < 100:
# The year is between 1969 and 1999 (inclusive).
if yy > 68:
yy += 1900
# The year is between 2000 and 2068 (inclusive).
else:
yy += 2000
tzoffset = None
tz = tz.upper()
if tz in _timezones:
tzoffset = _timezones[tz]
else:
try:
tzoffset = int(tz)
except ValueError:
pass
if tzoffset==0 and tz.startswith('-'):
tzoffset = None
# Convert a timezone offset into seconds ; -0500 -> -18000
if tzoffset:
if tzoffset < 0:
tzsign = -1
tzoffset = -tzoffset
else:
tzsign = 1
tzoffset = tzsign * ( (tzoffset//100)*3600 + (tzoffset % 100)*60)
# Daylight Saving Time flag is set to -1, since DST is unknown.
return [yy, mm, dd, thh, tmm, tss, 0, 1, -1, tzoffset]
def parsedate(data):
"""Convert a time string to a time tuple."""
t = parsedate_tz(data)
if isinstance(t, tuple):
return t[:9]
else:
return t
def mktime_tz(data):
"""Turn a 10-tuple as returned by parsedate_tz() into a POSIX timestamp."""
if data[9] is None:
# No zone info, so localtime is better assumption than GMT
return time.mktime(data[:8] + (-1,))
else:
t = calendar.timegm(data)
return t - data[9]
def quote(str):
"""Prepare string to be used in a quoted string.
Turns backslash and double quote characters into quoted pairs. These
are the only characters that need to be quoted inside a quoted string.
Does not add the surrounding double quotes.
"""
return str.replace('\\', '\\\\').replace('"', '\\"')
class AddrlistClass:
"""Address parser class by Ben Escoto.
To understand what this class does, it helps to have a copy of RFC 2822 in
front of you.
Note: this class interface is deprecated and may be removed in the future.
Use email.utils.AddressList instead.
"""
def __init__(self, field):
"""Initialize a new instance.
`field' is an unparsed address header field, containing
one or more addresses.
"""
self.specials = '()<>@,:;.\"[]'
self.pos = 0
self.LWS = ' \t'
self.CR = '\r\n'
self.FWS = self.LWS + self.CR
self.atomends = self.specials + self.LWS + self.CR
# Note that RFC 2822 now specifies `.' as obs-phrase, meaning that it
# is obsolete syntax. RFC 2822 requires that we recognize obsolete
# syntax, so allow dots in phrases.
self.phraseends = self.atomends.replace('.', '')
self.field = field
self.commentlist = []
def gotonext(self):
"""Skip white space and extract comments."""
wslist = []
while self.pos < len(self.field):
if self.field[self.pos] in self.LWS + '\n\r':
if self.field[self.pos] not in '\n\r':
wslist.append(self.field[self.pos])
self.pos += 1
elif self.field[self.pos] == '(':
self.commentlist.append(self.getcomment())
else:
break
return EMPTYSTRING.join(wslist)
def getaddrlist(self):
"""Parse all addresses.
Returns a list containing all of the addresses.
"""
result = []
while self.pos < len(self.field):
ad = self.getaddress()
if ad:
result += ad
else:
result.append(('', ''))
return result
def getaddress(self):
"""Parse the next address."""
self.commentlist = []
self.gotonext()
oldpos = self.pos
oldcl = self.commentlist
plist = self.getphraselist()
self.gotonext()
returnlist = []
if self.pos >= len(self.field):
# Bad email address technically, no domain.
if plist:
returnlist = [(SPACE.join(self.commentlist), plist[0])]
elif self.field[self.pos] in '.@':
# email address is just an addrspec
# this isn't very efficient since we start over
self.pos = oldpos
self.commentlist = oldcl
addrspec = self.getaddrspec()
returnlist = [(SPACE.join(self.commentlist), addrspec)]
elif self.field[self.pos] == ':':
# address is a group
returnlist = []
fieldlen = len(self.field)
self.pos += 1
while self.pos < len(self.field):
self.gotonext()
if self.pos < fieldlen and self.field[self.pos] == ';':
self.pos += 1
break
returnlist = returnlist + self.getaddress()
elif self.field[self.pos] == '<':
# Address is a phrase then a route addr
routeaddr = self.getrouteaddr()
if self.commentlist:
returnlist = [(SPACE.join(plist) + ' (' +
' '.join(self.commentlist) + ')', routeaddr)]
else:
returnlist = [(SPACE.join(plist), routeaddr)]
else:
if plist:
returnlist = [(SPACE.join(self.commentlist), plist[0])]
elif self.field[self.pos] in self.specials:
self.pos += 1
self.gotonext()
if self.pos < len(self.field) and self.field[self.pos] == ',':
self.pos += 1
return returnlist
def getrouteaddr(self):
"""Parse a route address (Return-path value).
This method just skips all the route stuff and returns the addrspec.
"""
if self.field[self.pos] != '<':
return
expectroute = False
self.pos += 1
self.gotonext()
adlist = ''
while self.pos < len(self.field):
if expectroute:
self.getdomain()
expectroute = False
elif self.field[self.pos] == '>':
self.pos += 1
break
elif self.field[self.pos] == '@':
self.pos += 1
expectroute = True
elif self.field[self.pos] == ':':
self.pos += 1
else:
adlist = self.getaddrspec()
self.pos += 1
break
self.gotonext()
return adlist
def getaddrspec(self):
"""Parse an RFC 2822 addr-spec."""
aslist = []
self.gotonext()
while self.pos < len(self.field):
preserve_ws = True
if self.field[self.pos] == '.':
if aslist and not aslist[-1].strip():
aslist.pop()
aslist.append('.')
self.pos += 1
preserve_ws = False
elif self.field[self.pos] == '"':
aslist.append('"%s"' % quote(self.getquote()))
elif self.field[self.pos] in self.atomends:
if aslist and not aslist[-1].strip():
aslist.pop()
break
else:
aslist.append(self.getatom())
ws = self.gotonext()
if preserve_ws and ws:
aslist.append(ws)
if self.pos >= len(self.field) or self.field[self.pos] != '@':
return EMPTYSTRING.join(aslist)
aslist.append('@')
self.pos += 1
self.gotonext()
domain = self.getdomain()
if not domain:
# Invalid domain, return an empty address instead of returning a
# local part to denote failed parsing.
return EMPTYSTRING
return EMPTYSTRING.join(aslist) + domain
def getdomain(self):
"""Get the complete domain name from an address."""
sdlist = []
while self.pos < len(self.field):
if self.field[self.pos] in self.LWS:
self.pos += 1
elif self.field[self.pos] == '(':
self.commentlist.append(self.getcomment())
elif self.field[self.pos] == '[':
sdlist.append(self.getdomainliteral())
elif self.field[self.pos] == '.':
self.pos += 1
sdlist.append('.')
elif self.field[self.pos] == '@':
# bpo-34155: Don't parse domains with two `@` like
# `a@malicious.org@important.com`.
return EMPTYSTRING
elif self.field[self.pos] in self.atomends:
break
else:
sdlist.append(self.getatom())
return EMPTYSTRING.join(sdlist)
def getdelimited(self, beginchar, endchars, allowcomments=True):
"""Parse a header fragment delimited by special characters.
`beginchar' is the start character for the fragment.
If self is not looking at an instance of `beginchar' then
getdelimited returns the empty string.
`endchars' is a sequence of allowable end-delimiting characters.
Parsing stops when one of these is encountered.
If `allowcomments' is non-zero, embedded RFC 2822 comments are allowed
within the parsed fragment.
"""
if self.field[self.pos] != beginchar:
return ''
slist = ['']
quote = False
self.pos += 1
while self.pos < len(self.field):
if quote:
slist.append(self.field[self.pos])
quote = False
elif self.field[self.pos] in endchars:
self.pos += 1
break
elif allowcomments and self.field[self.pos] == '(':
slist.append(self.getcomment())
continue # have already advanced pos from getcomment
elif self.field[self.pos] == '\\':
quote = True
else:
slist.append(self.field[self.pos])
self.pos += 1
return EMPTYSTRING.join(slist)
def getquote(self):
"""Get a quote-delimited fragment from self's field."""
return self.getdelimited('"', '"\r', False)
def getcomment(self):
"""Get a parenthesis-delimited fragment from self's field."""
return self.getdelimited('(', ')\r', True)
def getdomainliteral(self):
"""Parse an RFC 2822 domain-literal."""
return '[%s]' % self.getdelimited('[', ']\r', False)
def getatom(self, atomends=None):
"""Parse an RFC 2822 atom.
Optional atomends specifies a different set of end token delimiters
(the default is to use self.atomends). This is used e.g. in
getphraselist() since phrase endings must not include the `.' (which
is legal in phrases)."""
atomlist = ['']
if atomends is None:
atomends = self.atomends
while self.pos < len(self.field):
if self.field[self.pos] in atomends:
break
else:
atomlist.append(self.field[self.pos])
self.pos += 1
return EMPTYSTRING.join(atomlist)
def getphraselist(self):
"""Parse a sequence of RFC 2822 phrases.
A phrase is a sequence of words, which are in turn either RFC 2822
atoms or quoted-strings. Phrases are canonicalized by squeezing all
runs of continuous whitespace into one space.
"""
plist = []
while self.pos < len(self.field):
if self.field[self.pos] in self.FWS:
self.pos += 1
elif self.field[self.pos] == '"':
plist.append(self.getquote())
elif self.field[self.pos] == '(':
self.commentlist.append(self.getcomment())
elif self.field[self.pos] in self.phraseends:
break
else:
plist.append(self.getatom(self.phraseends))
return plist
class AddressList(AddrlistClass):
"""An AddressList encapsulates a list of parsed RFC 2822 addresses."""
def __init__(self, field):
AddrlistClass.__init__(self, field)
if field:
self.addresslist = self.getaddrlist()
else:
self.addresslist = []
def __len__(self):
return len(self.addresslist)
def __add__(self, other):
# Set union
newaddr = AddressList(None)
newaddr.addresslist = self.addresslist[:]
for x in other.addresslist:
if not x in self.addresslist:
newaddr.addresslist.append(x)
return newaddr
def __iadd__(self, other):
# Set union, in-place
for x in other.addresslist:
if not x in self.addresslist:
self.addresslist.append(x)
return self
def __sub__(self, other):
# Set difference
newaddr = AddressList(None)
for x in self.addresslist:
if not x in other.addresslist:
newaddr.addresslist.append(x)
return newaddr
def __isub__(self, other):
# Set difference, in-place
for x in other.addresslist:
if x in self.addresslist:
self.addresslist.remove(x)
return self
def __getitem__(self, index):
# Make indexing, slices, and 'in' work
return self.addresslist[index]

374
third_party/python/Lib/email/_policybase.py vendored Normal file
View file

@ -0,0 +1,374 @@
"""Policy framework for the email package.
Allows fine grained feature control of how the package parses and emits data.
"""
import abc
from email import header
from email import charset as _charset
from email.utils import _has_surrogates
__all__ = [
'Policy',
'Compat32',
'compat32',
]
class _PolicyBase:
"""Policy Object basic framework.
This class is useless unless subclassed. A subclass should define
class attributes with defaults for any values that are to be
managed by the Policy object. The constructor will then allow
non-default values to be set for these attributes at instance
creation time. The instance will be callable, taking these same
attributes keyword arguments, and returning a new instance
identical to the called instance except for those values changed
by the keyword arguments. Instances may be added, yielding new
instances with any non-default values from the right hand
operand overriding those in the left hand operand. That is,
A + B == A(<non-default values of B>)
The repr of an instance can be used to reconstruct the object
if and only if the repr of the values can be used to reconstruct
those values.
"""
def __init__(self, **kw):
"""Create new Policy, possibly overriding some defaults.
See class docstring for a list of overridable attributes.
"""
for name, value in kw.items():
if hasattr(self, name):
super(_PolicyBase,self).__setattr__(name, value)
else:
raise TypeError(
"{!r} is an invalid keyword argument for {}".format(
name, self.__class__.__name__))
def __repr__(self):
args = [ "{}={!r}".format(name, value)
for name, value in self.__dict__.items() ]
return "{}({})".format(self.__class__.__name__, ', '.join(args))
def clone(self, **kw):
"""Return a new instance with specified attributes changed.
The new instance has the same attribute values as the current object,
except for the changes passed in as keyword arguments.
"""
newpolicy = self.__class__.__new__(self.__class__)
for attr, value in self.__dict__.items():
object.__setattr__(newpolicy, attr, value)
for attr, value in kw.items():
if not hasattr(self, attr):
raise TypeError(
"{!r} is an invalid keyword argument for {}".format(
attr, self.__class__.__name__))
object.__setattr__(newpolicy, attr, value)
return newpolicy
def __setattr__(self, name, value):
if hasattr(self, name):
msg = "{!r} object attribute {!r} is read-only"
else:
msg = "{!r} object has no attribute {!r}"
raise AttributeError(msg.format(self.__class__.__name__, name))
def __add__(self, other):
"""Non-default values from right operand override those from left.
The object returned is a new instance of the subclass.
"""
return self.clone(**other.__dict__)
def _append_doc(doc, added_doc):
doc = doc.rsplit('\n', 1)[0]
added_doc = added_doc.split('\n', 1)[1]
return doc + '\n' + added_doc
def _extend_docstrings(cls):
if cls.__doc__ and cls.__doc__.startswith('+'):
cls.__doc__ = _append_doc(cls.__bases__[0].__doc__, cls.__doc__)
for name, attr in cls.__dict__.items():
if attr.__doc__ and attr.__doc__.startswith('+'):
for c in (c for base in cls.__bases__ for c in base.mro()):
doc = getattr(getattr(c, name), '__doc__')
if doc:
attr.__doc__ = _append_doc(doc, attr.__doc__)
break
return cls
class Policy(_PolicyBase, metaclass=abc.ABCMeta):
r"""Controls for how messages are interpreted and formatted.
Most of the classes and many of the methods in the email package accept
Policy objects as parameters. A Policy object contains a set of values and
functions that control how input is interpreted and how output is rendered.
For example, the parameter 'raise_on_defect' controls whether or not an RFC
violation results in an error being raised or not, while 'max_line_length'
controls the maximum length of output lines when a Message is serialized.
Any valid attribute may be overridden when a Policy is created by passing
it as a keyword argument to the constructor. Policy objects are immutable,
but a new Policy object can be created with only certain values changed by
calling the Policy instance with keyword arguments. Policy objects can
also be added, producing a new Policy object in which the non-default
attributes set in the right hand operand overwrite those specified in the
left operand.
Settable attributes:
raise_on_defect -- If true, then defects should be raised as errors.
Default: False.
linesep -- string containing the value to use as separation
between output lines. Default '\n'.
cte_type -- Type of allowed content transfer encodings
7bit -- ASCII only
8bit -- Content-Transfer-Encoding: 8bit is allowed
Default: 8bit. Also controls the disposition of
(RFC invalid) binary data in headers; see the
documentation of the binary_fold method.
max_line_length -- maximum length of lines, excluding 'linesep',
during serialization. None or 0 means no line
wrapping is done. Default is 78.
mangle_from_ -- a flag that, when True escapes From_ lines in the
body of the message by putting a `>' in front of
them. This is used when the message is being
serialized by a generator. Default: True.
message_factory -- the class to use to create new message objects.
If the value is None, the default is Message.
"""
raise_on_defect = False
linesep = '\n'
cte_type = '8bit'
max_line_length = 78
mangle_from_ = False
message_factory = None
def handle_defect(self, obj, defect):
"""Based on policy, either raise defect or call register_defect.
handle_defect(obj, defect)
defect should be a Defect subclass, but in any case must be an
Exception subclass. obj is the object on which the defect should be
registered if it is not raised. If the raise_on_defect is True, the
defect is raised as an error, otherwise the object and the defect are
passed to register_defect.
This method is intended to be called by parsers that discover defects.
The email package parsers always call it with Defect instances.
"""
if self.raise_on_defect:
raise defect
self.register_defect(obj, defect)
def register_defect(self, obj, defect):
"""Record 'defect' on 'obj'.
Called by handle_defect if raise_on_defect is False. This method is
part of the Policy API so that Policy subclasses can implement custom
defect handling. The default implementation calls the append method of
the defects attribute of obj. The objects used by the email package by
default that get passed to this method will always have a defects
attribute with an append method.
"""
obj.defects.append(defect)
def header_max_count(self, name):
"""Return the maximum allowed number of headers named 'name'.
Called when a header is added to a Message object. If the returned
value is not 0 or None, and there are already a number of headers with
the name 'name' equal to the value returned, a ValueError is raised.
Because the default behavior of Message's __setitem__ is to append the
value to the list of headers, it is easy to create duplicate headers
without realizing it. This method allows certain headers to be limited
in the number of instances of that header that may be added to a
Message programmatically. (The limit is not observed by the parser,
which will faithfully produce as many headers as exist in the message
being parsed.)
The default implementation returns None for all header names.
"""
return None
@abc.abstractmethod
def header_source_parse(self, sourcelines):
"""Given a list of linesep terminated strings constituting the lines of
a single header, return the (name, value) tuple that should be stored
in the model. The input lines should retain their terminating linesep
characters. The lines passed in by the email package may contain
surrogateescaped binary data.
"""
raise NotImplementedError
@abc.abstractmethod
def header_store_parse(self, name, value):
"""Given the header name and the value provided by the application
program, return the (name, value) that should be stored in the model.
"""
raise NotImplementedError
@abc.abstractmethod
def header_fetch_parse(self, name, value):
"""Given the header name and the value from the model, return the value
to be returned to the application program that is requesting that
header. The value passed in by the email package may contain
surrogateescaped binary data if the lines were parsed by a BytesParser.
The returned value should not contain any surrogateescaped data.
"""
raise NotImplementedError
@abc.abstractmethod
def fold(self, name, value):
"""Given the header name and the value from the model, return a string
containing linesep characters that implement the folding of the header
according to the policy controls. The value passed in by the email
package may contain surrogateescaped binary data if the lines were
parsed by a BytesParser. The returned value should not contain any
surrogateescaped data.
"""
raise NotImplementedError
@abc.abstractmethod
def fold_binary(self, name, value):
"""Given the header name and the value from the model, return binary
data containing linesep characters that implement the folding of the
header according to the policy controls. The value passed in by the
email package may contain surrogateescaped binary data.
"""
raise NotImplementedError
@_extend_docstrings
class Compat32(Policy):
"""+
This particular policy is the backward compatibility Policy. It
replicates the behavior of the email package version 5.1.
"""
mangle_from_ = True
def _sanitize_header(self, name, value):
# If the header value contains surrogates, return a Header using
# the unknown-8bit charset to encode the bytes as encoded words.
if not isinstance(value, str):
# Assume it is already a header object
return value
if _has_surrogates(value):
return header.Header(value, charset=_charset.UNKNOWN8BIT,
header_name=name)
else:
return value
def header_source_parse(self, sourcelines):
"""+
The name is parsed as everything up to the ':' and returned unmodified.
The value is determined by stripping leading whitespace off the
remainder of the first line, joining all subsequent lines together, and
stripping any trailing carriage return or linefeed characters.
"""
name, value = sourcelines[0].split(':', 1)
value = value.lstrip(' \t') + ''.join(sourcelines[1:])
return (name, value.rstrip('\r\n'))
def header_store_parse(self, name, value):
"""+
The name and value are returned unmodified.
"""
return (name, value)
def header_fetch_parse(self, name, value):
"""+
If the value contains binary data, it is converted into a Header object
using the unknown-8bit charset. Otherwise it is returned unmodified.
"""
return self._sanitize_header(name, value)
def fold(self, name, value):
"""+
Headers are folded using the Header folding algorithm, which preserves
existing line breaks in the value, and wraps each resulting line to the
max_line_length. Non-ASCII binary data are CTE encoded using the
unknown-8bit charset.
"""
return self._fold(name, value, sanitize=True)
def fold_binary(self, name, value):
"""+
Headers are folded using the Header folding algorithm, which preserves
existing line breaks in the value, and wraps each resulting line to the
max_line_length. If cte_type is 7bit, non-ascii binary data is CTE
encoded using the unknown-8bit charset. Otherwise the original source
header is used, with its existing line breaks and/or binary data.
"""
folded = self._fold(name, value, sanitize=self.cte_type=='7bit')
return folded.encode('ascii', 'surrogateescape')
def _fold(self, name, value, sanitize):
parts = []
parts.append('%s: ' % name)
if isinstance(value, str):
if _has_surrogates(value):
if sanitize:
h = header.Header(value,
charset=_charset.UNKNOWN8BIT,
header_name=name)
else:
# 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.
parts.append(value)
h = None
else:
h = header.Header(value, header_name=name)
else:
# Assume it is a Header-like object.
h = value
if h is not None:
# The Header class interprets a value of None for maxlinelen as the
# default value of 78, as recommended by RFC 2822.
maxlinelen = 0
if self.max_line_length is not None:
maxlinelen = self.max_line_length
parts.append(h.encode(linesep=self.linesep, maxlinelen=maxlinelen))
parts.append(self.linesep)
return ''.join(parts)
compat32 = Compat32()

