diff options
Diffstat (limited to '.venv/lib/python3.12/site-packages/future/backports/email')
28 files changed, 9462 insertions, 0 deletions
diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/__init__.py b/.venv/lib/python3.12/site-packages/future/backports/email/__init__.py new file mode 100644 index 00000000..f9523bc1 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/__init__.py @@ -0,0 +1,78 @@ +# Copyright (C) 2001-2007 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +""" +Backport of the Python 3.3 email package for Python-Future. + +A package for parsing, handling, and generating email messages. +""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +# Install the surrogate escape handler here because this is used by many +# modules in the email package. +from future.utils import surrogateescape +surrogateescape.register_surrogateescape() +# (Should this be done globally by ``future``?) + + +__version__ = '5.1.0' + +__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 future.backports.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 future.backports.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 future.backports.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 future.backports.email.parser import BytesParser + return BytesParser(*args, **kws).parse(fp) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/_encoded_words.py b/.venv/lib/python3.12/site-packages/future/backports/email/_encoded_words.py new file mode 100644 index 00000000..7c4a5291 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/_encoded_words.py @@ -0,0 +1,232 @@ +""" 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. + +""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import bytes +from future.builtins import chr +from future.builtins import int +from future.builtins import str + +# 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 future.backports.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 = bytes(encoded.replace(b'_', b' ')) + return _q_byte_subber(encoded), [] + + +# dict mapping bytes to their encoded form +class _QByteMap(dict): + + safe = bytes(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 str(''.join(_q_byte_map[x] for x in bytes(bstring))) + +def len_q(bstring): + return sum(len(_q_byte_map[x]) for x in bytes(bstring)) + + +# +# Base64 +# + +def decode_b(encoded): + defects = [] + pad_err = len(encoded) % 4 + if pad_err: + defects.append(errors.InvalidBase64PaddingDefect()) + padded_encoded = encoded + b'==='[:4-pad_err] + else: + padded_encoded = encoded + try: + # The validate kwarg to b64decode is not supported in Py2.x + if not re.match(b'^[A-Za-z0-9+/]*={0,2}$', padded_encoded): + raise binascii.Error('Non-base64 digit found') + return base64.b64decode(padded_encoded), defects + except binascii.Error: + # Since we had correct padding, this must an invalid char error. + defects = [errors.InvalidBase64CharactersDefect()] + # The non-alphabet characters are ignored as far as padding + # goes, but we don't know how many there are. So we'll just + # try various padding lengths until something works. + for i in 0, 1, 2, 3: + try: + return base64.b64decode(encoded+b'='*i), defects + except (binascii.Error, TypeError): # Py2 raises a TypeError + if i==0: + defects.append(errors.InvalidBase64PaddingDefect()) + else: + # This should never happen. + raise AssertionError("unexpected binascii.Error") + +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, _ = str(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. + + """ + string = str(string) + 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 "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/_header_value_parser.py b/.venv/lib/python3.12/site-packages/future/backports/email/_header_value_parser.py new file mode 100644 index 00000000..59b1b318 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/_header_value_parser.py @@ -0,0 +1,2965 @@ +"""Header value parser implementing various email-related RFC parsing rules. + +The parsing methods defined in this module implement various email related +parsing rules. Principal among them is RFC 5322, which is the followon +to RFC 2822 and primarily a clarification of the former. It also implements +RFC 2047 encoded word decoding. + +RFC 5322 goes to considerable trouble to maintain backward compatibility with +RFC 822 in the parse phase, while cleaning up the structure on the generation +phase. This parser supports correct RFC 5322 generation by tagging white space +as folding white space only when folding is allowed in the non-obsolete rule +sets. Actually, the parser is even more generous when accepting input than RFC +5322 mandates, following the spirit of Postel's Law, which RFC 5322 encourages. +Where possible deviations from the standard are annotated on the 'defects' +attribute of tokens that deviate. + +The general structure of the parser follows RFC 5322, and uses its terminology +where there is a direct correspondence. Where the implementation requires a +somewhat different structure than that used by the formal grammar, new terms +that mimic the closest existing terms are used. Thus, it really helps to have +a copy of RFC 5322 handy when studying this code. + +Input to the parser is a string that has already been unfolded according to +RFC 5322 rules. According to the RFC this unfolding is the very first step, and +this parser leaves the unfolding step to a higher level message parser, which +will have already detected the line breaks that need unfolding while +determining the beginning and end of each header. + +The output of the parser is a TokenList object, which is a list subclass. A +TokenList is a recursive data structure. The terminal nodes of the structure +are Terminal objects, which are subclasses of str. These do not correspond +directly to terminal objects in the formal grammar, but are instead more +practical higher level combinations of true terminals. + +All TokenList and Terminal objects have a 'value' attribute, which produces the +semantically meaningful value of that part of the parse subtree. The value of +all whitespace tokens (no matter how many sub-tokens they may contain) is a +single space, as per the RFC rules. This includes 'CFWS', which is herein +included in the general class of whitespace tokens. There is one exception to +the rule that whitespace tokens are collapsed into single spaces in values: in +the value of a 'bare-quoted-string' (a quoted-string with no leading or +trailing whitespace), any whitespace that appeared between the quotation marks +is preserved in the returned value. Note that in all Terminal strings quoted +pairs are turned into their unquoted values. + +All TokenList and Terminal objects also have a string value, which attempts to +be a "canonical" representation of the RFC-compliant form of the substring that +produced the parsed subtree, including minimal use of quoted pair quoting. +Whitespace runs are not collapsed. + +Comment tokens also have a 'content' attribute providing the string found +between the parens (including any nested comments) with whitespace preserved. + +All TokenList and Terminal objects have a 'defects' attribute which is a +possibly empty list all of the defects found while creating the token. Defects +may appear on any token in the tree, and a composite list of all defects in the +subtree is available through the 'all_defects' attribute of any node. (For +Terminal notes x.defects == x.all_defects.) + +Each object in a parse tree is called a 'token', and each has a 'token_type' +attribute that gives the name from the RFC 5322 grammar that it represents. +Not all RFC 5322 nodes are produced, and there is one non-RFC 5322 node that +may be produced: 'ptext'. A 'ptext' is a string of printable ascii characters. +It is returned in place of lists of (ctext/quoted-pair) and +(qtext/quoted-pair). + +XXX: provide complete list of token types. +""" +from __future__ import print_function +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import int, range, str, super, list + +import re +from collections import namedtuple, OrderedDict + +from future.backports.urllib.parse import (unquote, unquote_to_bytes) +from future.backports.email import _encoded_words as _ew +from future.backports.email import errors +from future.backports.email import utils + +# +# Useful constants and functions +# + +WSP = set(' \t') +CFWS_LEADER = WSP | set('(') +SPECIALS = set(r'()<>@,:;.