216
third_party/python/Lib/email/architecture.rst vendored Normal file
View file

@ -0,0 +1,216 @@
:mod:`email` Package Architecture
=================================
Overview
--------
The email package consists of three major components:
Model
An object structure that represents an email message, and provides an
API for creating, querying, and modifying a message.
Parser
Takes a sequence of characters or bytes and produces a model of the
email message represented by those characters or bytes.
Generator
Takes a model and turns it into a sequence of characters or bytes. The
sequence can either be intended for human consumption (a printable
unicode string) or bytes suitable for transmission over the wire. In
the latter case all data is properly encoded using the content transfer
encodings specified by the relevant RFCs.
Conceptually the package is organized around the model. The model provides both
"external" APIs intended for use by application programs using the library,
and "internal" APIs intended for use by the Parser and Generator components.
This division is intentionally a bit fuzzy; the API described by this
documentation is all a public, stable API. This allows for an application
with special needs to implement its own parser and/or generator.
In addition to the three major functional components, there is a third key
component to the architecture:
Policy
An object that specifies various behavioral settings and carries
implementations of various behavior-controlling methods.
The Policy framework provides a simple and convenient way to control the
behavior of the library, making it possible for the library to be used in a
very flexible fashion while leveraging the common code required to parse,
represent, and generate message-like objects. For example, in addition to the
default :rfc:`5322` email message policy, we also have a policy that manages
HTTP headers in a fashion compliant with :rfc:`2616`. Individual policy
controls, such as the maximum line length produced by the generator, can also
be controlled individually to meet specialized application requirements.
The Model
---------
The message model is implemented by the :class:`~email.message.Message` class.
The model divides a message into the two fundamental parts discussed by the
RFC: the header section and the body. The `Message` object acts as a
pseudo-dictionary of named headers. Its dictionary interface provides
convenient access to individual headers by name. However, all headers are kept
internally in an ordered list, so that the information about the order of the
headers in the original message is preserved.
The `Message` object also has a `payload` that holds the body. A `payload` can
be one of two things: data, or a list of `Message` objects. The latter is used
to represent a multipart MIME message. Lists can be nested arbitrarily deeply
in order to represent the message, with all terminal leaves having non-list
data payloads.
Message Lifecycle
-----------------
The general lifecycle of a message is:
Creation
A `Message` object can be created by a Parser, or it can be
instantiated as an empty message by an application.
Manipulation
The application may examine one or more headers, and/or the
payload, and it may modify one or more headers and/or
the payload. This may be done on the top level `Message`
object, or on any sub-object.
Finalization
The Model is converted into a unicode or binary stream,
or the model is discarded.
Header Policy Control During Lifecycle
--------------------------------------
One of the major controls exerted by the Policy is the management of headers
during the `Message` lifecycle. Most applications don't need to be aware of
this.
A header enters the model in one of two ways: via a Parser, or by being set to
a specific value by an application program after the Model already exists.
Similarly, a header exits the model in one of two ways: by being serialized by
a Generator, or by being retrieved from a Model by an application program. The
Policy object provides hooks for all four of these pathways.
The model storage for headers is a list of (name, value) tuples.
The Parser identifies headers during parsing, and passes them to the
:meth:`~email.policy.Policy.header_source_parse` method of the Policy. The
result of that method is the (name, value) tuple to be stored in the model.
When an application program supplies a header value (for example, through the
`Message` object `__setitem__` interface), the name and the value are passed to
the :meth:`~email.policy.Policy.header_store_parse` method of the Policy, which
returns the (name, value) tuple to be stored in the model.
When an application program retrieves a header (through any of the dict or list
interfaces of `Message`), the name and value are passed to the
:meth:`~email.policy.Policy.header_fetch_parse` method of the Policy to
obtain the value returned to the application.
When a Generator requests a header during serialization, the name and value are
passed to the :meth:`~email.policy.Policy.fold` method of the Policy, which
returns a string containing line breaks in the appropriate places. The
:meth:`~email.policy.Policy.cte_type` Policy control determines whether or
not Content Transfer Encoding is performed on the data in the header. There is
also a :meth:`~email.policy.Policy.binary_fold` method for use by generators
that produce binary output, which returns the folded header as binary data,
possibly folded at different places than the corresponding string would be.
Handling Binary Data
--------------------
In an ideal world all message data would conform to the RFCs, meaning that the
parser could decode the message into the idealized unicode message that the
sender originally wrote. In the real world, the email package must also be
able to deal with badly formatted messages, including messages containing
non-ASCII characters that either have no indicated character set or are not
valid characters in the indicated character set.
Since email messages are *primarily* text data, and operations on message data
are primarily text operations (except for binary payloads of course), the model
stores all text data as unicode strings. Un-decodable binary inside text
data is handled by using the `surrogateescape` error handler of the ASCII
codec. As with the binary filenames the error handler was introduced to
handle, this allows the email package to "carry" the binary data received
during parsing along until the output stage, at which time it is regenerated
in its original form.
This carried binary data is almost entirely an implementation detail. The one
place where it is visible in the API is in the "internal" API. A Parser must
do the `surrogateescape` encoding of binary input data, and pass that data to
the appropriate Policy method. The "internal" interface used by the Generator
to access header values preserves the `surrogateescaped` bytes. All other
interfaces convert the binary data either back into bytes or into a safe form
(losing information in some cases).
Backward Compatibility
----------------------
The :class:`~email.policy.Policy.Compat32` Policy provides backward
compatibility with version 5.1 of the email package. It does this via the
following implementation of the four+1 Policy methods described above:
header_source_parse
Splits the first line on the colon to obtain the name, discards any spaces
after the colon, and joins the remainder of the line with all of the
remaining lines, preserving the linesep characters to obtain the value.
Trailing carriage return and/or linefeed characters are stripped from the
resulting value string.
header_store_parse
Returns the name and value exactly as received from the application.
header_fetch_parse
If the value contains any `surrogateescaped` binary data, return the value
as a :class:`~email.header.Header` object, using the character set
`unknown-8bit`. Otherwise just returns the value.
fold
Uses :class:`~email.header.Header`'s folding to fold headers in the
same way the email5.1 generator did.
binary_fold
Same as fold, but encodes to 'ascii'.
New Algorithm
-------------
header_source_parse
Same as legacy behavior.
header_store_parse
Same as legacy behavior.
header_fetch_parse
If the value is already a header object, returns it. Otherwise, parses the
value using the new parser, and returns the resulting object as the value.
`surrogateescaped` bytes get turned into unicode unknown character code
points.
fold
Uses the new header folding algorithm, respecting the policy settings.
surrogateescaped bytes are encoded using the ``unknown-8bit`` charset for
``cte_type=7bit`` or ``8bit``. Returns a string.
At some point there will also be a ``cte_type=unicode``, and for that
policy fold will serialize the idealized unicode message with RFC-like
folding, converting any surrogateescaped bytes into the unicode
unknown character glyph.
binary_fold
Uses the new header folding algorithm, respecting the policy settings.
surrogateescaped bytes are encoded using the `unknown-8bit` charset for
``cte_type=7bit``, and get turned back into bytes for ``cte_type=8bit``.
Returns bytes.
At some point there will also be a ``cte_type=unicode``, and for that
policy binary_fold will serialize the message according to :rfc:``5335``.

119
third_party/python/Lib/email/base64mime.py vendored Normal file
View file

@ -0,0 +1,119 @@
# Copyright (C) 2002-2007 Python Software Foundation
# Author: Ben Gertzfield
# Contact: email-sig@python.org
"""Base64 content transfer encoding per RFCs 2045-2047.
This module handles the content transfer encoding method defined in RFC 2045
to encode arbitrary 8-bit data using the three 8-bit bytes in four 7-bit
characters encoding known as Base64.
It is used in the MIME standards for email to attach images, audio, and text
using some 8-bit character sets to messages.
This module provides an interface to encode and decode both headers and bodies
with Base64 encoding.
RFC 2045 defines a method for including character set information in an
`encoded-word' in a header. This method is commonly used for 8-bit real names
in To:, From:, Cc:, etc. fields, as well as Subject: lines.
This module does not do the line wrapping or end-of-line character conversion
necessary for proper internationalized headers; it only does dumb encoding and
decoding. To deal with the various line wrapping issues, use the email.header
module.
"""
__all__ = [
'body_decode',
'body_encode',
'decode',
'decodestring',
'header_encode',
'header_length',
]
from base64 import b64encode
from binascii import b2a_base64, a2b_base64
CRLF = '\r\n'
NL = '\n'
EMPTYSTRING = ''
# See also Charset.py
MISC_LEN = 7
# Helpers
def header_length(bytearray):
"""Return the length of s when it is encoded with base64."""
groups_of_3, leftover = divmod(len(bytearray), 3)
# 4 bytes out for each 3 bytes (or nonzero fraction thereof) in.
n = groups_of_3 * 4
if leftover:
n += 4
return n
def header_encode(header_bytes, charset='iso-8859-1'):
"""Encode a single header line with Base64 encoding in a given charset.
charset names the character set to use to encode the header. It defaults
to iso-8859-1. Base64 encoding is defined in RFC 2045.
"""
if not header_bytes:
return ""
if isinstance(header_bytes, str):
header_bytes = header_bytes.encode(charset)
encoded = b64encode(header_bytes).decode("ascii")
return '=?%s?b?%s?=' % (charset, encoded)
def body_encode(s, maxlinelen=76, eol=NL):
r"""Encode a string with base64.
Each line will be wrapped at, at most, maxlinelen characters (defaults to
76 characters).
Each line of encoded text will end with eol, which defaults to "\n". Set
this to "\r\n" if you will be using the result of this function directly
in an email.
"""
if not s:
return s
encvec = []
max_unencoded = maxlinelen * 3 // 4
for i in range(0, len(s), max_unencoded):
# BAW: should encode() inherit b2a_base64()'s dubious behavior in
# adding a newline to the encoded string?
enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii")
if enc.endswith(NL) and eol != NL:
enc = enc[:-1] + eol
encvec.append(enc)
return EMPTYSTRING.join(encvec)
def decode(string):
"""Decode a raw base64 string, returning a bytes object.
This function does not parse a full MIME header value encoded with
base64 (like =?iso-8859-1?b?bmloISBuaWgh?=) -- please use the high
level email.header class for that functionality.
"""
if not string:
return bytes()
elif isinstance(string, str):
return a2b_base64(string.encode('raw-unicode-escape'))
else:
return a2b_base64(string)
# For convenience and backwards compatibility w/ standard base64 module
body_decode = decode
decodestring = decode