\"[]') +ATOM_ENDS = SPECIALS | WSP +DOT_ATOM_ENDS = ATOM_ENDS - set('.') +# '.', '"', and '(' do not end phrases in order to support obs-phrase +PHRASE_ENDS = SPECIALS - set('."(') +TSPECIALS = (SPECIALS | set('/?=')) - set('.') +TOKEN_ENDS = TSPECIALS | WSP +ASPECIALS = TSPECIALS | set("*'%") +ATTRIBUTE_ENDS = ASPECIALS | WSP +EXTENDED_ATTRIBUTE_ENDS = ATTRIBUTE_ENDS - set('%') + +def quote_string(value): + return '"'+str(value).replace('\\', '\\\\').replace('"', r'\"')+'"' + +# +# Accumulator for header folding +# + +class _Folded(object): + + def __init__(self, maxlen, policy): + self.maxlen = maxlen + self.policy = policy + self.lastlen = 0 + self.stickyspace = None + self.firstline = True + self.done = [] + self.current = list() # uses l.clear() + + def newline(self): + self.done.extend(self.current) + self.done.append(self.policy.linesep) + self.current.clear() + self.lastlen = 0 + + def finalize(self): + if self.current: + self.newline() + + def __str__(self): + return ''.join(self.done) + + def append(self, stoken): + self.current.append(stoken) + + def append_if_fits(self, token, stoken=None): + if stoken is None: + stoken = str(token) + l = len(stoken) + if self.stickyspace is not None: + stickyspace_len = len(self.stickyspace) + if self.lastlen + stickyspace_len + l <= self.maxlen: + self.current.append(self.stickyspace) + self.lastlen += stickyspace_len + self.current.append(stoken) + self.lastlen += l + self.stickyspace = None + self.firstline = False + return True + if token.has_fws: + ws = token.pop_leading_fws() + if ws is not None: + self.stickyspace += str(ws) + stickyspace_len += len(ws) + token._fold(self) + return True + if stickyspace_len and l + 1 <= self.maxlen: + margin = self.maxlen - l + if 0 < margin < stickyspace_len: + trim = stickyspace_len - margin + self.current.append(self.stickyspace[:trim]) + self.stickyspace = self.stickyspace[trim:] + stickyspace_len = trim + self.newline() + self.current.append(self.stickyspace) + self.current.append(stoken) + self.lastlen = l + stickyspace_len + self.stickyspace = None + self.firstline = False + return True + if not self.firstline: + self.newline() + self.current.append(self.stickyspace) + self.current.append(stoken) + self.stickyspace = None + self.firstline = False + return True + if self.lastlen + l <= self.maxlen: + self.current.append(stoken) + self.lastlen += l + return True + if l < self.maxlen: + self.newline() + self.current.append(stoken) + self.lastlen = l + return True + return False + +# +# TokenList and its subclasses +# + +class TokenList(list): + + token_type = None + + def __init__(self, *args, **kw): + super(TokenList, self).__init__(*args, **kw) + self.defects = [] + + def __str__(self): + return ''.join(str(x) for x in self) + + def __repr__(self): + return '{}({})'.format(self.__class__.__name__, + super(TokenList, self).__repr__()) + + @property + def value(self): + return ''.join(x.value for x in self if x.value) + + @property + def all_defects(self): + return sum((x.all_defects for x in self), self.defects) + + # + # Folding API + # + # parts(): + # + # return a list of objects that constitute the "higher level syntactic + # objects" specified by the RFC as the best places to fold a header line. + # The returned objects must include leading folding white space, even if + # this means mutating the underlying parse tree of the object. Each object + # is only responsible for returning *its* parts, and should not drill down + # to any lower level except as required to meet the leading folding white + # space constraint. + # + # _fold(folded): + # + # folded: the result accumulator. This is an instance of _Folded. + # (XXX: I haven't finished factoring this out yet, the folding code + # pretty much uses this as a state object.) When the folded.current + # contains as much text as will fit, the _fold method should call + # folded.newline. + # folded.lastlen: the current length of the test stored in folded.current. + # folded.maxlen: The maximum number of characters that may appear on a + # folded line. Differs from the policy setting in that "no limit" is + # represented by +inf, which means it can be used in the trivially + # logical fashion in comparisons. + # + # Currently no subclasses implement parts, and I think this will remain + # true. A subclass only needs to implement _fold when the generic version + # isn't sufficient. _fold will need to be implemented primarily when it is + # possible for encoded words to appear in the specialized token-list, since + # there is no generic algorithm that can know where exactly the encoded + # words are allowed. A _fold implementation is responsible for filling + # lines in the same general way that the top level _fold does. It may, and + # should, call the _fold method of sub-objects in a similar fashion to that + # of the top level _fold. + # + # XXX: I'm hoping it will be possible to factor the existing code further + # to reduce redundancy and make the logic clearer. + + @property + def parts(self): + klass = self.__class__ + this = list() + for token in self: + if token.startswith_fws(): + if this: + yield this[0] if len(this)==1 else klass(this) + this.clear() + end_ws = token.pop_trailing_ws() + this.append(token) + if end_ws: + yield klass(this) + this = [end_ws] + if this: + yield this[0] if len(this)==1 else klass(this) + + def startswith_fws(self): + return self[0].startswith_fws() + + def pop_leading_fws(self): + if self[0].token_type == 'fws': + return self.pop(0) + return self[0].pop_leading_fws() + + def pop_trailing_ws(self): + if self[-1].token_type == 'cfws': + return self.pop(-1) + return self[-1].pop_trailing_ws() + + @property + def has_fws(self): + for part in self: + if part.has_fws: + return True + return False + + def has_leading_comment(self): + return self[0].has_leading_comment() + + @property + def comments(self): + comments = [] + for token in self: + comments.extend(token.comments) + return comments + + def fold(self, **_3to2kwargs): + # max_line_length 0/None means no limit, ie: infinitely long. + policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] + maxlen = policy.max_line_length or float("+inf") + folded = _Folded(maxlen, policy) + self._fold(folded) + folded.finalize() + return str(folded) + + def as_encoded_word(self, charset): + # This works only for things returned by 'parts', which include + # the leading fws, if any, that should be used. + res = [] + ws = self.pop_leading_fws() + if ws: + res.append(ws) + trailer = self.pop(-1) if self[-1].token_type=='fws' else '' + res.append(_ew.encode(str(self), charset)) + res.append(trailer) + return ''.join(res) + + def cte_encode(self, charset, policy): + res = [] + for part in self: + res.append(part.cte_encode(charset, policy)) + return ''.join(res) + + def _fold(self, folded): + for part in self.parts: + tstr = str(part) + tlen = len(tstr) + try: + str(part).encode('us-ascii') + except UnicodeEncodeError: + if any(isinstance(x, errors.UndecodableBytesDefect) + for x in part.all_defects): + charset = 'unknown-8bit' + else: + # XXX: this should be a policy setting + charset = 'utf-8' + tstr = part.cte_encode(charset, folded.policy) + tlen = len(tstr) + if folded.append_if_fits(part, tstr): + continue + # Peel off the leading whitespace if any and make it sticky, to + # avoid infinite recursion. + ws = part.pop_leading_fws() + if ws is not None: + # Peel off the leading whitespace and make it sticky, to + # avoid infinite recursion. + folded.stickyspace = str(part.pop(0)) + if folded.append_if_fits(part): + continue + if part.has_fws: + part._fold(folded) + continue + # There are no fold points in this one; it is too long for a single + # line and can't be split...we just have to put it on its own line. + folded.append(tstr) + folded.newline() + + def pprint(self, indent=''): + print('\n'.join(self._pp(indent=''))) + + def ppstr(self, indent=''): + return '\n'.join(self._pp(indent='')) + + def _pp(self, indent=''): + yield '{}{}/{}('.format( + indent, + self.__class__.