406
third_party/python/Lib/email/charset.py vendored Normal file
View file

@ -0,0 +1,406 @@
# Copyright (C) 2001-2007 Python Software Foundation
# Author: Ben Gertzfield, Barry Warsaw
# Contact: email-sig@python.org
__all__ = [
'Charset',
'add_alias',
'add_charset',
'add_codec',
]
from functools import partial
import email.base64mime
import email.quoprimime
from email import errors
from email.encoders import encode_7or8bit
# Flags for types of header encodings
QP = 1 # Quoted-Printable
BASE64 = 2 # Base64
SHORTEST = 3 # the shorter of QP and base64, but only for headers
# In "=?charset?q?hello_world?=", the =?, ?q?, and ?= add up to 7
RFC2047_CHROME_LEN = 7
DEFAULT_CHARSET = 'us-ascii'
UNKNOWN8BIT = 'unknown-8bit'
EMPTYSTRING = ''
# Defaults
CHARSETS = {
# input header enc body enc output conv
'iso-8859-1': (QP, QP, None),
'iso-8859-2': (QP, QP, None),
'iso-8859-3': (QP, QP, None),
'iso-8859-4': (QP, QP, None),
# iso-8859-5 is Cyrillic, and not especially used
# iso-8859-6 is Arabic, also not particularly used
# iso-8859-7 is Greek, QP will not make it readable
# iso-8859-8 is Hebrew, QP will not make it readable
'iso-8859-9': (QP, QP, None),
'iso-8859-10': (QP, QP, None),
# iso-8859-11 is Thai, QP will not make it readable
'iso-8859-13': (QP, QP, None),
'iso-8859-14': (QP, QP, None),
'iso-8859-15': (QP, QP, None),
'iso-8859-16': (QP, QP, None),
'windows-1252':(QP, QP, None),
'viscii': (QP, QP, None),
'us-ascii': (None, None, None),
'big5': (BASE64, BASE64, None),
'gb2312': (BASE64, BASE64, None),
'euc-jp': (BASE64, None, 'iso-2022-jp'),
'shift_jis': (BASE64, None, 'iso-2022-jp'),
'iso-2022-jp': (BASE64, None, None),
'koi8-r': (BASE64, BASE64, None),
'utf-8': (SHORTEST, BASE64, 'utf-8'),
}
# Aliases for other commonly-used names for character sets. Map
# them to the real ones used in email.
ALIASES = {
'latin_1': 'iso-8859-1',
'latin-1': 'iso-8859-1',
'latin_2': 'iso-8859-2',
'latin-2': 'iso-8859-2',
'latin_3': 'iso-8859-3',
'latin-3': 'iso-8859-3',
'latin_4': 'iso-8859-4',
'latin-4': 'iso-8859-4',
'latin_5': 'iso-8859-9',
'latin-5': 'iso-8859-9',
'latin_6': 'iso-8859-10',
'latin-6': 'iso-8859-10',
'latin_7': 'iso-8859-13',
'latin-7': 'iso-8859-13',
'latin_8': 'iso-8859-14',
'latin-8': 'iso-8859-14',
'latin_9': 'iso-8859-15',
'latin-9': 'iso-8859-15',
'latin_10':'iso-8859-16',
'latin-10':'iso-8859-16',
'cp949': 'ks_c_5601-1987',
'euc_jp': 'euc-jp',
'euc_kr': 'euc-kr',
'ascii': 'us-ascii',
}
# Map charsets to their Unicode codec strings.
CODEC_MAP = {
'gb2312': 'eucgb2312_cn',
'big5': 'big5_tw',
# Hack: We don't want *any* conversion for stuff marked us-ascii, as all
# sorts of garbage might be sent to us in the guise of 7-bit us-ascii.
# Let that stuff pass through without conversion to/from Unicode.
'us-ascii': None,
}
# Convenience functions for extending the above mappings
def add_charset(charset, header_enc=None, body_enc=None, output_charset=None):
"""Add character set properties to the global registry.
charset is the input character set, and must be the canonical name of a
character set.
Optional header_enc and body_enc is either Charset.QP for
quoted-printable, Charset.BASE64 for base64 encoding, Charset.SHORTEST for
the shortest of qp or base64 encoding, or None for no encoding. SHORTEST
is only valid for header_enc. It describes how message headers and
message bodies in the input charset are to be encoded. Default is no
encoding.
Optional output_charset is the character set that the output should be
in. Conversions will proceed from input charset, to Unicode, to the
output charset when the method Charset.convert() is called. The default
is to output in the same character set as the input.
Both input_charset and output_charset must have Unicode codec entries in
the module's charset-to-codec mapping; use add_codec(charset, codecname)
to add codecs the module does not know about. See the codecs module's
documentation for more information.
"""
if body_enc == SHORTEST:
raise ValueError('SHORTEST not allowed for body_enc')
CHARSETS[charset] = (header_enc, body_enc, output_charset)
def add_alias(alias, canonical):
"""Add a character set alias.
alias is the alias name, e.g. latin-1
canonical is the character set's canonical name, e.g. iso-8859-1
"""
ALIASES[alias] = canonical
def add_codec(charset, codecname):
"""Add a codec that map characters in the given charset to/from Unicode.
charset is the canonical name of a character set. codecname is the name
of a Python codec, as appropriate for the second argument to the unicode()
built-in, or to the encode() method of a Unicode string.
"""
CODEC_MAP[charset] = codecname
# Convenience function for encoding strings, taking into account
# that they might be unknown-8bit (ie: have surrogate-escaped bytes)
def _encode(string, codec):
if codec == UNKNOWN8BIT:
return string.encode('ascii', 'surrogateescape')
else:
return string.encode(codec)
class Charset:
"""Map character sets to their email properties.
This class provides information about the requirements imposed on email
for a specific character set. It also provides convenience routines for
converting between character sets, given the availability of the
applicable codecs. Given a character set, it will do its best to provide
information on how to use that character set in an email in an
RFC-compliant way.
Certain character sets must be encoded with quoted-printable or base64
when used in email headers or bodies. Certain character sets must be
converted outright, and are not allowed in email. Instances of this
module expose the following information about a character set:
input_charset: The initial character set specified. Common aliases
are converted to their `official' email names (e.g. latin_1
is converted to iso-8859-1). Defaults to 7-bit us-ascii.
header_encoding: If the character set must be encoded before it can be
used in an email header, this attribute will be set to
Charset.QP (for quoted-printable), Charset.BASE64 (for
base64 encoding), or Charset.SHORTEST for the shortest of
QP or BASE64 encoding. Otherwise, it will be None.
body_encoding: Same as header_encoding, but describes the encoding for the
mail message's body, which indeed may be different than the
header encoding. Charset.SHORTEST is not allowed for
body_encoding.
output_charset: Some character sets must be converted before they can be
used in email headers or bodies. If the input_charset is
one of them, this attribute will contain the name of the
charset output will be converted to. Otherwise, it will
be None.
input_codec: The name of the Python codec used to convert the
input_charset to Unicode. If no conversion codec is
necessary, this attribute will be None.
output_codec: The name of the Python codec used to convert Unicode
to the output_charset. If no conversion codec is necessary,
this attribute will have the same value as the input_codec.
"""
def __init__(self, input_charset=DEFAULT_CHARSET):
# RFC 2046, $4.1.2 says charsets are not case sensitive. We coerce to
# unicode because its .lower() is locale insensitive. If the argument
# is already a unicode, we leave it at that, but ensure that the
# charset is ASCII, as the standard (RFC XXX) requires.
try:
if isinstance(input_charset, str):
input_charset.encode('ascii')
else:
input_charset = str(input_charset, 'ascii')
except UnicodeError:
raise errors.CharsetError(input_charset)
input_charset = input_charset.lower()
# Set the input charset after filtering through the aliases
self.input_charset = ALIASES.get(input_charset, input_charset)
# We can try to guess which encoding and conversion to use by the
# charset_map dictionary. Try that first, but let the user override
# it.
henc, benc, conv = CHARSETS.get(self.input_charset,
(SHORTEST, BASE64, None))
if not conv:
conv = self.input_charset
# Set the attributes, allowing the arguments to override the default.
self.header_encoding = henc
self.body_encoding = benc
self.output_charset = ALIASES.get(conv, conv)
# Now set the codecs. If one isn't defined for input_charset,
# guess and try a Unicode codec with the same name as input_codec.
self.input_codec = CODEC_MAP.get(self.input_charset,
self.input_charset)
self.output_codec = CODEC_MAP.get(self.output_charset,
self.output_charset)
def __str__(self):
return self.input_charset.lower()
__repr__ = __str__
def __eq__(self, other):
return str(self) == str(other).lower()
def get_body_encoding(self):
"""Return the content-transfer-encoding used for body encoding.
This is either the string `quoted-printable' or `base64' depending on
the encoding used, or it is a function in which case you should call
the function with a single argument, the Message object being
encoded. The function should then set the Content-Transfer-Encoding
header itself to whatever is appropriate.
Returns "quoted-printable" if self.body_encoding is QP.
Returns "base64" if self.body_encoding is BASE64.
Returns conversion function otherwise.
"""
assert self.body_encoding != SHORTEST
if self.body_encoding == QP:
return 'quoted-printable'
elif self.body_encoding == BASE64:
return 'base64'
else:
return encode_7or8bit
def get_output_charset(self):
"""Return the output character set.
This is self.output_charset if that is not None, otherwise it is
self.input_charset.
"""
return self.output_charset or self.input_charset
def header_encode(self, string):
"""Header-encode a string by converting it first to bytes.
The type of encoding (base64 or quoted-printable) will be based on
this charset's `header_encoding`.
:param string: A unicode string for the header. It must be possible
to encode this string to bytes using the character set's
output codec.
:return: The encoded string, with RFC 2047 chrome.
"""
codec = self.output_codec or 'us-ascii'
header_bytes = _encode(string, codec)
# 7bit/8bit encodings return the string unchanged (modulo conversions)
encoder_module = self._get_encoder(header_bytes)
if encoder_module is None:
return string
return encoder_module.header_encode(header_bytes, codec)
def header_encode_lines(self, string, maxlengths):
"""Header-encode a string by converting it first to bytes.
This is similar to `header_encode()` except that the string is fit
into maximum line lengths as given by the argument.
:param string: A unicode string for the header. It must be possible
to encode this string to bytes using the character set's
output codec.
:param maxlengths: Maximum line length iterator. Each element
returned from this iterator will provide the next maximum line
length. This parameter is used as an argument to built-in next()
and should never be exhausted. The maximum line lengths should
not count the RFC 2047 chrome. These line lengths are only a
hint; the splitter does the best it can.
:return: Lines of encoded strings, each with RFC 2047 chrome.
"""
# See which encoding we should use.
codec = self.output_codec or 'us-ascii'
header_bytes = _encode(string, codec)
encoder_module = self._get_encoder(header_bytes)
encoder = partial(encoder_module.header_encode, charset=codec)
# Calculate the number of characters that the RFC 2047 chrome will
# contribute to each line.
charset = self.get_output_charset()
extra = len(charset) + RFC2047_CHROME_LEN
# Now comes the hard part. We must encode bytes but we can't split on
# bytes because some character sets are variable length and each
# encoded word must stand on its own. So the problem is you have to
# encode to bytes to figure out this word's length, but you must split
# on characters. This causes two problems: first, we don't know how
# many octets a specific substring of unicode characters will get
# encoded to, and second, we don't know how many ASCII characters
# those octets will get encoded to. Unless we try it. Which seems
# inefficient. In the interest of being correct rather than fast (and
# in the hope that there will be few encoded headers in any such
# message), brute force it. :(
lines = []
current_line = []
maxlen = next(maxlengths) - extra
for character in string:
current_line.append(character)
this_line = EMPTYSTRING.join(current_line)
length = encoder_module.header_length(_encode(this_line, charset))
if length > maxlen:
# This last character doesn't fit so pop it off.
current_line.pop()
# Does nothing fit on the first line?
if not lines and not current_line:
lines.append(None)
else:
separator = (' ' if lines else '')
joined_line = EMPTYSTRING.join(current_line)
header_bytes = _encode(joined_line, codec)
lines.append(encoder(header_bytes))
current_line = [character]
maxlen = next(maxlengths) - extra
joined_line = EMPTYSTRING.join(current_line)
header_bytes = _encode(joined_line, codec)
lines.append(encoder(header_bytes))
return lines
def _get_encoder(self, header_bytes):
if self.header_encoding == BASE64:
return email.base64mime
elif self.header_encoding == QP:
return email.quoprimime
elif self.header_encoding == SHORTEST:
len64 = email.base64mime.header_length(header_bytes)
lenqp = email.quoprimime.header_length(header_bytes)
if len64 < lenqp:
return email.base64mime
else:
return email.quoprimime
else:
return None
def body_encode(self, string):
"""Body-encode a string by converting it first to bytes.
The type of encoding (base64 or quoted-printable) will be based on
self.body_encoding. If body_encoding is None, we assume the
output charset is a 7bit encoding, so re-encoding the decoded
string using the ascii codec produces the correct string version
of the content.
"""
if not string:
return string
if self.body_encoding is BASE64:
if isinstance(string, str):
string = string.encode(self.output_charset)
return email.base64mime.body_encode(string)
elif self.body_encoding is QP:
# quopromime.body_encode takes a string, but operates on it as if
# it were a list of byte codes. For a (minimal) history on why
# this is so, see changeset 0cf700464177. To correctly encode a
# character set, then, we must turn it into pseudo bytes via the
# latin1 charset, which will encode any byte as a single code point
# between 0 and 255, which is what body_encode is expecting.
if isinstance(string, str):
string = string.encode(self.output_charset)
string = string.decode('latin1')
return email.quoprimime.body_encode(string)
else:
if isinstance(string, str):
string = string.encode(self.output_charset).decode('ascii')
return string

250
third_party/python/Lib/email/contentmanager.py vendored Normal file
View file

@ -0,0 +1,250 @@
import binascii
import email.charset
import email.message
import email.errors
from email import quoprimime
class ContentManager:
def __init__(self):
self.get_handlers = {}
self.set_handlers = {}
def add_get_handler(self, key, handler):
self.get_handlers[key] = handler
def get_content(self, msg, *args, **kw):
content_type = msg.get_content_type()
if content_type in self.get_handlers:
return self.get_handlers[content_type](msg, *args, **kw)
maintype = msg.get_content_maintype()
if maintype in self.get_handlers:
return self.get_handlers[maintype](msg, *args, **kw)
if '' in self.get_handlers:
return self.get_handlers[''](msg, *args, **kw)
raise KeyError(content_type)
def add_set_handler(self, typekey, handler):
self.set_handlers[typekey] = handler
def set_content(self, msg, obj, *args, **kw):
if msg.get_content_maintype() == 'multipart':
# XXX: is this error a good idea or not? We can remove it later,
# but we can't add it later, so do it for now.
raise TypeError("set_content not valid on multipart")
handler = self._find_set_handler(msg, obj)
msg.clear_content()
handler(msg, obj, *args, **kw)
def _find_set_handler(self, msg, obj):
full_path_for_error = None
for typ in type(obj).__mro__:
if typ in self.set_handlers:
return self.set_handlers[typ]
qname = typ.__qualname__
modname = getattr(typ, '__module__', '')
full_path = '.'.join((modname, qname)) if modname else qname
if full_path_for_error is None:
full_path_for_error = full_path
if full_path in self.set_handlers:
return self.set_handlers[full_path]
if qname in self.set_handlers:
return self.set_handlers[qname]
name = typ.__name__
if name in self.set_handlers:
return self.set_handlers[name]
if None in self.set_handlers:
return self.set_handlers[None]
raise KeyError(full_path_for_error)
raw_data_manager = ContentManager()
def get_text_content(msg, errors='replace'):
content = msg.get_payload(decode=True)
charset = msg.get_param('charset', 'ASCII')
return content.decode(charset, errors=errors)
raw_data_manager.add_get_handler('text', get_text_content)
def get_non_text_content(msg):
return msg.get_payload(decode=True)
for maintype in 'audio image video application'.split():
raw_data_manager.add_get_handler(maintype, get_non_text_content)
def get_message_content(msg):
return msg.get_payload(0)
for subtype in 'rfc822 external-body'.split():
raw_data_manager.add_get_handler('message/'+subtype, get_message_content)
def get_and_fixup_unknown_message_content(msg):
# If we don't understand a message subtype, we are supposed to treat it as
# if it were application/octet-stream, per
# tools.ietf.org/html/rfc2046#section-5.2.4. Feedparser doesn't do that,
# so do our best to fix things up. Note that it is *not* appropriate to
# model message/partial content as Message objects, so they are handled
# here as well. (How to reassemble them is out of scope for this comment :)
return bytes(msg.get_payload(0))
raw_data_manager.add_get_handler('message',
get_and_fixup_unknown_message_content)
def _prepare_set(msg, maintype, subtype, headers):
msg['Content-Type'] = '/'.join((maintype, subtype))
if headers:
if not hasattr(headers[0], 'name'):
mp = msg.policy
headers = [mp.header_factory(*mp.header_source_parse([header]))
for header in headers]
try:
for header in headers:
if header.defects:
raise header.defects[0]
msg[header.name] = header
except email.errors.HeaderDefect as exc:
raise ValueError("Invalid header: {}".format(
header.fold(policy=msg.policy))) from exc
def _finalize_set(msg, disposition, filename, cid, params):
if disposition is None and filename is not None:
disposition = 'attachment'
if disposition is not None:
msg['Content-Disposition'] = disposition
if filename is not None:
msg.set_param('filename',
filename,
header='Content-Disposition',
replace=True)
if cid is not None:
msg['Content-ID'] = cid
if params is not None:
for key, value in params.items():
msg.set_param(key, value)
# XXX: This is a cleaned-up version of base64mime.body_encode (including a bug
# fix in the calculation of unencoded_bytes_per_line). It would be nice to
# drop both this and quoprimime.body_encode in favor of enhanced binascii
# routines that accepted a max_line_length parameter.
def _encode_base64(data, max_line_length):
encoded_lines = []
unencoded_bytes_per_line = max_line_length // 4 * 3
for i in range(0, len(data), unencoded_bytes_per_line):
thisline = data[i:i+unencoded_bytes_per_line]
encoded_lines.append(binascii.b2a_base64(thisline).decode('ascii'))
return ''.join(encoded_lines)
def _encode_text(string, charset, cte, policy):
lines = string.encode(charset).splitlines()
linesep = policy.linesep.encode('ascii')
def embedded_body(lines): return linesep.join(lines) + linesep
def normal_body(lines): return b'\n'.join(lines) + b'\n'
if cte==None:
# Use heuristics to decide on the "best" encoding.
try:
return '7bit', normal_body(lines).decode('ascii')
except UnicodeDecodeError:
pass
if (policy.cte_type == '8bit' and
max(len(x) for x in lines) <= policy.max_line_length):
return '8bit', normal_body(lines).decode('ascii', 'surrogateescape')
sniff = embedded_body(lines[:10])
sniff_qp = quoprimime.body_encode(sniff.decode('latin-1'),
policy.max_line_length)
sniff_base64 = binascii.b2a_base64(sniff)
# This is a little unfair to qp; it includes lineseps, base64 doesn't.
if len(sniff_qp) > len(sniff_base64):
cte = 'base64'
else:
cte = 'quoted-printable'
if len(lines) <= 10:
return cte, sniff_qp
if cte == '7bit':
data = normal_body(lines).decode('ascii')
elif cte == '8bit':
data = normal_body(lines).decode('ascii', 'surrogateescape')
elif cte == 'quoted-printable':
data = quoprimime.body_encode(normal_body(lines).decode('latin-1'),
policy.max_line_length)
elif cte == 'base64':
data = _encode_base64(embedded_body(lines), policy.max_line_length)
else:
raise ValueError("Unknown content transfer encoding {}".format(cte))
return cte, data
def set_text_content(msg, string, subtype="plain", charset='utf-8', cte=None,
disposition=None, filename=None, cid=None,
params=None, headers=None):
_prepare_set(msg, 'text', subtype, headers)
cte, payload = _encode_text(string, charset, cte, msg.policy)
msg.set_payload(payload)
msg.set_param('charset',
email.charset.ALIASES.get(charset, charset),
replace=True)
msg['Content-Transfer-Encoding'] = cte
_finalize_set(msg, disposition, filename, cid, params)
raw_data_manager.add_set_handler(str, set_text_content)
def set_message_content(msg, message, subtype="rfc822", cte=None,
disposition=None, filename=None, cid=None,
params=None, headers=None):
if subtype == 'partial':
raise ValueError("message/partial is not supported for Message objects")
if subtype == 'rfc822':
if cte not in (None, '7bit', '8bit', 'binary'):
# http://tools.ietf.org/html/rfc2046#section-5.2.1 mandate.
raise ValueError(
"message/rfc822 parts do not support cte={}".format(cte))
# 8bit will get coerced on serialization if policy.cte_type='7bit'. We
# may end up claiming 8bit when it isn't needed, but the only negative
# result of that should be a gateway that needs to coerce to 7bit
# having to look through the whole embedded message to discover whether
# or not it actually has to do anything.
cte = '8bit' if cte is None else cte
elif subtype == 'external-body':
if cte not in (None, '7bit'):
# http://tools.ietf.org/html/rfc2046#section-5.2.3 mandate.
raise ValueError(
"message/external-body parts do not support cte={}".format(cte))
cte = '7bit'
elif cte is None:
# http://tools.ietf.org/html/rfc2046#section-5.2.4 says all future
# subtypes should be restricted to 7bit, so assume that.
cte = '7bit'
_prepare_set(msg, 'message', subtype, headers)
msg.set_payload([message])
msg['Content-Transfer-Encoding'] = cte
_finalize_set(msg, disposition, filename, cid, params)
raw_data_manager.add_set_handler(email.message.Message, set_message_content)
def set_bytes_content(msg, data, maintype, subtype, cte='base64',
disposition=None, filename=None, cid=None,
params=None, headers=None):
_prepare_set(msg, maintype, subtype, headers)
if cte == 'base64':
data = _encode_base64(data, max_line_length=msg.policy.max_line_length)
elif cte == 'quoted-printable':
# XXX: quoprimime.body_encode won't encode newline characters in data,
# so we can't use it. This means max_line_length is ignored. Another
# bug to fix later. (Note: encoders.quopri is broken on line ends.)
data = binascii.b2a_qp(data, istext=False, header=False, quotetabs=True)
data = data.decode('ascii')
elif cte == '7bit':
# Make sure it really is only ASCII. The early warning here seems
# worth the overhead...if you care write your own content manager :).
data.encode('ascii')
elif cte in ('8bit', 'binary'):
data = data.decode('ascii', 'surrogateescape')
msg.set_payload(data)
msg['Content-Transfer-Encoding'] = cte
_finalize_set(msg, disposition, filename, cid, params)
for typ in (bytes, bytearray, memoryview):
raw_data_manager.add_set_handler(typ, set_bytes_content)