__name__, + self.token_type) + for token in self: + if not hasattr(token, '_pp'): + yield (indent + ' !! invalid element in token ' + 'list: {!r}'.format(token)) + else: + for line in token._pp(indent+' '): + yield line + if self.defects: + extra = ' Defects: {}'.format(self.defects) + else: + extra = '' + yield '{}){}'.format(indent, extra) + + +class WhiteSpaceTokenList(TokenList): + + @property + def value(self): + return ' ' + + @property + def comments(self): + return [x.content for x in self if x.token_type=='comment'] + + +class UnstructuredTokenList(TokenList): + + token_type = 'unstructured' + + def _fold(self, folded): + if any(x.token_type=='encoded-word' for x in self): + return self._fold_encoded(folded) + # Here we can have either a pure ASCII string that may or may not + # have surrogateescape encoded bytes, or a unicode string. + last_ew = None + for part in self.parts: + tstr = str(part) + is_ew = False + try: + str(part).encode('us-ascii') + except UnicodeEncodeError: + if any(isinstance(x, errors.UndecodableBytesDefect) + for x in part.all_defects): + charset = 'unknown-8bit' + else: + charset = 'utf-8' + if last_ew is not None: + # We've already done an EW, combine this one with it + # if there's room. + chunk = get_unstructured( + ''.join(folded.current[last_ew:]+[tstr])).as_encoded_word(charset) + oldlastlen = sum(len(x) for x in folded.current[:last_ew]) + schunk = str(chunk) + lchunk = len(schunk) + if oldlastlen + lchunk <= folded.maxlen: + del folded.current[last_ew:] + folded.append(schunk) + folded.lastlen = oldlastlen + lchunk + continue + tstr = part.as_encoded_word(charset) + is_ew = True + if folded.append_if_fits(part, tstr): + if is_ew: + last_ew = len(folded.current) - 1 + continue + if is_ew or last_ew: + # It's too big to fit on the line, but since we've + # got encoded words we can use encoded word folding. + part._fold_as_ew(folded) + continue + # Peel off the leading whitespace if any and make it sticky, to + # avoid infinite recursion. + ws = part.pop_leading_fws() + if ws is not None: + folded.stickyspace = str(ws) + if folded.append_if_fits(part): + continue + if part.has_fws: + part.fold(folded) + continue + # It can't be split...we just have to put it on its own line. + folded.append(tstr) + folded.newline() + last_ew = None + + def cte_encode(self, charset, policy): + res = [] + last_ew = None + for part in self: + spart = str(part) + try: + spart.encode('us-ascii') + res.append(spart) + except UnicodeEncodeError: + if last_ew is None: + res.append(part.cte_encode(charset, policy)) + last_ew = len(res) + else: + tl = get_unstructured(''.join(res[last_ew:] + [spart])) + res.append(tl.as_encoded_word()) + return ''.join(res) + + +class Phrase(TokenList): + + token_type = 'phrase' + + def _fold(self, folded): + # As with Unstructured, we can have pure ASCII with or without + # surrogateescape encoded bytes, or we could have unicode. But this + # case is more complicated, since we have to deal with the various + # sub-token types and how they can be composed in the face of + # unicode-that-needs-CTE-encoding, and the fact that if a token a + # comment that becomes a barrier across which we can't compose encoded + # words. + last_ew = None + for part in self.parts: + tstr = str(part) + tlen = len(tstr) + has_ew = False + try: + str(part).encode('us-ascii') + except UnicodeEncodeError: + if any(isinstance(x, errors.UndecodableBytesDefect) + for x in part.all_defects): + charset = 'unknown-8bit' + else: + charset = 'utf-8' + if last_ew is not None and not part.has_leading_comment(): + # We've already done an EW, let's see if we can combine + # this one with it. The last_ew logic ensures that all we + # have at this point is atoms, no comments or quoted + # strings. So we can treat the text between the last + # encoded word and the content of this token as + # unstructured text, and things will work correctly. But + # we have to strip off any trailing comment on this token + # first, and if it is a quoted string we have to pull out + # the content (we're encoding it, so it no longer needs to + # be quoted). + if part[-1].token_type == 'cfws' and part.comments: + remainder = part.pop(-1) + else: + remainder = '' + for i, token in enumerate(part): + if token.token_type == 'bare-quoted-string': + part[i] = UnstructuredTokenList(token[:]) + chunk = get_unstructured( + ''.join(folded.current[last_ew:]+[tstr])).as_encoded_word(charset) + schunk = str(chunk) + lchunk = len(schunk) + if last_ew + lchunk <= folded.maxlen: + del folded.current[last_ew:] + folded.append(schunk) + folded.lastlen = sum(len(x) for x in folded.current) + continue + tstr = part.as_encoded_word(charset) + tlen = len(tstr) + has_ew = True + if folded.append_if_fits(part, tstr): + if has_ew and not part.comments: + last_ew = len(folded.current) - 1 + elif part.comments or part.token_type == 'quoted-string': + # If a comment is involved we can't combine EWs. And if a + # quoted string is involved, it's not worth the effort to + # try to combine them. + last_ew = None + continue + part._fold(folded) + + def cte_encode(self, charset, policy): + res = [] + last_ew = None + is_ew = False + for part in self: + spart = str(part) + try: + spart.encode('us-ascii') + res.append(spart) + except UnicodeEncodeError: + is_ew = True + if last_ew is None: + if not part.comments: + last_ew = len(res) + res.append(part.cte_encode(charset, policy)) + elif not part.has_leading_comment(): + if part[-1].token_type == 'cfws' and part.comments: + remainder = part.pop(-1) + else: + remainder = '' + for i, token in enumerate(part): + if token.token_type == 'bare-quoted-string': + part[i] = UnstructuredTokenList(token[:]) + tl = get_unstructured(''.join(res[last_ew:] + [spart])) + res[last_ew:] = [tl.as_encoded_word(charset)] + if part.comments or (not is_ew and part.token_type == 'quoted-string'): + last_ew = None + return ''.join(res) + +class Word(TokenList): + + token_type = 'word' + + +class CFWSList(WhiteSpaceTokenList): + + token_type = 'cfws' + + def has_leading_comment(self): + return bool(self.comments) + + +class Atom(TokenList): + + token_type = 'atom' + + +class Token(TokenList): + + token_type = 'token' + + +class EncodedWord(TokenList): + + token_type = 'encoded-word' + cte = None + charset = None + lang = None + + @property + def encoded(self): + if self.cte is not None: + return self.cte + _ew.encode(str(self), self.charset) + + + +class QuotedString(TokenList): + + token_type = 'quoted-string' + + @property + def content(self): + for x in self: + if x.token_type == 'bare-quoted-string': + return x.value + + @property + def quoted_value(self): + res = [] + for x in self: + if x.token_type == 'bare-quoted-string': + res.append(str(x)) + else: + res.append(x.value) + return ''.join(res) + + @property + def stripped_value(self): + for token in self: + if token.token_type == 'bare-quoted-string': + return token.value + + +class BareQuotedString(QuotedString): + + token_type = 'bare-quoted-string' + + def __str__(self): + return quote_string(''.join(str(x) for x in self)) + + @property + def value(self): + return ''.join(str(x) for x in self) + + +class Comment(WhiteSpaceTokenList): + + token_type = 'comment' + + def __str__(self): + return ''.join(sum([ + ["("], + [self.quote(x) for x in self], + [")"], + ], [])) + + def quote(self, value): + if value.token_type == 'comment': + return str(value) + return str(value).replace('\\', '\\\\').replace( + '(', '\(').replace( + ')', '\)') + + @property + def content(self): + return ''.join(str(x) for x in self) + + @property + def comments(self): + return [self.content] + +class AddressList(TokenList): + + token_type = 'address-list' + + @property + def addresses(self): + return [x for x in self if x.token_type=='address'] + + @property + def mailboxes(self): + return sum((x.mailboxes + for x in self if x.token_type=='address'), []) + + @property + def all_mailboxes(self): + return sum((x.all_mailboxes + for x in self if x.token_type=='address'), []) + + +class Address(TokenList): + + token_type = 'address' + + @property + def display_name(self): + if self[0].token_type == 'group': + return self[0].display_name + + @property + def mailboxes(self): + if self[0].token_type == 'mailbox': + return [self[0]] + elif self[0].token_type == 'invalid-mailbox': + return [] + return self[0].mailboxes + + @property + def all_mailboxes(self): + if self[0].token_type == 'mailbox': + return [self[0]] + elif self[0].token_type == 'invalid-mailbox': + return [self[0]] + return self[0].all_mailboxes + +class MailboxList(TokenList): + + token_type = 'mailbox-list' + + @property + def mailboxes(self): + return [x for x in self if x.token_type=='mailbox'] + + @property + def all_mailboxes(self): + return [x for x in self + if x.token_type in ('mailbox', 'invalid-mailbox')] + + +class GroupList(TokenList): + + token_type = 'group-list' + + @property + def mailboxes(self): + if not self or self[0].token_type != 'mailbox-list': + return [] + return self[0].mailboxes + + @property + def all_mailboxes(self): + if not self or self[0].token_type != 'mailbox-list': + return [] + return self[0].all_mailboxes + + +class Group(TokenList): + + token_type = "group" + + @property + def mailboxes(self): + if self[2].token_type != 'group-list': + return [] + return self[2].mailboxes + + @property + def all_mailboxes(self): + if self[2].token_type != 'group-list': + return [] + return self[2].all_mailboxes + + @property + def display_name(self): + return self[0].display_name + + +class NameAddr(TokenList): + + token_type = 'name-addr' + + @property + def display_name(self): + if len(self) == 1: + return None + return self[0].display_name + + @property + def local_part(self): + return self[-1].local_part + + @property + def domain(self): + return self[-1].domain + + @property + def route(self): + return self[-1].route + + @property + def addr_spec(self): + return self[-1].addr_spec + + +class AngleAddr(TokenList): + + token_type = 'angle-addr' + + @property + def local_part(self): + for x in self: + if x.token_type == 'addr-spec': + return x.local_part + + @property + def domain(self): + for x in self: + if x.token_type == 'addr-spec': + return x.domain + + @property + def route(self): + for x in self: + if x.token_type == 'obs-route': + return x.domains + + @property + def addr_spec(self): + for x in self: + if x.token_type == 'addr-spec': + return x.addr_spec + else: + return '<>' + + +class ObsRoute(TokenList): + + token_type = 'obs-route' + + @property + def domains(self): + return [x.domain for x in self if x.token_type == 'domain'] + + +class Mailbox(TokenList): + + token_type = 'mailbox' + + @property + def display_name(self): + if self[0].token_type == 'name-addr': + return self[0].display_name + + @property + def local_part(self): + return self[0].local_part + + @property + def domain(self): + return self[0].domain + + @property + def route(self): + if self[0].token_type == 'name-addr': + return self[0].route + + @property + def addr_spec(self): + return self[0].addr_spec + + +class InvalidMailbox(TokenList): + + token_type = 'invalid-mailbox' + + @property + def display_name(self): + return None + + local_part = domain = route = addr_spec = display_name + + +class Domain(TokenList): + + token_type = 'domain' + + @property + def domain(self): + return ''.join(super(Domain, self).value.split()) + + +class DotAtom(TokenList): + + token_type = 'dot-atom' + + +class DotAtomText(TokenList): + + token_type = 'dot-atom-text' + + +class AddrSpec(TokenList): + + token_type = 'addr-spec' + + @property + def local_part(self): + return self[0].local_part + + @property + def domain(self): + if len(self) < 3: + return None + return self[-1].domain + + @property + def value(self): + if len(self) < 3: + return self[0].value + return self[0].value.rstrip()+self[1].value+self[2].value.lstrip() + + @property + def addr_spec(self): + nameset = set(self.local_part) + if len(nameset) > len(nameset-DOT_ATOM_ENDS): + lp = quote_string(self.local_part) + else: + lp = self.local_part + if self.domain is not None: + return lp + '@' + self.domain + return lp + + +class ObsLocalPart(TokenList): + + token_type = 'obs-local-part' + + +class DisplayName(Phrase): + + token_type = 'display-name' + + @property + def display_name(self): + res = TokenList(self) + if res[0].token_type == 'cfws': + res.pop(0) + else: + if res[0][0].token_type == 'cfws': + res[0] = TokenList(res[0][1:]) + if res[-1].token_type == 'cfws': + res.pop() + else: + if res[-1][-1].token_type == 'cfws': + res[-1] = TokenList(res[-1][:-1]) + return res.value + + @property + def value(self): + quote = False + if self.defects: + quote = True + else: + for x in self: + if x.token_type == 'quoted-string': + quote = True + if quote: + pre = post = '' + if self[0].token_type=='cfws' or self[0][0].token_type=='cfws': + pre = ' ' + if self[-1].token_type=='cfws' or self[-1][-1].token_type=='cfws': + post = ' ' + return pre+quote_string(self.display_name)+post + else: + return super(DisplayName, self).value + + +class LocalPart(TokenList): + + token_type = 'local-part' + + @property + def value(self): + if self[0].token_type == "quoted-string": + return self[0].quoted_value + else: + return self[0].value + + @property + def local_part(self): + # Strip whitespace from front, back, and around dots. + res = [DOT] + last = DOT + last_is_tl = False + for tok in self[0] + [DOT]: + if tok.token_type == 'cfws': + continue + if (last_is_tl and tok.token_type == 'dot' and + last[-1].token_type == 'cfws'): + res[-1] = TokenList(last[:-1]) + is_tl = isinstance(tok, TokenList) + if (is_tl and last.token_type == 'dot' and + tok[0].token_type == 'cfws'): + res.append(TokenList(tok[1:])) + else: + res.append(tok) + last = res[-1] + last_is_tl = is_tl + res = TokenList(res[1:-1]) + return res.value + + +class DomainLiteral(TokenList): + + token_type = 'domain-literal' + + @property + def domain(self): + return ''.join(super(DomainLiteral, self).value.split()) + + @property + def ip(self): + for x in self: + if x.token_type == 'ptext': + return x.value + + +class MIMEVersion(TokenList): + + token_type = 'mime-version' + major = None + minor = None + + +class Parameter(TokenList): + + token_type = 'parameter' + sectioned = False + extended = False + charset = 'us-ascii' + + @property + def section_number(self): + # Because the first token, the attribute (name) eats CFWS, the second + # token is always the section if there is one. + return self[1].number if self.sectioned else 0 + + @property + def param_value(self): + # This is part of the "handle quoted extended parameters" hack. + for token in self: + if token.token_type == 'value': + return token.stripped_value + if token.token_type == 'quoted-string': + for token in token: + if token.token_type == 'bare-quoted-string': + for token in token: + if token.token_type == 'value': + return token.stripped_value + return '' + + +class InvalidParameter(Parameter): + + token_type = 'invalid-parameter' + + +class Attribute(TokenList): + + token_type = 'attribute' + + @property + def stripped_value(self): + for token in self: + if token.token_type.endswith('attrtext'): + return token.value + +class Section(TokenList): + + token_type = 'section' + number = None + + +class Value(TokenList): + + token_type = 'value' + + @property + def stripped_value(self): + token = self[0] + if token.token_type == 'cfws': + token = self[1] + if token.token_type.endswith( + ('quoted-string', 'attribute', 'extended-attribute')): + return token.stripped_value + return self.value + + +class MimeParameters(TokenList): + + token_type = 'mime-parameters' + + @property + def params(self): + # The RFC specifically states that the ordering of parameters is not + # guaranteed and may be reordered by the transport layer. So we have + # to assume the RFC 2231 pieces can come in any order. However, we + # output them in the order that we first see a given name, which gives + # us a stable __str__. + params = OrderedDict() + for token in self: + if not token.token_type.endswith('parameter'): + continue + if token[0].token_type != 'attribute': + continue + name = token[0].value.strip() + if name not in params: + params[name] = [] + params[name].append((token.section_number, token)) + for name, parts in params.items(): + parts = sorted(parts) + # XXX: there might be more recovery we could do here if, for + # example, this is really a case of a duplicate attribute name. + value_parts = [] + charset = parts[0][1].charset + for i, (section_number, param) in enumerate(parts): + if section_number != i: + param.defects.append(errors.InvalidHeaderDefect( + "inconsistent multipart parameter numbering")) + value = param.param_value + if param.extended: + try: + value = unquote_to_bytes(value) + except UnicodeEncodeError: + # source had surrogate escaped bytes. What we do now + # is a bit of an open question. I'm not sure this is + # the best choice, but it is what the old algorithm did + value = unquote(value, encoding='latin-1') + else: + try: + value = value.decode(charset, 'surrogateescape') + except LookupError: + # XXX: there should really be a custom defect for + # unknown character set to make it easy to find, + # because otherwise unknown charset is a silent + # failure. + value = value.decode('us-ascii', 'surrogateescape') + if utils._has_surrogates(value): + param.defects.append(errors.UndecodableBytesDefect()) + value_parts.append(value) + value = ''.join(value_parts) + yield name, value + + def __str__(self): + params = [] + for name, value in self.params: + if value: + params.append('{}={}'.format(name, quote_string(value))) + else: + params.append(name) + params = '; '.join(params) + return ' ' + params if params else '' + + +class ParameterizedHeaderValue(TokenList): + + @property + def params(self): + for token in reversed(self): + if token.token_type == 'mime-parameters': + return token.params + return {} + + @property + def parts(self): + if self and self[-1].token_type == 'mime-parameters': + # We don't want to start a new line if all of the params don't fit + # after the value, so unwrap the parameter list. + return TokenList(self[:-1] + self[-1]) + return TokenList(self).parts + + +class ContentType(ParameterizedHeaderValue): + + token_type = 'content-type' + maintype = 'text' + subtype = 'plain' + + +class ContentDisposition(ParameterizedHeaderValue): + + token_type = 'content-disposition' + content_disposition = None + + +class ContentTransferEncoding(TokenList): + + token_type = 'content-transfer-encoding' + cte = '7bit' + + +class HeaderLabel(TokenList): + + token_type = 'header-label' + + +class Header(TokenList): + + token_type = 'header' + + def _fold(self, folded): + folded.append(str(self.pop(0))) + folded.lastlen = len(folded.current[0]) + # The first line of the header is different from all others: we don't + # want to start a new object on a new line if it has any fold points in + # it that would allow part of it to be on the first header line. + # Further, if the first fold point would fit on the new line, we want + # to do that, but if it doesn't we want to put it on the first line. + # Folded supports this via the stickyspace attribute. If this + # attribute is not None, it does the special handling. + folded.stickyspace = str(self.pop(0)) if self[0].token_type == 'cfws' else '' + rest = self.pop(0) + if self: + raise ValueError("Malformed Header token list") + rest._fold(folded) + + +# +# Terminal classes and instances +# + +class Terminal(str): + + def __new__(cls, value, token_type): + self = super(Terminal, cls).__new__(cls, value) + self.token_type = token_type + self.defects = [] + return self + + def __repr__(self): + return "{}({})".format(self.__class__.__name__, super(Terminal, self).__repr__()) + + @property + def all_defects(self): + return list(self.defects) + + def _pp(self, indent=''): + return ["{}{}/{}({}){}".format( + indent, + self.__class__.__name__, + self.token_type, + super(Terminal, self).__repr__(), + '' if not self.defects else ' {}'.format(self.defects), + )] + + def cte_encode(self, charset, policy): + value = str(self) + try: + value.encode('us-ascii') + return value + except UnicodeEncodeError: + return _ew.encode(value, charset) + + def pop_trailing_ws(self): + # This terminates the recursion. + return None + + def pop_leading_fws(self): + # This terminates the recursion. + return None + + @property + def comments(self): + return [] + + def has_leading_comment(self): + return False + + def __getnewargs__(self): + return(str(self), self.token_type) + + +class WhiteSpaceTerminal(Terminal): + + @property + def value(self): + return ' ' + + def startswith_fws(self): + return True + + has_fws = True + + +class ValueTerminal(Terminal): + + @property + def value(self): + return self + + def startswith_fws(self): + return False + + has_fws = False + + def as_encoded_word(self, charset): + return _ew.encode(str(self), charset) + + +class EWWhiteSpaceTerminal(WhiteSpaceTerminal): + + @property + def value(self): + return '' + + @property + def encoded(self): + return self[:] + + def __str__(self): + return '' + + has_fws = True + + +# XXX these need to become classes and used as instances so +# that a program can't change them in a parse tree and screw +# up other parse trees. Maybe should have tests for that, too. +DOT = ValueTerminal('.', 'dot') +ListSeparator = ValueTerminal(',', 'list-separator') +RouteComponentMarker = ValueTerminal('@', 'route-component-marker') + +# +# Parser +# + +"""Parse strings according to RFC822/2047/2822/5322 rules. + +This is a stateless parser. Each get_XXX function accepts a string and +returns either a Terminal or a TokenList representing the RFC object named +by the method and a string containing the remaining unparsed characters +from the input. Thus a parser method consumes the next syntactic construct +of a given type and returns a token representing the construct plus the +unparsed remainder of the input string. + +For example, if the first element of a structured header is a 'phrase', +then: + + phrase, value = get_phrase(value) + +returns the complete phrase from the start of the string value, plus any +characters left in the string after the phrase is removed. + +""" + +_wsp_splitter = re.compile(r'([{}]+)'.format(''.join(WSP))).split +_non_atom_end_matcher = re.compile(r"[^{}]+".format( + ''.join(ATOM_ENDS).replace('\\','\\\\').replace(']','\]'))).match +_non_printable_finder = re.compile(r"[\x00-\x20\x7F]").findall +_non_token_end_matcher = re.compile(r"[^{}]+".format( + ''.join(TOKEN_ENDS).replace('\\','\\\\').replace(']','\]'))).match +_non_attribute_end_matcher = re.compile(r"[^{}]+".format( + ''.join(ATTRIBUTE_ENDS).replace('\\','\\\\').replace(']','\]'))).match +_non_extended_attribute_end_matcher = re.compile(r"[^{}]+".format( + ''.join(EXTENDED_ATTRIBUTE_ENDS).replace( + '\\','\\\\').replace(']','\]'))).match + +def _validate_xtext(xtext): + """If input token contains ASCII non-printables, register a defect.""" + + non_printables = _non_printable_finder(xtext) + if non_printables: + xtext.defects.append(errors.NonPrintableDefect(non_printables)) + if utils._has_surrogates(xtext): + xtext.defects.append(errors.UndecodableBytesDefect( + "Non-ASCII characters found in header token")) + +def _get_ptext_to_endchars(value, endchars): + """Scan printables/quoted-pairs until endchars and return unquoted ptext. + + This function turns a run of qcontent, ccontent-without-comments, or + dtext-with-quoted-printables into a single string by unquoting any + quoted printables. It returns the string, the remaining value, and + a flag that is True iff there were any quoted printables decoded. + + """ + _3to2list = list(_wsp_splitter(value, 1)) + fragment, remainder, = _3to2list[:1] + [_3to2list[1:]] + vchars = [] + escape = False + had_qp = False + for pos in range(len(fragment)): + if fragment[pos] == '\\': + if escape: + escape = False + had_qp = True + else: + escape = True + continue + if escape: + escape = False + elif fragment[pos] in endchars: + break + vchars.append(fragment[pos]) + else: + pos = pos + 1 + return ''.join(vchars), ''.join([fragment[pos:]] + remainder), had_qp + +def _decode_ew_run(value): + """ Decode a run of RFC2047 encoded words. + + _decode_ew_run(value) -> (text, value, defects) + + Scans the supplied value for a run of tokens that look like they are RFC + 2047 encoded words, decodes those words into text according to RFC 2047 + rules (whitespace between encoded words is discarded), and returns the text + and the remaining value (including any leading whitespace on the remaining + value), as well as a list of any defects encountered while decoding. The + input value may not have any leading whitespace. + + """ + res = [] + defects = [] + last_ws = '' + while value: + try: + tok, ws, value = _wsp_splitter(value, 1) + except ValueError: + tok, ws, value = value, '', '' + if not (tok.startswith('=?') and tok.endswith('?=')): + return ''.join(res), last_ws + tok + ws + value, defects + text, charset, lang, new_defects = _ew.decode(tok) + res.append(text) + defects.extend(new_defects) + last_ws = ws + return ''.join(res), last_ws, defects + +def get_fws(value): + """FWS = 1*WSP + + This isn't the RFC definition. We're using fws to represent tokens where + folding can be done, but when we are parsing the *un*folding has already + been done so we don't need to watch out for CRLF. + + """ + newvalue = value.lstrip() + fws = WhiteSpaceTerminal(value[:len(value)-len(newvalue)], 'fws') + return fws, newvalue + +def get_encoded_word(value): + """ encoded-word = "=?" charset "?" encoding "?" encoded-text "?=" + + """ + ew = EncodedWord() + if not value.startswith('=?'): + raise errors.HeaderParseError( + "expected encoded word but found {}".format(value)) + _3to2list1 = list(value[2:].split('?=', 1)) + tok, remainder, = _3to2list1[:1] + [_3to2list1[1:]] + if tok == value[2:]: + raise errors.HeaderParseError( + "expected encoded word but found {}".format(value)) + remstr = ''.join(remainder) + if remstr[:2].isdigit(): + _3to2list3 = list(remstr.split('?=', 1)) + rest, remainder, = _3to2list3[:1] + [_3to2list3[1:]] + tok = tok + '?=' + rest + if len(tok.split()) > 1: + ew.defects.append(errors.InvalidHeaderDefect( + "whitespace inside encoded word")) + ew.cte = value + value = ''.join(remainder) + try: + text, charset, lang, defects = _ew.decode('=?' + tok + '?=') + except ValueError: + raise errors.HeaderParseError( + "encoded word format invalid: '{}'".format(ew.cte)) + ew.charset = charset + ew.lang = lang + ew.defects.extend(defects) + while text: + if text[0] in WSP: + token, text = get_fws(text) + ew.append(token) + continue + _3to2list5 = list(_wsp_splitter(text, 1)) + chars, remainder, = _3to2list5[:1] + [_3to2list5[1:]] + vtext = ValueTerminal(chars, 'vtext') + _validate_xtext(vtext) + ew.append(vtext) + text = ''.join(remainder) + return ew, value + +def get_unstructured(value): + """unstructured = (*([FWS] vchar) *WSP) / obs-unstruct + obs-unstruct = *((*LF *CR *(obs-utext) *LF *CR)) / FWS) + obs-utext = %d0 / obs-NO-WS-CTL / LF / CR + + obs-NO-WS-CTL is control characters except WSP/CR/LF. + + So, basically, we have printable runs, plus control characters or nulls in + the obsolete syntax, separated by whitespace. Since RFC 2047 uses the + obsolete syntax in its specification, but requires whitespace on either + side of the encoded words, I can see no reason to need to separate the + non-printable-non-whitespace from the printable runs if they occur, so we + parse this into xtext tokens separated by WSP tokens. + + Because an 'unstructured' value must by definition constitute the entire + value, this 'get' routine does not return a remaining value, only the + parsed TokenList. + + """ + # XXX: but what about bare CR and LF? They might signal the start or + # end of an encoded word. YAGNI for now, since out current parsers + # will never send us strings with bard CR or LF. + + unstructured = UnstructuredTokenList() + while value: + if value[0] in WSP: + token, value = get_fws(value) + unstructured.append(token) + continue + if value.startswith('=?'): + try: + token, value = get_encoded_word(value) + except errors.HeaderParseError: + pass + else: + have_ws = True + if len(unstructured) > 0: + if unstructured[-1].token_type != 'fws': + unstructured.defects.append(errors.InvalidHeaderDefect( + "missing whitespace before encoded word")) + have_ws = False + if have_ws and len(unstructured) > 1: + if unstructured[-2].token_type == 'encoded-word': + unstructured[-1] = EWWhiteSpaceTerminal( + unstructured[-1], 'fws') + unstructured.append(token) + continue + _3to2list7 = list(_wsp_splitter(value, 1)) + tok, remainder, = _3to2list7[:1] + [_3to2list7[1:]] + vtext = ValueTerminal(tok, 'vtext') + _validate_xtext(vtext) + unstructured.append(vtext) + value = ''.join(remainder) + return unstructured + +def get_qp_ctext(value): + """ctext = <printable ascii except \ ( )> + + This is not the RFC ctext, since we are handling nested comments in comment + and unquoting quoted-pairs here. We allow anything except the '()' + characters, but if we find any ASCII other than the RFC defined printable + ASCII an NonPrintableDefect is added to the token's defects list. Since + quoted pairs are converted to their unquoted values, what is returned is + a 'ptext' token. In this case it is a WhiteSpaceTerminal, so it's value + is ' '. + + """ + ptext, value, _ = _get_ptext_to_endchars(value, '()') + ptext = WhiteSpaceTerminal(ptext, 'ptext') + _validate_xtext(ptext) + return ptext, value + +def get_qcontent(value): + """qcontent = qtext / quoted-pair + + We allow anything except the DQUOTE character, but if we find any ASCII + other than the RFC defined printable ASCII an NonPrintableDefect is + added to the token's defects list. Any quoted pairs are converted to their + unquoted values, so what is returned is a 'ptext' token. In this case it + is a ValueTerminal. + + """ + ptext, value, _ = _get_ptext_to_endchars(value, '"') + ptext = ValueTerminal(ptext, 'ptext') + _validate_xtext(ptext) + return ptext, value + +def get_atext(value): + """atext = <matches _atext_matcher> + + We allow any non-ATOM_ENDS in atext, but add an InvalidATextDefect to + the token's defects list if we find non-atext characters. + """ + m = _non_atom_end_matcher(value) + if not m: + raise errors.HeaderParseError( + "expected atext but found '{}'".format(value)) + atext = m.group() + value = value[len(atext):] + atext = ValueTerminal(atext, 'atext') + _validate_xtext(atext) + return atext, value + +def get_bare_quoted_string(value): + """bare-quoted-string = DQUOTE *([FWS] qcontent) [FWS] DQUOTE + + A quoted-string without the leading or trailing white space. Its + value is the text between the quote marks, with whitespace + preserved and quoted pairs decoded. + """ + if value[0] != '"': + raise errors.HeaderParseError( + "expected '\"' but found '{}'".format(value)) + bare_quoted_string = BareQuotedString() + value = value[1:] + while value and value[0] != '"': + if value[0] in WSP: + token, value = get_fws(value) + else: + token, value = get_qcontent(value) + bare_quoted_string.append(token) + if not value: + bare_quoted_string.defects.append(errors.InvalidHeaderDefect( + "end of header inside quoted string")) + return bare_quoted_string, value + return bare_quoted_string, value[1:] + +def get_comment(value): + """comment = "(" *([FWS] ccontent) [FWS] ")" + ccontent = ctext / quoted-pair / comment + + We handle nested comments here, and quoted-pair in our qp-ctext routine. + """ + if value and value[0] != '(': + raise errors.HeaderParseError( + "expected '(' but found '{}'".format(value)) + comment = Comment() + value = value[1:] + while value and value[0] != ")": + if value[0] in WSP: + token, value = get_fws(value) + elif value[0] == '(': + token, value = get_comment(value) + else: + token, value = get_qp_ctext(value) + comment.append(token) + if not value: + comment.defects.append(errors.InvalidHeaderDefect( + "end of header inside comment")) + return comment, value + return comment, value[1:] + +def get_cfws(value): + """CFWS = (1*([FWS] comment) [FWS]) / FWS + + """ + cfws = CFWSList() + while value and value[0] in CFWS_LEADER: + if value[0] in WSP: + token, value = get_fws(value) + else: + token, value = get_comment(value) + cfws.append(token) + return cfws, value + +def get_quoted_string(value): + """quoted-string = [CFWS] <bare-quoted-string> [CFWS] + + 'bare-quoted-string' is an intermediate class defined by this + parser and not by the RFC grammar. It is the quoted string + without any attached CFWS. + """ + quoted_string = QuotedString() + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + quoted_string.append(token) + token, value = get_bare_quoted_string(value) + quoted_string.append(token) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + quoted_string.append(token) + return quoted_string, value + +def get_atom(value): + """atom = [CFWS] 1*atext [CFWS] + + """ + atom = Atom() + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + atom.append(token) + if value and value[0] in ATOM_ENDS: + raise errors.HeaderParseError( + "expected atom but found '{}'".format(value)) + token, value = get_atext(value) + atom.append(token) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + atom.append(token) + return atom, value + +def get_dot_atom_text(value): + """ dot-text = 1*atext *("." 1*atext) + + """ + dot_atom_text = DotAtomText() + if not value or value[0] in ATOM_ENDS: + raise errors.HeaderParseError("expected atom at a start of " + "dot-atom-text but found '{}'".format(value)) + while value and value[0] not in ATOM_ENDS: + token, value = get_atext(value) + dot_atom_text.append(token) + if value and value[0] == '.': + dot_atom_text.append(DOT) + value = value[1:] + if dot_atom_text[-1] is DOT: + raise errors.HeaderParseError("expected atom at end of dot-atom-text " + "but found '{}'".format('.'