69
third_party/python/Lib/email/encoders.py vendored Normal file
View file

@ -0,0 +1,69 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Encodings and related functions."""
__all__ = [
'encode_7or8bit',
'encode_base64',
'encode_noop',
'encode_quopri',
]
from base64 import encodebytes as _bencode
from quopri import encodestring as _encodestring
def _qencode(s):
enc = _encodestring(s, quotetabs=True)
# Must encode spaces, which quopri.encodestring() doesn't do
return enc.replace(b' ', b'=20')
def encode_base64(msg):
"""Encode the message's payload in Base64.
Also, add an appropriate Content-Transfer-Encoding header.
"""
orig = msg.get_payload(decode=True)
encdata = str(_bencode(orig), 'ascii')
msg.set_payload(encdata)
msg['Content-Transfer-Encoding'] = 'base64'
def encode_quopri(msg):
"""Encode the message's payload in quoted-printable.
Also, add an appropriate Content-Transfer-Encoding header.
"""
orig = msg.get_payload(decode=True)
encdata = _qencode(orig)
msg.set_payload(encdata)
msg['Content-Transfer-Encoding'] = 'quoted-printable'
def encode_7or8bit(msg):
"""Set the Content-Transfer-Encoding header to 7bit or 8bit."""
orig = msg.get_payload(decode=True)
if orig is None:
# There's no payload. For backwards compatibility we use 7bit
msg['Content-Transfer-Encoding'] = '7bit'
return
# We play a trick to make this go fast. If decoding from ASCII succeeds,
# we know the data must be 7bit, otherwise treat it as 8bit.
try:
orig.decode('ascii')
except UnicodeError:
msg['Content-Transfer-Encoding'] = '8bit'
else:
msg['Content-Transfer-Encoding'] = '7bit'
def encode_noop(msg):
"""Do nothing."""

110
third_party/python/Lib/email/errors.py vendored Normal file
View file

@ -0,0 +1,110 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""email package exception classes."""
class MessageError(Exception):
"""Base class for errors in the email package."""
class MessageParseError(MessageError):
"""Base class for message parsing errors."""
class HeaderParseError(MessageParseError):
"""Error while parsing headers."""
class BoundaryError(MessageParseError):
"""Couldn't find terminating boundary."""
class MultipartConversionError(MessageError, TypeError):
"""Conversion to a multipart is prohibited."""
class CharsetError(MessageError):
"""An illegal charset was given."""
# These are parsing defects which the parser was able to work around.
class MessageDefect(ValueError):
"""Base class for a message defect."""
def __init__(self, line=None):
if line is not None:
super().__init__(line)
self.line = line
class NoBoundaryInMultipartDefect(MessageDefect):
"""A message claimed to be a multipart but had no boundary parameter."""
class StartBoundaryNotFoundDefect(MessageDefect):
"""The claimed start boundary was never found."""
class CloseBoundaryNotFoundDefect(MessageDefect):
"""A start boundary was found, but not the corresponding close boundary."""
class FirstHeaderLineIsContinuationDefect(MessageDefect):
"""A message had a continuation line as its first header line."""
class MisplacedEnvelopeHeaderDefect(MessageDefect):
"""A 'Unix-from' header was found in the middle of a header block."""
class MissingHeaderBodySeparatorDefect(MessageDefect):
"""Found line with no leading whitespace and no colon before blank line."""
# XXX: backward compatibility, just in case (it was never emitted).
MalformedHeaderDefect = MissingHeaderBodySeparatorDefect
class MultipartInvariantViolationDefect(MessageDefect):
"""A message claimed to be a multipart but no subparts were found."""
class InvalidMultipartContentTransferEncodingDefect(MessageDefect):
"""An invalid content transfer encoding was set on the multipart itself."""
class UndecodableBytesDefect(MessageDefect):
"""Header contained bytes that could not be decoded"""
class InvalidBase64PaddingDefect(MessageDefect):
"""base64 encoded sequence had an incorrect length"""
class InvalidBase64CharactersDefect(MessageDefect):
"""base64 encoded sequence had characters not in base64 alphabet"""
class InvalidBase64LengthDefect(MessageDefect):
"""base64 encoded sequence had invalid length (1 mod 4)"""
# These errors are specific to header parsing.
class HeaderDefect(MessageDefect):
"""Base class for a header defect."""
def __init__(self, *args, **kw):
super().__init__(*args, **kw)
class InvalidHeaderDefect(HeaderDefect):
"""Header is not valid, message gives details."""
class HeaderMissingRequiredValue(HeaderDefect):
"""A header that must have a value had none"""
class NonPrintableDefect(HeaderDefect):
"""ASCII characters outside the ascii-printable range found"""
def __init__(self, non_printables):
super().__init__(non_printables)
self.non_printables = non_printables
def __str__(self):
return ("the following ASCII non-printables found in header: "
"{}".format(self.non_printables))
class ObsoleteHeaderDefect(HeaderDefect):
"""Header uses syntax declared obsolete by RFC 5322"""
class NonASCIILocalPartDefect(HeaderDefect):
"""local_part contains non-ASCII characters"""
# This defect only occurs during unicode parsing, not when
# parsing messages decoded from binary.

536
third_party/python/Lib/email/feedparser.py vendored Normal file
View file

@ -0,0 +1,536 @@
# Copyright (C) 2004-2006 Python Software Foundation
# Authors: Baxter, Wouters and Warsaw
# Contact: email-sig@python.org
"""FeedParser - An email feed parser.
The feed parser implements an interface for incrementally parsing an email
message, line by line. This has advantages for certain applications, such as
those reading email messages off a socket.
FeedParser.feed() is the primary interface for pushing new data into the
parser. It returns when there's nothing more it can do with the available
data. When you have no more data to push into the parser, call .close().
This completes the parsing and returns the root message object.
The other advantage of this parser is that it will never raise a parsing
exception. Instead, when it finds something unexpected, it adds a 'defect' to
the current message. Defects are just instances that live on the message
object's .defects attribute.
"""
__all__ = ['FeedParser', 'BytesFeedParser']
import re
from email import errors
from email._policybase import compat32
from collections import deque
from io import StringIO
NLCRE = re.compile(r'\r\n|\r|\n')
NLCRE_bol = re.compile(r'(\r\n|\r|\n)')
NLCRE_eol = re.compile(r'(\r\n|\r|\n)\Z')
NLCRE_crack = re.compile(r'(\r\n|\r|\n)')
# RFC 2822 $3.6.8 Optional fields. ftext is %d33-57 / %d59-126, Any character
# except controls, SP, and ":".
headerRE = re.compile(r'^(From |[\041-\071\073-\176]*:|[\t ])')
EMPTYSTRING = ''
NL = '\n'
NeedMoreData = object()
class BufferedSubFile(object):
"""A file-ish object that can have new data loaded into it.
You can also push and pop line-matching predicates onto a stack. When the
current predicate matches the current line, a false EOF response
(i.e. empty string) is returned instead. This lets the parser adhere to a
simple abstraction -- it parses until EOF closes the current message.
"""
def __init__(self):
# Text stream of the last partial line pushed into this object.
# See issue 22233 for why this is a text stream and not a list.
self._partial = StringIO(newline='')
# A deque of full, pushed lines
self._lines = deque()
# The stack of false-EOF checking predicates.
self._eofstack = []
# A flag indicating whether the file has been closed or not.
self._closed = False
def push_eof_matcher(self, pred):
self._eofstack.append(pred)
def pop_eof_matcher(self):
return self._eofstack.pop()
def close(self):
# Don't forget any trailing partial line.
self._partial.seek(0)
self.pushlines(self._partial.readlines())
self._partial.seek(0)
self._partial.truncate()
self._closed = True
def readline(self):
if not self._lines:
if self._closed:
return ''
return NeedMoreData
# Pop the line off the stack and see if it matches the current
# false-EOF predicate.
line = self._lines.popleft()
# RFC 2046, section 5.1.2 requires us to recognize outer level
# boundaries at any level of inner nesting. Do this, but be sure it's
# in the order of most to least nested.
for ateof in reversed(self._eofstack):
if ateof(line):
# We're at the false EOF. But push the last line back first.
self._lines.appendleft(line)
return ''
return line
def unreadline(self, line):
# Let the consumer push a line back into the buffer.
assert line is not NeedMoreData
self._lines.appendleft(line)
def push(self, data):
"""Push some new data into this object."""
self._partial.write(data)
if '\n' not in data and '\r' not in data:
# No new complete lines, wait for more.
return
# Crack into lines, preserving the linesep characters.
self._partial.seek(0)
parts = self._partial.readlines()
self._partial.seek(0)
self._partial.truncate()
# If the last element of the list does not end in a newline, then treat
# it as a partial line. We only check for '\n' here because a line
# ending with '\r' might be a line that was split in the middle of a
# '\r\n' sequence (see bugs 1555570 and 1721862).
if not parts[-1].endswith('\n'):
self._partial.write(parts.pop())
self.pushlines(parts)
def pushlines(self, lines):
self._lines.extend(lines)
def __iter__(self):
return self
def __next__(self):
line = self.readline()
if line == '':
raise StopIteration
return line
class FeedParser:
"""A feed-style parser of email."""
def __init__(self, _factory=None, *, policy=compat32):
"""_factory is called with no arguments to create a new message obj
The policy keyword specifies a policy object that controls a number of
aspects of the parser's operation. The default policy maintains
backward compatibility.
"""
self.policy = policy
self._old_style_factory = False
if _factory is None:
if policy.message_factory is None:
from email.message import Message
self._factory = Message
else:
self._factory = policy.message_factory
else:
self._factory = _factory
try:
_factory(policy=self.policy)
except TypeError:
# Assume this is an old-style factory
self._old_style_factory = True
self._input = BufferedSubFile()
self._msgstack = []
self._parse = self._parsegen().__next__
self._cur = None
self._last = None
self._headersonly = False
# Non-public interface for supporting Parser's headersonly flag
def _set_headersonly(self):
self._headersonly = True
def feed(self, data):
"""Push more data into the parser."""
self._input.push(data)
self._call_parse()
def _call_parse(self):
try:
self._parse()
except StopIteration:
pass
def close(self):
"""Parse all remaining data and return the root message object."""
self._input.close()
self._call_parse()
root = self._pop_message()
assert not self._msgstack
# Look for final set of defects
if root.get_content_maintype() == 'multipart' \
and not root.is_multipart():
defect = errors.MultipartInvariantViolationDefect()
self.policy.handle_defect(root, defect)
return root
def _new_message(self):
if self._old_style_factory:
msg = self._factory()
else:
msg = self._factory(policy=self.policy)
if self._cur and self._cur.get_content_type() == 'multipart/digest':
msg.set_default_type('message/rfc822')
if self._msgstack:
self._msgstack[-1].attach(msg)
self._msgstack.append(msg)
self._cur = msg
self._last = msg
def _pop_message(self):
retval = self._msgstack.pop()
if self._msgstack:
self._cur = self._msgstack[-1]
else:
self._cur = None
return retval
def _parsegen(self):
# Create a new message and start by parsing headers.
self._new_message()
headers = []
# Collect the headers, searching for a line that doesn't match the RFC
# 2822 header or continuation pattern (including an empty line).
for line in self._input:
if line is NeedMoreData:
yield NeedMoreData
continue
if not headerRE.match(line):
# If we saw the RFC defined header/body separator
# (i.e. newline), just throw it away. Otherwise the line is
# part of the body so push it back.
if not NLCRE.match(line):
defect = errors.MissingHeaderBodySeparatorDefect()
self.policy.handle_defect(self._cur, defect)
self._input.unreadline(line)
break
headers.append(line)
# Done with the headers, so parse them and figure out what we're
# supposed to see in the body of the message.
self._parse_headers(headers)
# Headers-only parsing is a backwards compatibility hack, which was
# necessary in the older parser, which could raise errors. All
# remaining lines in the input are thrown into the message body.
if self._headersonly:
lines = []
while True:
line = self._input.readline()
if line is NeedMoreData:
yield NeedMoreData
continue
if line == '':
break
lines.append(line)
self._cur.set_payload(EMPTYSTRING.join(lines))
return
if self._cur.get_content_type() == 'message/delivery-status':
# message/delivery-status contains blocks of headers separated by
# a blank line. We'll represent each header block as a separate
# nested message object, but the processing is a bit different
# than standard message/* types because there is no body for the
# nested messages. A blank line separates the subparts.
while True:
self._input.push_eof_matcher(NLCRE.match)
for retval in self._parsegen():
if retval is NeedMoreData:
yield NeedMoreData
continue
break
msg = self._pop_message()
# We need to pop the EOF matcher in order to tell if we're at
# the end of the current file, not the end of the last block
# of message headers.
self._input.pop_eof_matcher()
# The input stream must be sitting at the newline or at the
# EOF. We want to see if we're at the end of this subpart, so
# first consume the blank line, then test the next line to see
# if we're at this subpart's EOF.
while True:
line = self._input.readline()
if line is NeedMoreData:
yield NeedMoreData
continue
break
while True:
line = self._input.readline()
if line is NeedMoreData:
yield NeedMoreData
continue
break
if line == '':
break
# Not at EOF so this is a line we're going to need.
self._input.unreadline(line)
return
if self._cur.get_content_maintype() == 'message':
# The message claims to be a message/* type, then what follows is
# another RFC 2822 message.
for retval in self._parsegen():
if retval is NeedMoreData:
yield NeedMoreData
continue
break
self._pop_message()
return
if self._cur.get_content_maintype() == 'multipart':
boundary = self._cur.get_boundary()
if boundary is None:
# The message /claims/ to be a multipart but it has not
# defined a boundary. That's a problem which we'll handle by
# reading everything until the EOF and marking the message as
# defective.
defect = errors.NoBoundaryInMultipartDefect()
self.policy.handle_defect(self._cur, defect)
lines = []
for line in self._input:
if line is NeedMoreData:
yield NeedMoreData
continue
lines.append(line)
self._cur.set_payload(EMPTYSTRING.join(lines))
return
# Make sure a valid content type was specified per RFC 2045:6.4.
if (self._cur.get('content-transfer-encoding', '8bit').lower()
not in ('7bit', '8bit', 'binary')):
defect = errors.InvalidMultipartContentTransferEncodingDefect()
self.policy.handle_defect(self._cur, defect)
# Create a line match predicate which matches the inter-part
# boundary as well as the end-of-multipart boundary. Don't push
# this onto the input stream until we've scanned past the
# preamble.
separator = '--' + boundary
boundaryre = re.compile(
'(?P<sep>' + re.escape(separator) +
r')(?P<end>--)?(?P<ws>[ \t]*)(?P<linesep>\r\n|\r|\n)?$')
capturing_preamble = True
preamble = []
linesep = False
close_boundary_seen = False
while True:
line = self._input.readline()
if line is NeedMoreData:
yield NeedMoreData
continue
if line == '':
break
mo = boundaryre.match(line)
if mo:
# If we're looking at the end boundary, we're done with
# this multipart. If there was a newline at the end of
# the closing boundary, then we need to initialize the
# epilogue with the empty string (see below).
if mo.group('end'):
close_boundary_seen = True
linesep = mo.group('linesep')
break
# We saw an inter-part boundary. Were we in the preamble?
if capturing_preamble:
if preamble:
# According to RFC 2046, the last newline belongs
# to the boundary.
lastline = preamble[-1]
eolmo = NLCRE_eol.search(lastline)
if eolmo:
preamble[-1] = lastline[:-len(eolmo.group(0))]
self._cur.preamble = EMPTYSTRING.join(preamble)
capturing_preamble = False
self._input.unreadline(line)
continue
# We saw a boundary separating two parts. Consume any
# multiple boundary lines that may be following. Our
# interpretation of RFC 2046 BNF grammar does not produce
# body parts within such double boundaries.
while True:
line = self._input.readline()
if line is NeedMoreData:
yield NeedMoreData
continue
mo = boundaryre.match(line)
if not mo:
self._input.unreadline(line)
break
# Recurse to parse this subpart; the input stream points
# at the subpart's first line.
self._input.push_eof_matcher(boundaryre.match)
for retval in self._parsegen():
if retval is NeedMoreData:
yield NeedMoreData
continue
break
# Because of RFC 2046, the newline preceding the boundary
# separator actually belongs to the boundary, not the
# previous subpart's payload (or epilogue if the previous
# part is a multipart).
if self._last.get_content_maintype() == 'multipart':
epilogue = self._last.epilogue
if epilogue == '':
self._last.epilogue = None
elif epilogue is not None:
mo = NLCRE_eol.search(epilogue)
if mo:
end = len(mo.group(0))
self._last.epilogue = epilogue[:-end]
else:
payload = self._last._payload
if isinstance(payload, str):
mo = NLCRE_eol.search(payload)
if mo:
payload = payload[:-len(mo.group(0))]
self._last._payload = payload
self._input.pop_eof_matcher()
self._pop_message()
# Set the multipart up for newline cleansing, which will
# happen if we're in a nested multipart.
self._last = self._cur
else:
# I think we must be in the preamble
assert capturing_preamble
preamble.append(line)
# We've seen either the EOF or the end boundary. If we're still
# capturing the preamble, we never saw the start boundary. Note
# that as a defect and store the captured text as the payload.
if capturing_preamble:
defect = errors.StartBoundaryNotFoundDefect()
self.policy.handle_defect(self._cur, defect)
self._cur.set_payload(EMPTYSTRING.join(preamble))
epilogue = []
for line in self._input:
if line is NeedMoreData:
yield NeedMoreData
continue
self._cur.epilogue = EMPTYSTRING.join(epilogue)
return
# If we're not processing the preamble, then we might have seen
# EOF without seeing that end boundary...that is also a defect.
if not close_boundary_seen:
defect = errors.CloseBoundaryNotFoundDefect()
self.policy.handle_defect(self._cur, defect)
return
# Everything from here to the EOF is epilogue. If the end boundary
# ended in a newline, we'll need to make sure the epilogue isn't
# None
if linesep:
epilogue = ['']
else:
epilogue = []
for line in self._input:
if line is NeedMoreData:
yield NeedMoreData
continue
epilogue.append(line)
# Any CRLF at the front of the epilogue is not technically part of
# the epilogue. Also, watch out for an empty string epilogue,
# which means a single newline.
if epilogue:
firstline = epilogue[0]
bolmo = NLCRE_bol.match(firstline)
if bolmo:
epilogue[0] = firstline[len(bolmo.group(0)):]
self._cur.epilogue = EMPTYSTRING.join(epilogue)
return
# Otherwise, it's some non-multipart type, so the entire rest of the
# file contents becomes the payload.
lines = []
for line in self._input:
if line is NeedMoreData:
yield NeedMoreData
continue
lines.append(line)
self._cur.set_payload(EMPTYSTRING.join(lines))
def _parse_headers(self, lines):
# Passed a list of lines that make up the headers for the current msg
lastheader = ''
lastvalue = []
for lineno, line in enumerate(lines):
# Check for continuation
if line[0] in ' \t':
if not lastheader:
# The first line of the headers was a continuation. This
# is illegal, so let's note the defect, store the illegal
# line, and ignore it for purposes of headers.
defect = errors.FirstHeaderLineIsContinuationDefect(line)
self.policy.handle_defect(self._cur, defect)
continue
lastvalue.append(line)
continue
if lastheader:
self._cur.set_raw(*self.policy.header_source_parse(lastvalue))
lastheader, lastvalue = '', []
# Check for envelope header, i.e. unix-from
if line.startswith('From '):
if lineno == 0:
# Strip off the trailing newline
mo = NLCRE_eol.search(line)
if mo:
line = line[:-len(mo.group(0))]
self._cur.set_unixfrom(line)
continue
elif lineno == len(lines) - 1:
# Something looking like a unix-from at the end - it's
# probably the first line of the body, so push back the
# line and stop.
self._input.unreadline(line)
return
else:
# Weirdly placed unix-from line. Note this as a defect
# and ignore it.
defect = errors.MisplacedEnvelopeHeaderDefect(line)
self._cur.defects.append(defect)
continue
# Split the line on the colon separating field name from value.
# There will always be a colon, because if there wasn't the part of
# the parser that calls us would have started parsing the body.
i = line.find(':')
# If the colon is on the start of the line the header is clearly
# malformed, but we might be able to salvage the rest of the
# message. Track the error but keep going.
if i == 0:
defect = errors.InvalidHeaderDefect("Missing header name.")
self._cur.defects.append(defect)
continue
assert i>0, "_parse_headers fed line with no : and no leading WS"
lastheader = line[:i]
lastvalue = [line]
# Done with all the lines, so handle the last header.
if lastheader:
self._cur.set_raw(*self.policy.header_source_parse(lastvalue))
class BytesFeedParser(FeedParser):
"""Like FeedParser, but feed accepts bytes."""
def feed(self, data):
super().feed(data.decode('ascii', 'surrogateescape'))

508
third_party/python/Lib/email/generator.py vendored Normal file
View file

@ -0,0 +1,508 @@
# 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
from copy import deepcopy
from io import StringIO, BytesIO
from email.utils import _has_surrogates
UNDERSCORE = '_'
NL = '\n' # XXX: no longer used by the code below.
NLCRE = re.compile(r'\r\n|\r|\n')
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_=None, maxheaderlen=None, *,
policy=None):
"""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 if policy
is not set), 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.
The policy keyword specifies a policy object that controls a number of
aspects of the generator's operation. If no policy is specified,
the policy associated with the Message object passed to the
flatten method is used.
"""
if mangle_from_ is None:
mangle_from_ = True if policy is None else policy.mangle_from_
self._fp = outfp
self._mangle_from_ = mangle_from_
self.maxheaderlen = maxheaderlen
self.policy = policy
def write(self, s):
# Just delegate to the file object
self._fp.write(s)
def flatten(self, msg, unixfrom=False, linesep=None):
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 determined by the policy specified
when the Generator instance was created or, if none was specified,
from the policy associated with the msg.
"""
# 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.
policy = msg.policy if self.policy is None else self.policy
if linesep is not None:
policy = policy.clone(linesep=linesep)
if self.maxheaderlen is not None:
policy = policy.clone(max_line_length=self.maxheaderlen)
self._NL = policy.linesep
self._encoded_NL = self._encode(self._NL)
self._EMPTY = ''
self._encoded_EMPTY = self._encode(self._EMPTY)
# Because we use clone (below) when we recursively process message
# subparts, and because clone uses the computed policy (not None),
# submessages will automatically get set to the computed policy when
# they are processed by this code.
old_gen_policy = self.policy
old_msg_policy = msg.policy
try:
self.policy = policy
msg.policy = policy
if unixfrom:
ufrom = msg.get_unixfrom()
if not ufrom:
ufrom = 'From nobody ' + time.ctime(time.time())
self.write(ufrom + self._NL)
self._write(msg)
finally:
self.policy = old_gen_policy
msg.policy = old_msg_policy
def clone(self, fp):
"""Clone this generator with the exact same options."""
return self.__class__(fp,
self._mangle_from_,
None, # Use policy setting, which we've adjusted
policy=self.policy)
#
# 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.
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_lines(self, lines):
# We have to transform the line endings.
if not lines:
return
lines = NLCRE.split(lines)
for line in lines[:-1]:
self.write(line)
self.write(self._NL)
if lines[-1]:
self.write(lines[-1])
# XXX logic tells me this else should be needed, but the tests fail
# with it and pass without it. (NLCRE.split ends with a blank element
# if and only if there was a trailing newline.)
#else:
# self.write(self._NL)
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._munge_cte = None
self._fp = sfp = self._new_buffer()
self._dispatch(msg)
finally:
self._fp = oldfp
munge_cte = self._munge_cte
del self._munge_cte
# If we munged the cte, copy the message again and re-fix the CTE.
if munge_cte:
msg = deepcopy(msg)
msg.replace_header('content-transfer-encoding', munge_cte[0])
msg.replace_header('content-type', munge_cte[1])
# 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.raw_items():
self.write(self.policy.fold(h, v))
# 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:
# XXX: This copy stuff is an ugly hack to avoid modifying the
# existing message.
msg = deepcopy(msg)
del msg['content-transfer-encoding']
msg.set_payload(payload, charset)
payload = msg.get_payload()
self._munge_cte = (msg['content-transfer-encoding'],
msg['content-type'])
if self._mangle_from_:
payload = fcre.sub('>From ', payload)
self._write_lines(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:
if self._mangle_from_:
preamble = fcre.sub('>From ', msg.preamble)
else:
preamble = msg.preamble
self._write_lines(preamble)
self.write(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 + '--' + self._NL)
if msg.epilogue is not None:
if self._mangle_from_:
epilogue = fcre.sub('>From ', msg.epilogue)
else:
epilogue = msg.epilogue
self._write_lines(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.
p = self.policy
self.policy = p.clone(max_line_length=0)
try:
self._handle_multipart(msg)
finally:
self.policy = p
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._payload
if isinstance(payload, list):
g.flatten(msg.get_payload(0), unixfrom=False, linesep=self._NL)
payload = s.getvalue()
else:
payload = self._encode(payload)
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_boundary = 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. If the policy has
cte_type set to 7bit, then the message is transformed such that the
non-ASCII bytes are properly content transfer encoded, using the charset
unknown-8bit.
The outfp object must accept bytes in its write method.
"""
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.raw_items():
self._fp.write(self.policy.fold_binary(h, v))
# 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) and not self.policy.cte_type=='7bit':
if self._mangle_from_:
msg._payload = fcre.sub(">From ", msg._payload)
self._write_lines(msg._payload)
else:
super(BytesGenerator,self)._handle_text(msg)
# Default body handler
_writeBody = _handle_text
@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_=None, maxheaderlen=None, fmt=None, *,
policy=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,
policy=policy)
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

578
third_party/python/Lib/email/header.py vendored Normal file
View file

@ -0,0 +1,578 @@
# Copyright (C) 2002-2007 Python Software Foundation
# Author: Ben Gertzfield, Barry Warsaw
# Contact: email-sig@python.org
"""Header encoding and decoding functionality."""
__all__ = [
'Header',
'decode_header',
'make_header',
]
import re
import binascii
import email.quoprimime
import email.base64mime
from email.errors import HeaderParseError
from email import charset as _charset
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.
_embedded_header = re.compile(r'\n[^ \t]+:')
# Helpers
_max_append = email.quoprimime._max_append
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.
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 = email.quoprimime.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 = email.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:
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 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])
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 _embedded_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:
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__()

594
third_party/python/Lib/email/headerregistry.py vendored Normal file
View file

@ -0,0 +1,594 @@
"""Representing and manipulating email headers via custom objects.
This module provides an implementation of the HeaderRegistry API.
The implementation is designed to flexibly follow RFC5322 rules.
Eventually HeaderRegistry will be a public API, but it isn't yet,
and will probably change some before that happens.
"""
from types import MappingProxyType
from email import utils
from email import errors
from email import _header_value_parser as parser
class Address:
def __init__(self, display_name='', username='', domain='', addr_spec=None):
"""Create an object representing a full email address.
An address can have a 'display_name', a 'username', and a 'domain'. In
addition to specifying the username and domain separately, they may be
specified together by using the addr_spec keyword *instead of* the
username and domain keywords. If an addr_spec string is specified it
must be properly quoted according to RFC 5322 rules; an error will be
raised if it is not.
An Address object has display_name, username, domain, and addr_spec
attributes, all of which are read-only. The addr_spec and the string
value of the object are both quoted according to RFC5322 rules, but
without any Content Transfer Encoding.
"""
inputs = ''.join(filter(None, (display_name, username, domain, addr_spec)))
if '\r' in inputs or '\n' in inputs:
raise ValueError("invalid arguments; address parts cannot contain CR or LF")
# This clause with its potential 'raise' may only happen when an
# application program creates an Address object using an addr_spec
# keyword. The email library code itself must always supply username
# and domain.
if addr_spec is not None:
if username or domain:
raise TypeError("addrspec specified when username and/or "
"domain also specified")
a_s, rest = parser.get_addr_spec(addr_spec)
if rest:
raise ValueError("Invalid addr_spec; only '{}' "
"could be parsed from '{}'".format(
a_s, addr_spec))
if a_s.all_defects:
raise a_s.all_defects[0]
username = a_s.local_part
domain = a_s.domain
self._display_name = display_name
self._username = username
self._domain = domain
@property
def display_name(self):
return self._display_name
@property
def username(self):
return self._username
@property
def domain(self):
return self._domain
@property
def addr_spec(self):
"""The addr_spec (username@domain) portion of the address, quoted
according to RFC 5322 rules, but with no Content Transfer Encoding.
"""
nameset = set(self.username)
if len(nameset) > len(nameset-parser.DOT_ATOM_ENDS):
lp = parser.quote_string(self.username)
else:
lp = self.username
if self.domain:
return lp + '@' + self.domain
if not lp:
return '<>'
return lp
def __repr__(self):
return "{}(display_name={!r}, username={!r}, domain={!r})".format(
self.__class__.__name__,
self.display_name, self.username, self.domain)
def __str__(self):
nameset = set(self.display_name)
if len(nameset) > len(nameset-parser.SPECIALS):
disp = parser.quote_string(self.display_name)
else:
disp = self.display_name
if disp:
addr_spec = '' if self.addr_spec=='<>' else self.addr_spec
return "{} <{}>".format(disp, addr_spec)
return self.addr_spec
def __eq__(self, other):
if type(other) != type(self):
return False
return (self.display_name == other.display_name and
self.username == other.username and
self.domain == other.domain)
class Group:
def __init__(self, display_name=None, addresses=None):
"""Create an object representing an address group.
An address group consists of a display_name followed by colon and a
list of addresses (see Address) terminated by a semi-colon. The Group
is created by specifying a display_name and a possibly empty list of
Address objects. A Group can also be used to represent a single
address that is not in a group, which is convenient when manipulating
lists that are a combination of Groups and individual Addresses. In
this case the display_name should be set to None. In particular, the
string representation of a Group whose display_name is None is the same
as the Address object, if there is one and only one Address object in
the addresses list.
"""
self._display_name = display_name
self._addresses = tuple(addresses) if addresses else tuple()
@property
def display_name(self):
return self._display_name
@property
def addresses(self):
return self._addresses
def __repr__(self):
return "{}(display_name={!r}, addresses={!r}".format(
self.__class__.__name__,
self.display_name, self.addresses)
def __str__(self):
if self.display_name is None and len(self.addresses)==1:
return str(self.addresses[0])
disp = self.display_name
if disp is not None:
nameset = set(disp)
if len(nameset) > len(nameset-parser.SPECIALS):
disp = parser.quote_string(disp)
adrstr = ", ".join(str(x) for x in self.addresses)
adrstr = ' ' + adrstr if adrstr else adrstr
return "{}:{};".format(disp, adrstr)
def __eq__(self, other):
if type(other) != type(self):
return False
return (self.display_name == other.display_name and
self.addresses == other.addresses)
# Header Classes #
class BaseHeader(str):
"""Base class for message headers.
Implements generic behavior and provides tools for subclasses.
A subclass must define a classmethod named 'parse' that takes an unfolded
value string and a dictionary as its arguments. The dictionary will
contain one key, 'defects', initialized to an empty list. After the call
the dictionary must contain two additional keys: parse_tree, set to the
parse tree obtained from parsing the header, and 'decoded', set to the
string value of the idealized representation of the data from the value.
(That is, encoded words are decoded, and values that have canonical
representations are so represented.)
The defects key is intended to collect parsing defects, which the message
parser will subsequently dispose of as appropriate. The parser should not,
insofar as practical, raise any errors. Defects should be added to the
list instead. The standard header parsers register defects for RFC
compliance issues, for obsolete RFC syntax, and for unrecoverable parsing
errors.
The parse method may add additional keys to the dictionary. In this case
the subclass must define an 'init' method, which will be passed the
dictionary as its keyword arguments. The method should use (usually by
setting them as the value of similarly named attributes) and remove all the
extra keys added by its parse method, and then use super to call its parent
class with the remaining arguments and keywords.
The subclass should also make sure that a 'max_count' attribute is defined
that is either None or 1. XXX: need to better define this API.
"""
def __new__(cls, name, value):
kwds = {'defects': []}
cls.parse(value, kwds)
if utils._has_surrogates(kwds['decoded']):
kwds['decoded'] = utils._sanitize(kwds['decoded'])
self = str.__new__(cls, kwds['decoded'])
del kwds['decoded']
self.init(name, **kwds)
return self
def init(self, name, *, parse_tree, defects):
self._name = name
self._parse_tree = parse_tree
self._defects = defects
@property
def name(self):
return self._name
@property
def defects(self):
return tuple(self._defects)
def __reduce__(self):
return (
_reconstruct_header,
(
self.__class__.__name__,
self.__class__.__bases__,
str(self),
),
self.__dict__)
@classmethod
def _reconstruct(cls, value):
return str.__new__(cls, value)
def fold(self, *, policy):
"""Fold header according to policy.
The parsed representation of the header is folded according to
RFC5322 rules, as modified by the policy. If the parse tree
contains surrogateescaped bytes, the bytes are CTE encoded using
the charset 'unknown-8bit".
Any non-ASCII characters in the parse tree are CTE encoded using
charset utf-8. XXX: make this a policy setting.
The returned value is an ASCII-only string possibly containing linesep
characters, and ending with a linesep character. The string includes
the header name and the ': ' separator.
"""
# At some point we need to put fws here iif it was in the source.
header = parser.Header([
parser.HeaderLabel([
parser.ValueTerminal(self.name, 'header-name'),
parser.ValueTerminal(':', 'header-sep')]),
])
if self._parse_tree:
header.append(
parser.CFWSList([parser.WhiteSpaceTerminal(' ', 'fws')]))
header.append(self._parse_tree)
return header.fold(policy=policy)
def _reconstruct_header(cls_name, bases, value):
return type(cls_name, bases, {})._reconstruct(value)
class UnstructuredHeader:
max_count = None
value_parser = staticmethod(parser.get_unstructured)
@classmethod
def parse(cls, value, kwds):
kwds['parse_tree'] = cls.value_parser(value)
kwds['decoded'] = str(kwds['parse_tree'])
class UniqueUnstructuredHeader(UnstructuredHeader):
max_count = 1
class DateHeader:
"""Header whose value consists of a single timestamp.
Provides an additional attribute, datetime, which is either an aware
datetime using a timezone, or a naive datetime if the timezone
in the input string is -0000. Also accepts a datetime as input.
The 'value' attribute is the normalized form of the timestamp,
which means it is the output of format_datetime on the datetime.
"""
max_count = None
# This is used only for folding, not for creating 'decoded'.
value_parser = staticmethod(parser.get_unstructured)
@classmethod
def parse(cls, value, kwds):
if not value:
kwds['defects'].append(errors.HeaderMissingRequiredValue())
kwds['datetime'] = None
kwds['decoded'] = ''
kwds['parse_tree'] = parser.TokenList()
return
if isinstance(value, str):
value = utils.parsedate_to_datetime(value)
kwds['datetime'] = value
kwds['decoded'] = utils.format_datetime(kwds['datetime'])
kwds['parse_tree'] = cls.value_parser(kwds['decoded'])
def init(self, *args, **kw):
self._datetime = kw.pop('datetime')
super().init(*args, **kw)
@property
def datetime(self):
return self._datetime
class UniqueDateHeader(DateHeader):
max_count = 1
class AddressHeader:
max_count = None
@staticmethod
def value_parser(value):
address_list, value = parser.get_address_list(value)
assert not value, 'this should not happen'
return address_list
@classmethod
def parse(cls, value, kwds):
if isinstance(value, str):
# We are translating here from the RFC language (address/mailbox)
# to our API language (group/address).
kwds['parse_tree'] = address_list = cls.value_parser(value)
groups = []
for addr in address_list.addresses:
groups.append(Group(addr.display_name,
[Address(mb.display_name or '',
mb.local_part or '',
mb.domain or '')
for mb in addr.all_mailboxes]))
defects = list(address_list.all_defects)
else:
# Assume it is Address/Group stuff
if not hasattr(value, '__iter__'):
value = [value]
groups = [Group(None, [item]) if not hasattr(item, 'addresses')
else item
for item in value]
defects = []
kwds['groups'] = groups
kwds['defects'] = defects
kwds['decoded'] = ', '.join([str(item) for item in groups])
if 'parse_tree' not in kwds:
kwds['parse_tree'] = cls.value_parser(kwds['decoded'])
def init(self, *args, **kw):
self._groups = tuple(kw.pop('groups'))
self._addresses = None
super().init(*args, **kw)
@property
def groups(self):
return self._groups
@property
def addresses(self):
if self._addresses is None:
self._addresses = tuple([address for group in self._groups
for address in group.addresses])
return self._addresses
class UniqueAddressHeader(AddressHeader):
max_count = 1
class SingleAddressHeader(AddressHeader):
@property
def address(self):
if len(self.addresses)!=1:
raise ValueError(("value of single address header {} is not "
"a single address").format(self.name))
return self.addresses[0]
class UniqueSingleAddressHeader(SingleAddressHeader):
max_count = 1
class MIMEVersionHeader:
max_count = 1
value_parser = staticmethod(parser.parse_mime_version)
@classmethod
def parse(cls, value, kwds):
kwds['parse_tree'] = parse_tree = cls.value_parser(value)
kwds['decoded'] = str(parse_tree)
kwds['defects'].extend(parse_tree.all_defects)
kwds['major'] = None if parse_tree.minor is None else parse_tree.major
kwds['minor'] = parse_tree.minor
if parse_tree.minor is not None:
kwds['version'] = '{}.{}'.format(kwds['major'], kwds['minor'])
else:
kwds['version'] = None
def init(self, *args, **kw):
self._version = kw.pop('version')
self._major = kw.pop('major')
self._minor = kw.pop('minor')
super().init(*args, **kw)
@property
def major(self):
return self._major
@property
def minor(self):
return self._minor
@property
def version(self):
return self._version
class ParameterizedMIMEHeader:
# Mixin that handles the params dict. Must be subclassed and
# a property value_parser for the specific header provided.
max_count = 1
@classmethod
def parse(cls, value, kwds):
kwds['parse_tree'] = parse_tree = cls.value_parser(value)
kwds['decoded'] = str(parse_tree)
kwds['defects'].extend(parse_tree.all_defects)
if parse_tree.params is None:
kwds['params'] = {}
else:
# The MIME RFCs specify that parameter ordering is arbitrary.
kwds['params'] = {utils._sanitize(name).lower():
utils._sanitize(value)
for name, value in parse_tree.params}
def init(self, *args, **kw):
self._params = kw.pop('params')
super().init(*args, **kw)
@property
def params(self):
return MappingProxyType(self._params)
class ContentTypeHeader(ParameterizedMIMEHeader):
value_parser = staticmethod(parser.parse_content_type_header)
def init(self, *args, **kw):
super().init(*args, **kw)
self._maintype = utils._sanitize(self._parse_tree.maintype)
self._subtype = utils._sanitize(self._parse_tree.subtype)
@property
def maintype(self):
return self._maintype
@property
def subtype(self):
return self._subtype
@property
def content_type(self):
return self.maintype + '/' + self.subtype
class ContentDispositionHeader(ParameterizedMIMEHeader):
value_parser = staticmethod(parser.parse_content_disposition_header)
def init(self, *args, **kw):
super().init(*args, **kw)
cd = self._parse_tree.content_disposition
self._content_disposition = cd if cd is None else utils._sanitize(cd)
@property
def content_disposition(self):
return self._content_disposition
class ContentTransferEncodingHeader:
max_count = 1
value_parser = staticmethod(parser.parse_content_transfer_encoding_header)
@classmethod
def parse(cls, value, kwds):
kwds['parse_tree'] = parse_tree = cls.value_parser(value)
kwds['decoded'] = str(parse_tree)
kwds['defects'].extend(parse_tree.all_defects)
def init(self, *args, **kw):
super().init(*args, **kw)
self._cte = utils._sanitize(self._parse_tree.cte)
@property
def cte(self):
return self._cte
# The header factory #
_default_header_map = {
'subject': UniqueUnstructuredHeader,
'date': UniqueDateHeader,
'resent-date': DateHeader,
'orig-date': UniqueDateHeader,
'sender': UniqueSingleAddressHeader,
'resent-sender': SingleAddressHeader,
'to': UniqueAddressHeader,
'resent-to': AddressHeader,
'cc': UniqueAddressHeader,
'resent-cc': AddressHeader,
'bcc': UniqueAddressHeader,
'resent-bcc': AddressHeader,
'from': UniqueAddressHeader,
'resent-from': AddressHeader,
'reply-to': UniqueAddressHeader,
'mime-version': MIMEVersionHeader,
'content-type': ContentTypeHeader,
'content-disposition': ContentDispositionHeader,
'content-transfer-encoding': ContentTransferEncodingHeader,
}
class HeaderRegistry:
"""A header_factory and header registry."""
def __init__(self, base_class=BaseHeader, default_class=UnstructuredHeader,
use_default_map=True):
"""Create a header_factory that works with the Policy API.
base_class is the class that will be the last class in the created
header class's __bases__ list. default_class is the class that will be
used if "name" (see __call__) does not appear in the registry.
use_default_map controls whether or not the default mapping of names to
specialized classes is copied in to the registry when the factory is
created. The default is True.
"""
self.registry = {}
self.base_class = base_class
self.default_class = default_class
if use_default_map:
self.registry.update(_default_header_map)
def map_to_type(self, name, cls):
"""Register cls as the specialized class for handling "name" headers.
"""
self.registry[name.lower()] = cls
def __getitem__(self, name):
cls = self.registry.get(name.lower(), self.default_class)
return type('_'+cls.__name__, (cls, self.base_class), {})
def __call__(self, name, value):
"""Create a header instance for header 'name' from 'value'.
Creates a header instance by creating a specialized class for parsing
and representing the specified header by combining the factory
base_class with a specialized class from the registry or the
default_class, and passing the name and value to the constructed
class's constructor.
"""
return self[name](name, value)

71
third_party/python/Lib/email/iterators.py vendored Normal file
View file

@ -0,0 +1,71 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Various types of useful iterators and generators."""
__all__ = [
'body_line_iterator',
'typed_subpart_iterator',
'walk',
# Do not include _structure() since it's part of the debugging API.
]
import sys
from io import StringIO
# This function will become a method of the Message class
def walk(self):
"""Walk over the message tree, yielding each subpart.
The walk is performed in depth-first order. This method is a
generator.
"""
yield self
if self.is_multipart():
for subpart in self.get_payload():
yield from subpart.walk()
# These two functions are imported into the Iterators.py interface module.
def body_line_iterator(msg, decode=False):
"""Iterate over the parts, returning string payloads line-by-line.
Optional decode (default False) is passed through to .get_payload().
"""
for subpart in msg.walk():
payload = subpart.get_payload(decode=decode)
if isinstance(payload, str):
yield from StringIO(payload)
def typed_subpart_iterator(msg, maintype='text', subtype=None):
"""Iterate over the subparts with a given MIME type.
Use `maintype' as the main MIME type to match against; this defaults to
"text". Optional `subtype' is the MIME subtype to match against; if
omitted, only the main type is matched.
"""
for subpart in msg.walk():
if subpart.get_content_maintype() == maintype:
if subtype is None or subpart.get_content_subtype() == subtype:
yield subpart
def _structure(msg, fp=None, level=0, include_default=False):
"""A handy debugging aid"""
if fp is None:
fp = sys.stdout
tab = ' ' * (level * 4)
print(tab + msg.get_content_type(), end='', file=fp)
if include_default:
print(' [%s]' % msg.get_default_type(), file=fp)
else:
print(file=fp)
if msg.is_multipart():
for subpart in msg.get_payload():
_structure(subpart, fp, level+1, include_default)

1164
third_party/python/Lib/email/message.py vendored Normal file
View file

File diff suppressed because it is too large Load diff

0
third_party/python/Lib/email/mime/__init__.py vendored Normal file
View file

37
third_party/python/Lib/email/mime/application.py vendored Normal file
View file

@ -0,0 +1,37 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Keith Dart
# Contact: email-sig@python.org
"""Class representing application/* type MIME documents."""
__all__ = ["MIMEApplication"]
from email import encoders
from email.mime.nonmultipart import MIMENonMultipart
class MIMEApplication(MIMENonMultipart):
"""Class for generating application/* MIME documents."""
def __init__(self, _data, _subtype='octet-stream',
_encoder=encoders.encode_base64, *, policy=None, **_params):
"""Create an application/* type MIME document.
_data is a string containing the raw application data.
_subtype is the MIME content type subtype, defaulting to
'octet-stream'.
_encoder is a function which will perform the actual encoding for
transport of the application data, defaulting to base64 encoding.
Any additional keyword arguments are passed to the base class
constructor, which turns them into parameters on the Content-Type
header.
"""
if _subtype is None:
raise TypeError('Invalid application MIME subtype')
MIMENonMultipart.__init__(self, 'application', _subtype, policy=policy,
**_params)
self.set_payload(_data)
_encoder(self)

74
third_party/python/Lib/email/mime/audio.py vendored Normal file
View file

@ -0,0 +1,74 @@
# Copyright (C) 2001-2007 Python Software Foundation
# Author: Anthony Baxter
# Contact: email-sig@python.org
"""Class representing audio/* type MIME documents."""
__all__ = ['MIMEAudio']
import sndhdr
from io import BytesIO
from email import encoders
from email.mime.nonmultipart import MIMENonMultipart
_sndhdr_MIMEmap = {'au' : 'basic',
'wav' :'x-wav',
'aiff':'x-aiff',
'aifc':'x-aiff',
}
# There are others in sndhdr that don't have MIME types. :(
# Additional ones to be added to sndhdr? midi, mp3, realaudio, wma??
def _whatsnd(data):
"""Try to identify a sound file type.
sndhdr.what() has a pretty cruddy interface, unfortunately. This is why
we re-do it here. It would be easier to reverse engineer the Unix 'file'
command and use the standard 'magic' file, as shipped with a modern Unix.
"""
hdr = data[:512]
fakefile = BytesIO(hdr)
for testfn in sndhdr.tests:
res = testfn(hdr, fakefile)
if res is not None:
return _sndhdr_MIMEmap.get(res[0])
return None
class MIMEAudio(MIMENonMultipart):
"""Class for generating audio/* MIME documents."""
def __init__(self, _audiodata, _subtype=None,
_encoder=encoders.encode_base64, *, policy=None, **_params):
"""Create an audio/* type MIME document.
_audiodata is a string containing the raw audio data. If this data
can be decoded by the standard Python `sndhdr' module, then the
subtype will be automatically included in the Content-Type header.
Otherwise, you can specify the specific audio subtype via the
_subtype parameter. If _subtype is not given, and no subtype can be
guessed, a TypeError is raised.
_encoder is a function which will perform the actual encoding for
transport of the image data. It takes one argument, which is this
Image instance. It should use get_payload() and set_payload() to
change the payload to the encoded form. It should also add any
Content-Transfer-Encoding or other headers to the message as
necessary. The default encoding is Base64.
Any additional keyword arguments are passed to the base class
constructor, which turns them into parameters on the Content-Type
header.
"""
if _subtype is None:
_subtype = _whatsnd(_audiodata)
if _subtype is None:
raise TypeError('Could not find audio MIME subtype')
MIMENonMultipart.__init__(self, 'audio', _subtype, policy=policy,
**_params)
self.set_payload(_audiodata)
_encoder(self)

30
third_party/python/Lib/email/mime/base.py vendored Normal file
View file

@ -0,0 +1,30 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Base class for MIME specializations."""
__all__ = ['MIMEBase']
import email.policy
from email import message
class MIMEBase(message.Message):
"""Base class for MIME specializations."""
def __init__(self, _maintype, _subtype, *, policy=None, **_params):
"""This constructor adds a Content-Type: and a MIME-Version: header.
The Content-Type: header is taken from the _maintype and _subtype
arguments. Additional parameters for this header are taken from the
keyword arguments.
"""
if policy is None:
policy = email.policy.compat32
message.Message.__init__(self, policy=policy)
ctype = '%s/%s' % (_maintype, _subtype)
self.add_header('Content-Type', ctype, **_params)
self['MIME-Version'] = '1.0'

47
third_party/python/Lib/email/mime/image.py vendored Normal file
View file

@ -0,0 +1,47 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Class representing image/* type MIME documents."""
__all__ = ['MIMEImage']
import imghdr
from email import encoders
from email.mime.nonmultipart import MIMENonMultipart
class MIMEImage(MIMENonMultipart):
"""Class for generating image/* type MIME documents."""
def __init__(self, _imagedata, _subtype=None,
_encoder=encoders.encode_base64, *, policy=None, **_params):
"""Create an image/* type MIME document.
_imagedata is a string containing the raw image data. If this data
can be decoded by the standard Python `imghdr' module, then the
subtype will be automatically included in the Content-Type header.
Otherwise, you can specify the specific image subtype via the _subtype
parameter.
_encoder is a function which will perform the actual encoding for
transport of the image data. It takes one argument, which is this
Image instance. It should use get_payload() and set_payload() to
change the payload to the encoded form. It should also add any
Content-Transfer-Encoding or other headers to the message as
necessary. The default encoding is Base64.
Any additional keyword arguments are passed to the base class
constructor, which turns them into parameters on the Content-Type
header.
"""
if _subtype is None:
_subtype = imghdr.what(None, _imagedata)
if _subtype is None:
raise TypeError('Could not guess image MIME subtype')
MIMENonMultipart.__init__(self, 'image', _subtype, policy=policy,
**_params)
self.set_payload(_imagedata)
_encoder(self)

34
third_party/python/Lib/email/mime/message.py vendored Normal file
View file

@ -0,0 +1,34 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Class representing message/* MIME documents."""
__all__ = ['MIMEMessage']
from email import message
from email.mime.nonmultipart import MIMENonMultipart
class MIMEMessage(MIMENonMultipart):
"""Class representing message/* MIME documents."""
def __init__(self, _msg, _subtype='rfc822', *, policy=None):
"""Create a message/* type MIME document.
_msg is a message object and must be an instance of Message, or a
derived class of Message, otherwise a TypeError is raised.
Optional _subtype defines the subtype of the contained message. The
default is "rfc822" (this is defined by the MIME standard, even though
the term "rfc822" is technically outdated by RFC 2822).
"""
MIMENonMultipart.__init__(self, 'message', _subtype, policy=policy)
if not isinstance(_msg, message.Message):
raise TypeError('Argument is not an instance of Message')
# It's convenient to use this base class method. We need to do it
# this way or we'll get an exception
message.Message.attach(self, _msg)
# And be sure our default type is set correctly
self.set_default_type('message/rfc822')

48
third_party/python/Lib/email/mime/multipart.py vendored Normal file
View file

@ -0,0 +1,48 @@
# Copyright (C) 2002-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Base class for MIME multipart/* type messages."""
__all__ = ['MIMEMultipart']
from email.mime.base import MIMEBase
class MIMEMultipart(MIMEBase):
"""Base class for MIME multipart/* type messages."""
def __init__(self, _subtype='mixed', boundary=None, _subparts=None,
*, policy=None,
**_params):
"""Creates a multipart/* type message.
By default, creates a multipart/mixed message, with proper
Content-Type and MIME-Version headers.
_subtype is the subtype of the multipart content type, defaulting to
`mixed'.
boundary is the multipart boundary string. By default it is
calculated as needed.
_subparts is a sequence of initial subparts for the payload. It
must be an iterable object, such as a list. You can always
attach new subparts to the message by using the attach() method.
Additional parameters for the Content-Type header are taken from the
keyword arguments (or passed into the _params argument).
"""
MIMEBase.__init__(self, 'multipart', _subtype, policy=policy, **_params)
# Initialise _payload to an empty list as the Message superclass's
# implementation of is_multipart assumes that _payload is a list for
# multipart messages.
self._payload = []
if _subparts:
for p in _subparts:
self.attach(p)
if boundary:
self.set_boundary(boundary)

22
third_party/python/Lib/email/mime/nonmultipart.py vendored Normal file
View file

@ -0,0 +1,22 @@
# Copyright (C) 2002-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Base class for MIME type messages that are not multipart."""
__all__ = ['MIMENonMultipart']
from email import errors
from email.mime.base import MIMEBase
class MIMENonMultipart(MIMEBase):
"""Base class for MIME non-multipart type messages."""
def attach(self, payload):
# The public API prohibits attaching multiple subparts to MIMEBase
# derived subtypes since none of them are, by definition, of content
# type multipart/*
raise errors.MultipartConversionError(
'Cannot attach additional subparts to non-multipart/*')

42
third_party/python/Lib/email/mime/text.py vendored Normal file
View file

@ -0,0 +1,42 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Class representing text/* type MIME documents."""
__all__ = ['MIMEText']
from email.charset import Charset
from email.mime.nonmultipart import MIMENonMultipart
class MIMEText(MIMENonMultipart):
"""Class for generating text/* type MIME documents."""
def __init__(self, _text, _subtype='plain', _charset=None, *, policy=None):
"""Create a text/* type MIME document.
_text is the string for this message object.
_subtype is the MIME sub content type, defaulting to "plain".
_charset is the character set parameter added to the Content-Type
header. This defaults to "us-ascii". Note that as a side-effect, the
Content-Transfer-Encoding header will also be set.
"""
# If no _charset was specified, check to see if there are non-ascii
# characters present. If not, use 'us-ascii', otherwise use utf-8.
# XXX: This can be removed once #7304 is fixed.
if _charset is None:
try:
_text.encode('us-ascii')
_charset = 'us-ascii'
except UnicodeEncodeError:
_charset = 'utf-8'
MIMENonMultipart.__init__(self, 'text', _subtype, policy=policy,
**{'charset': str(_charset)})
self.set_payload(_text, _charset)

131
third_party/python/Lib/email/parser.py vendored Normal file
View file

@ -0,0 +1,131 @@
# Copyright (C) 2001-2007 Python Software Foundation
# Author: Barry Warsaw, Thomas Wouters, Anthony Baxter
# Contact: email-sig@python.org
"""A parser of RFC 2822 and MIME email messages."""
__all__ = ['Parser', 'HeaderParser', 'BytesParser', 'BytesHeaderParser',
'FeedParser', 'BytesFeedParser']
from io import StringIO, TextIOWrapper
from email.feedparser import FeedParser, BytesFeedParser
from email._policybase import compat32
class Parser:
def __init__(self, _class=None, *, policy=compat32):
"""Parser of RFC 2822 and MIME email messages.
Creates an in-memory object tree representing the email message, which
can then be manipulated and turned over to a Generator to return the
textual representation of the message.
The string must be formatted as a block of RFC 2822 headers and header
continuation lines, optionally preceded by a `Unix-from' header. The
header block is terminated either by the end of the string or by a
blank line.
_class is the class to instantiate for new message objects when they
must be created. This class must have a constructor that can take
zero arguments. Default is Message.Message.
The policy keyword specifies a policy object that controls a number of
aspects of the parser's operation. The default policy maintains
backward compatibility.
"""
self._class = _class
self.policy = policy
def parse(self, fp, headersonly=False):
"""Create a message structure from the data in a file.
Reads all the data from the file and returns the root of the message
structure. Optional headersonly is a flag specifying whether to stop
parsing after reading the headers or not. The default is False,
meaning it parses the entire contents of the file.
"""
feedparser = FeedParser(self._class, policy=self.policy)
if headersonly:
feedparser._set_headersonly()
while True:
data = fp.read(8192)
if not data:
break
feedparser.feed(data)
return feedparser.close()
def parsestr(self, text, headersonly=False):
"""Create a message structure from a string.
Returns the root of the message structure. Optional headersonly is a
flag specifying whether to stop parsing after reading the headers or
not. The default is False, meaning it parses the entire contents of
the file.
"""
return self.parse(StringIO(text), headersonly=headersonly)
class HeaderParser(Parser):
def parse(self, fp, headersonly=True):
return Parser.parse(self, fp, True)
def parsestr(self, text, headersonly=True):
return Parser.parsestr(self, text, True)
class BytesParser:
def __init__(self, *args, **kw):
"""Parser of binary RFC 2822 and MIME email messages.
Creates an in-memory object tree representing the email message, which
can then be manipulated and turned over to a Generator to return the
textual representation of the message.
The input must be formatted as a block of RFC 2822 headers and header
continuation lines, optionally preceded by a `Unix-from' header. The
header block is terminated either by the end of the input or by a
blank line.
_class is the class to instantiate for new message objects when they
must be created. This class must have a constructor that can take
zero arguments. Default is Message.Message.
"""
self.parser = Parser(*args, **kw)
def parse(self, fp, headersonly=False):
"""Create a message structure from the data in a binary file.
Reads all the data from the file and returns the root of the message
structure. Optional headersonly is a flag specifying whether to stop
parsing after reading the headers or not. The default is False,
meaning it parses the entire contents of the file.
"""
fp = TextIOWrapper(fp, encoding='ascii', errors='surrogateescape')
try:
return self.parser.parse(fp, headersonly)
finally:
fp.detach()
def parsebytes(self, text, headersonly=False):
"""Create a message structure from a byte string.
Returns the root of the message structure. Optional headersonly is a
flag specifying whether to stop parsing after reading the headers or
not. The default is False, meaning it parses the entire contents of
the file.
"""
text = text.decode('ASCII', errors='surrogateescape')
return self.parser.parsestr(text, headersonly)
class BytesHeaderParser(BytesParser):
def parse(self, fp, headersonly=True):
return BytesParser.parse(self, fp, headersonly=True)
def parsebytes(self, text, headersonly=True):
return BytesParser.parsebytes(self, text, headersonly=True)

223
third_party/python/Lib/email/policy.py vendored Normal file
View file

@ -0,0 +1,223 @@
"""This will be the home for the policy that hooks in the new
code that adds all the email6 features.
"""
import re
from email._policybase import Policy, Compat32, compat32, _extend_docstrings
from email.utils import _has_surrogates
from email.headerregistry import HeaderRegistry as HeaderRegistry
from email.contentmanager import raw_data_manager
from email.message import EmailMessage
__all__ = [
'Compat32',
'compat32',
'Policy',
'EmailPolicy',
'default',
'strict',
'SMTP',
'HTTP',
]
linesep_splitter = re.compile(r'\n|\r')
@_extend_docstrings
class EmailPolicy(Policy):
"""+
PROVISIONAL
The API extensions enabled by this policy are currently provisional.
Refer to the documentation for details.
This policy adds new header parsing and folding algorithms. Instead of
simple strings, headers are custom objects with custom attributes
depending on the type of the field. The folding algorithm fully
implements RFCs 2047 and 5322.
In addition to the settable attributes listed above that apply to
all Policies, this policy adds the following additional attributes:
utf8 -- if False (the default) message headers will be
serialized as ASCII, using encoded words to encode
any non-ASCII characters in the source strings. If
True, the message headers will be serialized using
utf8 and will not contain encoded words (see RFC
6532 for more on this serialization format).
refold_source -- if the value for a header in the Message object
came from the parsing of some source, this attribute
indicates whether or not a generator should refold
that value when transforming the message back into
stream form. The possible values are:
none -- all source values use original folding
long -- source values that have any line that is
longer than max_line_length will be
refolded
all -- all values are refolded.
The default is 'long'.
header_factory -- a callable that takes two arguments, 'name' and
'value', where 'name' is a header field name and
'value' is an unfolded header field value, and
returns a string-like object that represents that
header. A default header_factory is provided that
understands some of the RFC5322 header field types.
(Currently address fields and date fields have
special treatment, while all other fields are
treated as unstructured. This list will be
completed before the extension is marked stable.)
content_manager -- an object with at least two methods: get_content
and set_content. When the get_content or
set_content method of a Message object is called,
it calls the corresponding method of this object,
passing it the message object as its first argument,
and any arguments or keywords that were passed to
it as additional arguments. The default
content_manager is
:data:`~email.contentmanager.raw_data_manager`.
"""
message_factory = EmailMessage
utf8 = False
refold_source = 'long'
header_factory = HeaderRegistry()
content_manager = raw_data_manager
def __init__(self, **kw):
# Ensure that each new instance gets a unique header factory
# (as opposed to clones, which share the factory).
if 'header_factory' not in kw:
object.__setattr__(self, 'header_factory', HeaderRegistry())
super().__init__(**kw)
def header_max_count(self, name):
"""+
The implementation for this class returns the max_count attribute from
the specialized header class that would be used to construct a header
of type 'name'.
"""
return self.header_factory[name].max_count
# The logic of the next three methods is chosen such that it is possible to
# switch a Message object between a Compat32 policy and a policy derived
# from this class and have the results stay consistent. This allows a
# Message object constructed with this policy to be passed to a library
# that only handles Compat32 objects, or to receive such an object and
# convert it to use the newer style by just changing its policy. It is
# also chosen because it postpones the relatively expensive full rfc5322
# parse until as late as possible when parsing from source, since in many
# applications only a few headers will actually be inspected.
def header_source_parse(self, sourcelines):
"""+
The name is parsed as everything up to the ':' and returned unmodified.
The value is determined by stripping leading whitespace off the
remainder of the first line, joining all subsequent lines together, and
stripping any trailing carriage return or linefeed characters. (This
is the same as Compat32).
"""
name, value = sourcelines[0].split(':', 1)
value = value.lstrip(' \t') + ''.join(sourcelines[1:])
return (name, value.rstrip('\r\n'))
def header_store_parse(self, name, value):
"""+
The name is returned unchanged. If the input value has a 'name'
attribute and it matches the name ignoring case, the value is returned
unchanged. Otherwise the name and value are passed to header_factory
method, and the resulting custom header object is returned as the
value. In this case a ValueError is raised if the input value contains
CR or LF characters.
"""
if hasattr(value, 'name') and value.name.lower() == name.lower():
return (name, value)
if isinstance(value, str) and len(value.splitlines())>1:
# XXX this error message isn't quite right when we use splitlines
# (see issue 22233), but I'm not sure what should happen here.
raise ValueError("Header values may not contain linefeed "
"or carriage return characters")
return (name, self.header_factory(name, value))
def header_fetch_parse(self, name, value):
"""+
If the value has a 'name' attribute, it is returned to unmodified.
Otherwise the name and the value with any linesep characters removed
are passed to the header_factory method, and the resulting custom
header object is returned. Any surrogateescaped bytes get turned
into the unicode unknown-character glyph.
"""
if hasattr(value, 'name'):
return value
# We can't use splitlines here because it splits on more than \r and \n.
value = ''.join(linesep_splitter.split(value))
return self.header_factory(name, value)
def fold(self, name, value):
"""+
Header folding is controlled by the refold_source policy setting. A
value is considered to be a 'source value' if and only if it does not
have a 'name' attribute (having a 'name' attribute means it is a header
object of some sort). If a source value needs to be refolded according
to the policy, it is converted into a custom header object by passing
the name and the value with any linesep characters removed to the
header_factory method. Folding of a custom header object is done by
calling its fold method with the current policy.
Source values are split into lines using splitlines. If the value is
not to be refolded, the lines are rejoined using the linesep from the
policy and returned. The exception is lines containing non-ascii
binary data. In that case the value is refolded regardless of the
refold_source setting, which causes the binary data to be CTE encoded
using the unknown-8bit charset.
"""
return self._fold(name, value, refold_binary=True)
def fold_binary(self, name, value):
"""+
The same as fold if cte_type is 7bit, except that the returned value is
bytes.
If cte_type is 8bit, non-ASCII binary data is converted back into
bytes. Headers with binary data are not refolded, regardless of the
refold_header setting, since there is no way to know whether the binary
data consists of single byte characters or multibyte characters.
If utf8 is true, headers are encoded to utf8, otherwise to ascii with
non-ASCII unicode rendered as encoded words.
"""
folded = self._fold(name, value, refold_binary=self.cte_type=='7bit')
charset = 'utf8' if self.utf8 else 'ascii'
return folded.encode(charset, 'surrogateescape')
def _fold(self, name, value, refold_binary=False):
if hasattr(value, 'name'):
return value.fold(policy=self)
maxlen = self.max_line_length if self.max_line_length else float('inf')
lines = value.splitlines()
refold = (self.refold_source == 'all' or
self.refold_source == 'long' and
(lines and len(lines[0])+len(name)+2 > maxlen or
any(len(x) > maxlen for x in lines[1:])))
if refold or refold_binary and _has_surrogates(value):
return self.header_factory(name, ''.join(lines)).fold(policy=self)
return name + ': ' + self.linesep.join(lines) + self.linesep
default = EmailPolicy()
# Make the default policy use the class default header_factory
del default.header_factory
strict = default.clone(raise_on_defect=True)
SMTP = default.clone(linesep='\r\n')
HTTP = default.clone(linesep='\r\n', max_line_length=None)
SMTPUTF8 = SMTP.clone(utf8=True)

299
third_party/python/Lib/email/quoprimime.py vendored Normal file
View file

@ -0,0 +1,299 @@
# Copyright (C) 2001-2006 Python Software Foundation
# Author: Ben Gertzfield
# Contact: email-sig@python.org
"""Quoted-printable content transfer encoding per RFCs 2045-2047.
This module handles the content transfer encoding method defined in RFC 2045
to encode US ASCII-like 8-bit data called `quoted-printable'. It is used to
safely encode text that is in a character set similar to the 7-bit US ASCII
character set, but that includes some 8-bit characters that are normally not
allowed in email bodies or headers.
Quoted-printable is very space-inefficient for encoding binary files; use the
email.base64mime module for that instead.
This module provides an interface to encode and decode both headers and bodies
with quoted-printable encoding.
RFC 2045 defines a method for including character set information in an
`encoded-word' in a header. This method is commonly used for 8-bit real names
in To:/From:/Cc: etc. fields, as well as Subject: lines.
This module does not do the line wrapping or end-of-line character
conversion necessary for proper internationalized headers; it only
does dumb encoding and decoding. To deal with the various line
wrapping issues, use the email.header module.
"""
__all__ = [
'body_decode',
'body_encode',
'body_length',
'decode',
'decodestring',
'header_decode',
'header_encode',
'header_length',
'quote',
'unquote',
]
import re
from string import ascii_letters, digits, hexdigits
CRLF = '\r\n'
NL = '\n'
EMPTYSTRING = ''
# Build a mapping of octets to the expansion of that octet. Since we're only
# going to have 256 of these things, this isn't terribly inefficient
# space-wise. Remember that headers and bodies have different sets of safe
# characters. Initialize both maps with the full expansion, and then override
# the safe bytes with the more compact form.
_QUOPRI_MAP = ['=%02X' % c for c in range(256)]
_QUOPRI_HEADER_MAP = _QUOPRI_MAP[:]
_QUOPRI_BODY_MAP = _QUOPRI_MAP[:]
# Safe header bytes which need no encoding.
for c in b'-!*+/' + ascii_letters.encode('ascii') + digits.encode('ascii'):
_QUOPRI_HEADER_MAP[c] = chr(c)
# Headers have one other special encoding; spaces become underscores.
_QUOPRI_HEADER_MAP[ord(' ')] = '_'
# Safe body bytes which need no encoding.
for c in (b' !"#$%&\'()*+,-./0123456789:;<>'
b'?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`'
b'abcdefghijklmnopqrstuvwxyz{|}~\t'):
_QUOPRI_BODY_MAP[c] = chr(c)
# Helpers
def header_check(octet):
"""Return True if the octet should be escaped with header quopri."""
return chr(octet) != _QUOPRI_HEADER_MAP[octet]
def body_check(octet):
"""Return True if the octet should be escaped with body quopri."""
return chr(octet) != _QUOPRI_BODY_MAP[octet]
def header_length(bytearray):
"""Return a header quoted-printable encoding length.
Note that this does not include any RFC 2047 chrome added by
`header_encode()`.
:param bytearray: An array of bytes (a.k.a. octets).
:return: The length in bytes of the byte array when it is encoded with
quoted-printable for headers.
"""
return sum(len(_QUOPRI_HEADER_MAP[octet]) for octet in bytearray)
def body_length(bytearray):
"""Return a body quoted-printable encoding length.
:param bytearray: An array of bytes (a.k.a. octets).
:return: The length in bytes of the byte array when it is encoded with
quoted-printable for bodies.
"""
return sum(len(_QUOPRI_BODY_MAP[octet]) for octet in bytearray)
def _max_append(L, s, maxlen, extra=''):
if not isinstance(s, str):
s = chr(s)
if not L:
L.append(s.lstrip())
elif len(L[-1]) + len(s) <= maxlen:
L[-1] += extra + s
else:
L.append(s.lstrip())
def unquote(s):
"""Turn a string in the form =AB to the ASCII character with value 0xab"""
return chr(int(s[1:3], 16))
def quote(c):
return _QUOPRI_MAP[ord(c)]
def header_encode(header_bytes, charset='iso-8859-1'):
"""Encode a single header line with quoted-printable (like) encoding.
Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but
used specifically for email header fields to allow charsets with mostly 7
bit characters (and some 8 bit) to remain more or less readable in non-RFC
2045 aware mail clients.
charset names the character set to use in the RFC 2046 header. It
defaults to iso-8859-1.
"""
# Return empty headers as an empty string.
if not header_bytes:
return ''
# Iterate over every byte, encoding if necessary.
encoded = header_bytes.decode('latin1').translate(_QUOPRI_HEADER_MAP)
# Now add the RFC chrome to each encoded chunk and glue the chunks
# together.
return '=?%s?q?%s?=' % (charset, encoded)
_QUOPRI_BODY_ENCODE_MAP = _QUOPRI_BODY_MAP[:]
for c in b'\r\n':
_QUOPRI_BODY_ENCODE_MAP[c] = chr(c)
def body_encode(body, maxlinelen=76, eol=NL):
"""Encode with quoted-printable, wrapping at maxlinelen characters.
Each line of encoded text will end with eol, which defaults to "\\n". Set
this to "\\r\\n" if you will be using the result of this function directly
in an email.
Each line will be wrapped at, at most, maxlinelen characters before the
eol string (maxlinelen defaults to 76 characters, the maximum value
permitted by RFC 2045). Long lines will have the 'soft line break'
quoted-printable character "=" appended to them, so the decoded text will
be identical to the original text.
The minimum maxlinelen is 4 to have room for a quoted character ("=XX")
followed by a soft line break. Smaller values will generate a
ValueError.
"""
if maxlinelen < 4:
raise ValueError("maxlinelen must be at least 4")
if not body:
return body
# quote special characters
body = body.translate(_QUOPRI_BODY_ENCODE_MAP)
soft_break = '=' + eol
# leave space for the '=' at the end of a line
maxlinelen1 = maxlinelen - 1
encoded_body = []
append = encoded_body.append
for line in body.splitlines():
# break up the line into pieces no longer than maxlinelen - 1
start = 0
laststart = len(line) - 1 - maxlinelen
while start <= laststart:
stop = start + maxlinelen1
# make sure we don't break up an escape sequence
if line[stop - 2] == '=':
append(line[start:stop - 1])
start = stop - 2
elif line[stop - 1] == '=':
append(line[start:stop])
start = stop - 1
else:
append(line[start:stop] + '=')
start = stop
# handle rest of line, special case if line ends in whitespace
if line and line[-1] in ' \t':
room = start - laststart
if room >= 3:
# It's a whitespace character at end-of-line, and we have room
# for the three-character quoted encoding.
q = quote(line[-1])
elif room == 2:
# There's room for the whitespace character and a soft break.
q = line[-1] + soft_break
else:
# There's room only for a soft break. The quoted whitespace
# will be the only content on the subsequent line.
q = soft_break + quote(line[-1])
append(line[start:-1] + q)
else:
append(line[start:])
# add back final newline if present
if body[-1] in CRLF:
append('')
return eol.join(encoded_body)
# BAW: I'm not sure if the intent was for the signature of this function to be
# the same as base64MIME.decode() or not...
def decode(encoded, eol=NL):
"""Decode a quoted-printable string.
Lines are separated with eol, which defaults to \\n.
"""
if not encoded:
return encoded
# BAW: see comment in encode() above. Again, we're building up the
# decoded string with string concatenation, which could be done much more
# efficiently.
decoded = ''
for line in encoded.splitlines():
line = line.rstrip()
if not line:
decoded += eol
continue
i = 0
n = len(line)
while i < n:
c = line[i]
if c != '=':
decoded += c
i += 1
# Otherwise, c == "=". Are we at the end of the line? If so, add
# a soft line break.
elif i+1 == n:
i += 1
continue
# Decode if in form =AB
elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits:
decoded += unquote(line[i:i+3])
i += 3
# Otherwise, not in form =AB, pass literally
else:
decoded += c
i += 1
if i == n:
decoded += eol
# Special case if original string did not end with eol
if encoded[-1] not in '\r\n' and decoded.endswith(eol):
decoded = decoded[:-1]
return decoded
# For convenience and backwards compatibility w/ standard base64 module
body_decode = decode
decodestring = decode
def _unquote_match(match):
"""Turn a match in the form =AB to the ASCII character with value 0xab"""
s = match.group(0)
return unquote(s)
# Header decoding is done a bit differently
def header_decode(s):
"""Decode a string encoded with RFC 2045 MIME header `Q' encoding.
This function does not parse a full MIME header value encoded with
quoted-printable (like =?iso-8859-1?q?Hello_World?=) -- please use
the high level email.header class for that functionality.
"""
s = s.replace('_', ' ')
return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s, flags=re.ASCII)

388
third_party/python/Lib/email/utils.py vendored Normal file
View file

@ -0,0 +1,388 @@
# Copyright (C) 2001-2010 Python Software Foundation
# Author: Barry Warsaw
# Contact: email-sig@python.org
"""Miscellaneous utilities."""
__all__ = [
'collapse_rfc2231_value',
'decode_params',
'decode_rfc2231',
'encode_rfc2231',
'formataddr',
'formatdate',
'format_datetime',
'getaddresses',
'make_msgid',
'mktime_tz',
'parseaddr',
'parsedate',
'parsedate_tz',
'parsedate_to_datetime',
'unquote',
]
import os
import re
import time
import random
import socket
import datetime
import urllib.parse
from email._parseaddr import quote
from email._parseaddr import AddressList as _AddressList
from email._parseaddr import mktime_tz
from email._parseaddr import parsedate, parsedate_tz, _parsedate_tz
# Intrapackage imports
from email.charset import Charset
COMMASPACE = ', '
EMPTYSTRING = ''
UEMPTYSTRING = ''
CRLF = '\r\n'
TICK = "'"
specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')
def _has_surrogates(s):
"""Return True if s contains surrogate-escaped binary data."""
# This check is based on the fact that unless there are surrogates, utf8
# (Python's default encoding) can encode any string. This is the fastest
# way to check for surrogates, see issue 11454 for timings.
try:
s.encode()
return False
except UnicodeEncodeError:
return True
# How to deal with a string containing bytes before handing it to the
# application through the 'normal' interface.
def _sanitize(string):
# Turn any escaped bytes into unicode 'unknown' char. If the escaped
# bytes happen to be utf-8 they will instead get decoded, even if they
# were invalid in the charset the source was supposed to be in. This
# seems like it is not a bad thing; a defect was still registered.
original_bytes = string.encode('utf-8', 'surrogateescape')
return original_bytes.decode('utf-8', 'replace')
# Helpers
def formataddr(pair, charset='utf-8'):
"""The inverse of parseaddr(), this takes a 2-tuple of the form
(realname, email_address) and returns the string value suitable
for an RFC 2822 From, To or Cc header.
If the first element of pair is false, then the second element is
returned unmodified.
Optional charset if given is the character set that is used to encode
realname in case realname is not ASCII safe. Can be an instance of str or
a Charset-like object which has a header_encode method. Default is
'utf-8'.
"""
name, address = pair
# The address MUST (per RFC) be ascii, so raise a UnicodeError if it isn't.
address.encode('ascii')
if name:
try:
name.encode('ascii')
except UnicodeEncodeError:
if isinstance(charset, str):
charset = Charset(charset)
encoded_name = charset.header_encode(name)
return "%s <%s>" % (encoded_name, address)
else:
quotes = ''
if specialsre.search(name):
quotes = '"'
name = escapesre.sub(r'\\\g<0>', name)
return '%s%s%s <%s>' % (quotes, name, quotes, address)
return address
def getaddresses(fieldvalues):
"""Return a list of (REALNAME, EMAIL) for each fieldvalue."""
all = COMMASPACE.join(fieldvalues)
a = _AddressList(all)
return a.addresslist
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<atom>.*?) # non-greedy up to the next ?= is the atom
\?= # literal ?=
''', re.VERBOSE | re.IGNORECASE)
def _format_timetuple_and_zone(timetuple, zone):
return '%s, %02d %s %04d %02d:%02d:%02d %s' % (
['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][timetuple[6]],
timetuple[2],
['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'][timetuple[1] - 1],
timetuple[0], timetuple[3], timetuple[4], timetuple[5],
zone)
def formatdate(timeval=None, localtime=False, usegmt=False):
"""Returns a date string as specified by RFC 2822, e.g.:
Fri, 09 Nov 2001 01:08:47 -0000
Optional timeval if given is a floating point time value as accepted by
gmtime() and localtime(), otherwise the current time is used.
Optional localtime is a flag that when True, interprets timeval, and
returns a date relative to the local timezone instead of UTC, properly
taking daylight savings time into account.
Optional argument usegmt means that the timezone is written out as
an ascii string, not numeric one (so "GMT" instead of "+0000"). This
is needed for HTTP, and is only used when localtime==False.
"""
# Note: we cannot use strftime() because that honors the locale and RFC
# 2822 requires that day and month names be the English abbreviations.
if timeval is None:
timeval = time.time()
if localtime or usegmt:
dt = datetime.datetime.fromtimestamp(timeval, datetime.timezone.utc)
else:
dt = datetime.datetime.utcfromtimestamp(timeval)
if localtime:
dt = dt.astimezone()
usegmt = False
return format_datetime(dt, usegmt)
def format_datetime(dt, usegmt=False):
"""Turn a datetime into a date string as specified in RFC 2822.
If usegmt is True, dt must be an aware datetime with an offset of zero. In
this case 'GMT' will be rendered instead of the normal +0000 required by
RFC2822. This is to support HTTP headers involving date stamps.
"""
now = dt.timetuple()
if usegmt:
if dt.tzinfo is None or dt.tzinfo != datetime.timezone.utc:
raise ValueError("usegmt option requires a UTC datetime")
zone = 'GMT'
elif dt.tzinfo is None:
zone = '-0000'
else:
zone = dt.strftime("%z")
return _format_timetuple_and_zone(now, zone)
def make_msgid(idstring=None, domain=None):
"""Returns a string suitable for RFC 2822 compliant Message-ID, e.g:
<142480216486.20800.16526388040877946887@nightshade.la.mastaler.com>
Optional idstring if given is a string used to strengthen the
uniqueness of the message id. Optional domain if given provides the
portion of the message id after the '@'. It defaults to the locally
defined hostname.
"""
timeval = int(time.time()*100)
pid = os.getpid()
randint = random.getrandbits(64)
if idstring is None:
idstring = ''
else:
idstring = '.' + idstring
if domain is None:
domain = socket.getfqdn()
msgid = '<%d.%d.%d%s@%s>' % (timeval, pid, randint, idstring, domain)
return msgid
def parsedate_to_datetime(data):
*dtuple, tz = _parsedate_tz(data)
if tz is None:
return datetime.datetime(*dtuple[:6])
return datetime.datetime(*dtuple[:6],
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
def parseaddr(addr):
"""
Parse addr into its constituent realname and email address parts.
Return a tuple of realname and email address, unless the parse fails, in
which case return a 2-tuple of ('', '').
"""
addrs = _AddressList(addr).addresslist
if not addrs:
return '', ''
return addrs[0]
# rfc822.unquote() doesn't properly de-backslash-ify in Python pre-2.3.
def unquote(str):
"""Remove quotes from a string."""
if len(str) > 1:
if str.startswith('"') and str.endswith('"'):
return str[1:-1].replace('\\\\', '\\').replace('\\"', '"')
if str.startswith('<') and str.endswith('>'):
return str[1:-1]
return str
# RFC2231-related functions - parameter encoding and decoding
def decode_rfc2231(s):
"""Decode string according to RFC 2231"""
parts = s.split(TICK, 2)
if len(parts) <= 2:
return None, None, s
return parts
def encode_rfc2231(s, charset=None, language=None):
"""Encode string according to RFC 2231.
If neither charset nor language is given, then s is returned as-is. If
charset is given but not language, the string is encoded using the empty
string for language.
"""
s = urllib.parse.quote(s, safe='', encoding=charset or 'ascii')
if charset is None and language is None:
return s
if language is None:
language = ''
return "%s'%s'%s" % (charset, language, s)
rfc2231_continuation = re.compile(r'^(?P<name>\w+)\*((?P<num>[0-9]+)\*?)?$',
re.ASCII)
def decode_params(params):
"""Decode parameters list according to RFC 2231.
params is a sequence of 2-tuples containing (param name, string value).
"""
# Copy params so we don't mess with the original
params = params[:]
new_params = []
# Map parameter's name to a list of continuations. The values are a
# 3-tuple of the continuation number, the string value, and a flag
# specifying whether a particular segment is %-encoded.
rfc2231_params = {}
name, value = params.pop(0)
new_params.append((name, value))
while params:
name, value = params.pop(0)
if name.endswith('*'):
encoded = True
else:
encoded = False
value = unquote(value)
mo = rfc2231_continuation.match(name)
if mo:
name, num = mo.group('name', 'num')
if num is not None:
num = int(num)
rfc2231_params.setdefault(name, []).append((num, value, encoded))
else:
new_params.append((name, '"%s"' % quote(value)))
if rfc2231_params:
for name, continuations in rfc2231_params.items():
value = []
extended = False
# Sort by number
continuations.sort()
# And now append all values in numerical order, converting
# %-encodings for the encoded segments. If any of the
# continuation names ends in a *, then the entire string, after
# decoding segments and concatenating, must have the charset and
# language specifiers at the beginning of the string.
for num, s, encoded in continuations:
if encoded:
# Decode as "latin-1", so the characters in s directly
# represent the percent-encoded octet values.
# collapse_rfc2231_value treats this as an octet sequence.
s = urllib.parse.unquote(s, encoding="latin-1")
extended = True
value.append(s)
value = quote(EMPTYSTRING.join(value))
if extended:
charset, language, value = decode_rfc2231(value)
new_params.append((name, (charset, language, '"%s"' % value)))
else:
new_params.append((name, '"%s"' % value))
return new_params
def collapse_rfc2231_value(value, errors='replace',
fallback_charset='us-ascii'):
if not isinstance(value, tuple) or len(value) != 3:
return unquote(value)
# While value comes to us as a unicode string, we need it to be a bytes
# object. We do not want bytes() normal utf-8 decoder, we want a straight
# interpretation of the string as character bytes.
charset, language, text = value
if charset is None:
# Issue 17369: if charset/lang is None, decode_rfc2231 couldn't parse
# the value, so use the fallback_charset.
charset = fallback_charset
rawbytes = bytes(text, 'raw-unicode-escape')
try:
return str(rawbytes, charset, errors)
except LookupError:
# charset is not a known codec.
return unquote(text)
#
# datetime doesn't provide a localtime function yet, so provide one. Code
# adapted from the patch in issue 9527. This may not be perfect, but it is
# better than not having it.
#
def localtime(dt=None, isdst=-1):
"""Return local time as an aware datetime object.
If called without arguments, return current time. Otherwise *dt*
argument should be a datetime instance, and it is converted to the
local time zone according to the system time zone database. If *dt* is
naive (that is, dt.tzinfo is None), it is assumed to be in local time.
In this case, a positive or zero value for *isdst* causes localtime to
presume initially that summer time (for example, Daylight Saving Time)
is or is not (respectively) in effect for the specified time. A
negative value for *isdst* causes the localtime() function to attempt
to divine whether summer time is in effect for the specified time.
"""
if dt is None:
return datetime.datetime.now(datetime.timezone.utc).astimezone()
if dt.tzinfo is not None:
return dt.astimezone()
# We have a naive datetime. Convert to a (localtime) timetuple and pass to
# system mktime together with the isdst hint. System mktime will return
# seconds since epoch.
tm = dt.timetuple()[:-1] + (isdst,)
seconds = time.mktime(tm)
localtm = time.localtime(seconds)
try:
delta = datetime.timedelta(seconds=localtm.tm_gmtoff)
tz = datetime.timezone(delta, localtm.tm_zone)
except AttributeError:
# Compute UTC offset and compare with the value implied by tm_isdst.
# If the values match, use the zone name implied by tm_isdst.
delta = dt - datetime.datetime(*time.gmtime(seconds)[:6])
dst = time.daylight and localtm.tm_isdst > 0
gmtoff = -(time.altzone if dst else time.timezone)
if delta == datetime.timedelta(seconds=gmtoff):
tz = datetime.timezone(delta, time.tzname[dst])
else:
tz = datetime.timezone(delta)
return dt.replace(tzinfo=tz)