+value)) + return dot_atom_text, value + +def get_dot_atom(value): + """ dot-atom = [CFWS] dot-atom-text [CFWS] + + """ + dot_atom = DotAtom() + if value[0] in CFWS_LEADER: + token, value = get_cfws(value) + dot_atom.append(token) + token, value = get_dot_atom_text(value) + dot_atom.append(token) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + dot_atom.append(token) + return dot_atom, value + +def get_word(value): + """word = atom / quoted-string + + Either atom or quoted-string may start with CFWS. We have to peel off this + CFWS first to determine which type of word to parse. Afterward we splice + the leading CFWS, if any, into the parsed sub-token. + + If neither an atom or a quoted-string is found before the next special, a + HeaderParseError is raised. + + The token returned is either an Atom or a QuotedString, as appropriate. + This means the 'word' level of the formal grammar is not represented in the + parse tree; this is because having that extra layer when manipulating the + parse tree is more confusing than it is helpful. + + """ + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + else: + leader = None + if value[0]=='"': + token, value = get_quoted_string(value) + elif value[0] in SPECIALS: + raise errors.HeaderParseError("Expected 'atom' or 'quoted-string' " + "but found '{}'".format(value)) + else: + token, value = get_atom(value) + if leader is not None: + token[:0] = [leader] + return token, value + +def get_phrase(value): + """ phrase = 1*word / obs-phrase + obs-phrase = word *(word / "." / CFWS) + + This means a phrase can be a sequence of words, periods, and CFWS in any + order as long as it starts with at least one word. If anything other than + words is detected, an ObsoleteHeaderDefect is added to the token's defect + list. We also accept a phrase that starts with CFWS followed by a dot; + this is registered as an InvalidHeaderDefect, since it is not supported by + even the obsolete grammar. + + """ + phrase = Phrase() + try: + token, value = get_word(value) + phrase.append(token) + except errors.HeaderParseError: + phrase.defects.append(errors.InvalidHeaderDefect( + "phrase does not start with word")) + while value and value[0] not in PHRASE_ENDS: + if value[0]=='.': + phrase.append(DOT) + phrase.defects.append(errors.ObsoleteHeaderDefect( + "period in 'phrase'")) + value = value[1:] + else: + try: + token, value = get_word(value) + except errors.HeaderParseError: + if value[0] in CFWS_LEADER: + token, value = get_cfws(value) + phrase.defects.append(errors.ObsoleteHeaderDefect( + "comment found without atom")) + else: + raise + phrase.append(token) + return phrase, value + +def get_local_part(value): + """ local-part = dot-atom / quoted-string / obs-local-part + + """ + local_part = LocalPart() + leader = None + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value: + raise errors.HeaderParseError( + "expected local-part but found '{}'".format(value)) + try: + token, value = get_dot_atom(value) + except errors.HeaderParseError: + try: + token, value = get_word(value) + except errors.HeaderParseError: + if value[0] != '\\' and value[0] in PHRASE_ENDS: + raise + token = TokenList() + if leader is not None: + token[:0] = [leader] + local_part.append(token) + if value and (value[0]=='\\' or value[0] not in PHRASE_ENDS): + obs_local_part, value = get_obs_local_part(str(local_part) + value) + if obs_local_part.token_type == 'invalid-obs-local-part': + local_part.defects.append(errors.InvalidHeaderDefect( + "local-part is not dot-atom, quoted-string, or obs-local-part")) + else: + local_part.defects.append(errors.ObsoleteHeaderDefect( + "local-part is not a dot-atom (contains CFWS)")) + local_part[0] = obs_local_part + try: + local_part.value.encode('ascii') + except UnicodeEncodeError: + local_part.defects.append(errors.NonASCIILocalPartDefect( + "local-part contains non-ASCII characters)")) + return local_part, value + +def get_obs_local_part(value): + """ obs-local-part = word *("." word) + """ + obs_local_part = ObsLocalPart() + last_non_ws_was_dot = False + while value and (value[0]=='\\' or value[0] not in PHRASE_ENDS): + if value[0] == '.': + if last_non_ws_was_dot: + obs_local_part.defects.append(errors.InvalidHeaderDefect( + "invalid repeated '.'")) + obs_local_part.append(DOT) + last_non_ws_was_dot = True + value = value[1:] + continue + elif value[0]=='\\': + obs_local_part.append(ValueTerminal(value[0], + 'misplaced-special')) + value = value[1:] + obs_local_part.defects.append(errors.InvalidHeaderDefect( + "'\\' character outside of quoted-string/ccontent")) + last_non_ws_was_dot = False + continue + if obs_local_part and obs_local_part[-1].token_type != 'dot': + obs_local_part.defects.append(errors.InvalidHeaderDefect( + "missing '.' between words")) + try: + token, value = get_word(value) + last_non_ws_was_dot = False + except errors.HeaderParseError: + if value[0] not in CFWS_LEADER: + raise + token, value = get_cfws(value) + obs_local_part.append(token) + if (obs_local_part[0].token_type == 'dot' or + obs_local_part[0].token_type=='cfws' and + obs_local_part[1].token_type=='dot'): + obs_local_part.defects.append(errors.InvalidHeaderDefect( + "Invalid leading '.' in local part")) + if (obs_local_part[-1].token_type == 'dot' or + obs_local_part[-1].token_type=='cfws' and + obs_local_part[-2].token_type=='dot'): + obs_local_part.defects.append(errors.InvalidHeaderDefect( + "Invalid trailing '.' in local part")) + if obs_local_part.defects: + obs_local_part.token_type = 'invalid-obs-local-part' + return obs_local_part, value + +def get_dtext(value): + """ dtext = <printable ascii except \ [ ]> / obs-dtext + obs-dtext = obs-NO-WS-CTL / quoted-pair + + We allow anything except the excluded characters, but if we find any + ASCII other than the RFC defined printable ASCII an NonPrintableDefect is + added to the token's defects list. Quoted pairs are converted to their + unquoted values, so what is returned is a ptext token, in this case a + ValueTerminal. If there were quoted-printables, an ObsoleteHeaderDefect is + added to the returned token's defect list. + + """ + ptext, value, had_qp = _get_ptext_to_endchars(value, '[]') + ptext = ValueTerminal(ptext, 'ptext') + if had_qp: + ptext.defects.append(errors.ObsoleteHeaderDefect( + "quoted printable found in domain-literal")) + _validate_xtext(ptext) + return ptext, value + +def _check_for_early_dl_end(value, domain_literal): + if value: + return False + domain_literal.append(errors.InvalidHeaderDefect( + "end of input inside domain-literal")) + domain_literal.append(ValueTerminal(']', 'domain-literal-end')) + return True + +def get_domain_literal(value): + """ domain-literal = [CFWS] "[" *([FWS] dtext) [FWS] "]" [CFWS] + + """ + domain_literal = DomainLiteral() + if value[0] in CFWS_LEADER: + token, value = get_cfws(value) + domain_literal.append(token) + if not value: + raise errors.HeaderParseError("expected domain-literal") + if value[0] != '[': + raise errors.HeaderParseError("expected '[' at start of domain-literal " + "but found '{}'".format(value)) + value = value[1:] + if _check_for_early_dl_end(value, domain_literal): + return domain_literal, value + domain_literal.append(ValueTerminal('[', 'domain-literal-start')) + if value[0] in WSP: + token, value = get_fws(value) + domain_literal.append(token) + token, value = get_dtext(value) + domain_literal.append(token) + if _check_for_early_dl_end(value, domain_literal): + return domain_literal, value + if value[0] in WSP: + token, value = get_fws(value) + domain_literal.append(token) + if _check_for_early_dl_end(value, domain_literal): + return domain_literal, value + if value[0] != ']': + raise errors.HeaderParseError("expected ']' at end of domain-literal " + "but found '{}'".format(value)) + domain_literal.append(ValueTerminal(']', 'domain-literal-end')) + value = value[1:] + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + domain_literal.append(token) + return domain_literal, value + +def get_domain(value): + """ domain = dot-atom / domain-literal / obs-domain + obs-domain = atom *("." atom)) + + """ + domain = Domain() + leader = None + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value: + raise errors.HeaderParseError( + "expected domain but found '{}'".format(value)) + if value[0] == '[': + token, value = get_domain_literal(value) + if leader is not None: + token[:0] = [leader] + domain.append(token) + return domain, value + try: + token, value = get_dot_atom(value) + except errors.HeaderParseError: + token, value = get_atom(value) + if leader is not None: + token[:0] = [leader] + domain.append(token) + if value and value[0] == '.': + domain.defects.append(errors.ObsoleteHeaderDefect( + "domain is not a dot-atom (contains CFWS)")) + if domain[0].token_type == 'dot-atom': + domain[:] = domain[0] + while value and value[0] == '.': + domain.append(DOT) + token, value = get_atom(value[1:]) + domain.append(token) + return domain, value + +def get_addr_spec(value): + """ addr-spec = local-part "@" domain + + """ + addr_spec = AddrSpec() + token, value = get_local_part(value) + addr_spec.append(token) + if not value or value[0] != '@': + addr_spec.defects.append(errors.InvalidHeaderDefect( + "add-spec local part with no domain")) + return addr_spec, value + addr_spec.append(ValueTerminal('@', 'address-at-symbol')) + token, value = get_domain(value[1:]) + addr_spec.append(token) + return addr_spec, value + +def get_obs_route(value): + """ obs-route = obs-domain-list ":" + obs-domain-list = *(CFWS / ",") "@" domain *("," [CFWS] ["@" domain]) + + Returns an obs-route token with the appropriate sub-tokens (that is, + there is no obs-domain-list in the parse tree). + """ + obs_route = ObsRoute() + while value and (value[0]==',' or value[0] in CFWS_LEADER): + if value[0] in CFWS_LEADER: + token, value = get_cfws(value) + obs_route.append(token) + elif value[0] == ',': + obs_route.append(ListSeparator) + value = value[1:] + if not value or value[0] != '@': + raise errors.HeaderParseError( + "expected obs-route domain but found '{}'".format(value)) + obs_route.append(RouteComponentMarker) + token, value = get_domain(value[1:]) + obs_route.append(token) + while value and value[0]==',': + obs_route.append(ListSeparator) + value = value[1:] + if not value: + break + if value[0] in CFWS_LEADER: + token, value = get_cfws(value) + obs_route.append(token) + if value[0] == '@': + obs_route.append(RouteComponentMarker) + token, value = get_domain(value[1:]) + obs_route.append(token) + if not value: + raise errors.HeaderParseError("end of header while parsing obs-route") + if value[0] != ':': + raise errors.HeaderParseError( "expected ':' marking end of " + "obs-route but found '{}'".format(value)) + obs_route.append(ValueTerminal(':', 'end-of-obs-route-marker')) + return obs_route, value[1:] + +def get_angle_addr(value): + """ angle-addr = [CFWS] "<" addr-spec ">" [CFWS] / obs-angle-addr + obs-angle-addr = [CFWS] "<" obs-route addr-spec ">" [CFWS] + + """ + angle_addr = AngleAddr() + if value[0] in CFWS_LEADER: + token, value = get_cfws(value) + angle_addr.append(token) + if not value or value[0] != '<': + raise errors.HeaderParseError( + "expected angle-addr but found '{}'".format(value)) + angle_addr.append(ValueTerminal('<', 'angle-addr-start')) + value = value[1:] + # Although it is not legal per RFC5322, SMTP uses '<>' in certain + # circumstances. + if value[0] == '>': + angle_addr.append(ValueTerminal('>', 'angle-addr-end')) + angle_addr.defects.append(errors.InvalidHeaderDefect( + "null addr-spec in angle-addr")) + value = value[1:] + return angle_addr, value + try: + token, value = get_addr_spec(value) + except errors.HeaderParseError: + try: + token, value = get_obs_route(value) + angle_addr.defects.append(errors.ObsoleteHeaderDefect( + "obsolete route specification in angle-addr")) + except errors.HeaderParseError: + raise errors.HeaderParseError( + "expected addr-spec or obs-route but found '{}'".format(value)) + angle_addr.append(token) + token, value = get_addr_spec(value) + angle_addr.append(token) + if value and value[0] == '>': + value = value[1:] + else: + angle_addr.defects.append(errors.InvalidHeaderDefect( + "missing trailing '>' on angle-addr")) + angle_addr.append(ValueTerminal('>', 'angle-addr-end')) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + angle_addr.append(token) + return angle_addr, value + +def get_display_name(value): + """ display-name = phrase + + Because this is simply a name-rule, we don't return a display-name + token containing a phrase, but rather a display-name token with + the content of the phrase. + + """ + display_name = DisplayName() + token, value = get_phrase(value) + display_name.extend(token[:]) + display_name.defects = token.defects[:] + return display_name, value + + +def get_name_addr(value): + """ name-addr = [display-name] angle-addr + + """ + name_addr = NameAddr() + # Both the optional display name and the angle-addr can start with cfws. + leader = None + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value: + raise errors.HeaderParseError( + "expected name-addr but found '{}'".format(leader)) + if value[0] != '<': + if value[0] in PHRASE_ENDS: + raise errors.HeaderParseError( + "expected name-addr but found '{}'".format(value)) + token, value = get_display_name(value) + if not value: + raise errors.HeaderParseError( + "expected name-addr but found '{}'".format(token)) + if leader is not None: + token[0][:0] = [leader] + leader = None + name_addr.append(token) + token, value = get_angle_addr(value) + if leader is not None: + token[:0] = [leader] + name_addr.append(token) + return name_addr, value + +def get_mailbox(value): + """ mailbox = name-addr / addr-spec + + """ + # The only way to figure out if we are dealing with a name-addr or an + # addr-spec is to try parsing each one. + mailbox = Mailbox() + try: + token, value = get_name_addr(value) + except errors.HeaderParseError: + try: + token, value = get_addr_spec(value) + except errors.HeaderParseError: + raise errors.HeaderParseError( + "expected mailbox but found '{}'".format(value)) + if any(isinstance(x, errors.InvalidHeaderDefect) + for x in token.all_defects): + mailbox.token_type = 'invalid-mailbox' + mailbox.append(token) + return mailbox, value + +def get_invalid_mailbox(value, endchars): + """ Read everything up to one of the chars in endchars. + + This is outside the formal grammar. The InvalidMailbox TokenList that is + returned acts like a Mailbox, but the data attributes are None. + + """ + invalid_mailbox = InvalidMailbox() + while value and value[0] not in endchars: + if value[0] in PHRASE_ENDS: + invalid_mailbox.append(ValueTerminal(value[0], + 'misplaced-special')) + value = value[1:] + else: + token, value = get_phrase(value) + invalid_mailbox.append(token) + return invalid_mailbox, value + +def get_mailbox_list(value): + """ mailbox-list = (mailbox *("," mailbox)) / obs-mbox-list + obs-mbox-list = *([CFWS] ",") mailbox *("," [mailbox / CFWS]) + + For this routine we go outside the formal grammar in order to improve error + handling. We recognize the end of the mailbox list only at the end of the + value or at a ';' (the group terminator). This is so that we can turn + invalid mailboxes into InvalidMailbox tokens and continue parsing any + remaining valid mailboxes. We also allow all mailbox entries to be null, + and this condition is handled appropriately at a higher level. + + """ + mailbox_list = MailboxList() + while value and value[0] != ';': + try: + token, value = get_mailbox(value) + mailbox_list.append(token) + except errors.HeaderParseError: + leader = None + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value or value[0] in ',;': + mailbox_list.append(leader) + mailbox_list.defects.append(errors.ObsoleteHeaderDefect( + "empty element in mailbox-list")) + else: + token, value = get_invalid_mailbox(value, ',;') + if leader is not None: + token[:0] = [leader] + mailbox_list.append(token) + mailbox_list.defects.append(errors.InvalidHeaderDefect( + "invalid mailbox in mailbox-list")) + elif value[0] == ',': + mailbox_list.defects.append(errors.ObsoleteHeaderDefect( + "empty element in mailbox-list")) + else: + token, value = get_invalid_mailbox(value, ',;') + if leader is not None: + token[:0] = [leader] + mailbox_list.append(token) + mailbox_list.defects.append(errors.InvalidHeaderDefect( + "invalid mailbox in mailbox-list")) + if value and value[0] not in ',;': + # Crap after mailbox; treat it as an invalid mailbox. + # The mailbox info will still be available. + mailbox = mailbox_list[-1] + mailbox.token_type = 'invalid-mailbox' + token, value = get_invalid_mailbox(value, ',;') + mailbox.extend(token) + mailbox_list.defects.append(errors.InvalidHeaderDefect( + "invalid mailbox in mailbox-list")) + if value and value[0] == ',': + mailbox_list.append(ListSeparator) + value = value[1:] + return mailbox_list, value + + +def get_group_list(value): + """ group-list = mailbox-list / CFWS / obs-group-list + obs-group-list = 1*([CFWS] ",") [CFWS] + + """ + group_list = GroupList() + if not value: + group_list.defects.append(errors.InvalidHeaderDefect( + "end of header before group-list")) + return group_list, value + leader = None + if value and value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value: + # This should never happen in email parsing, since CFWS-only is a + # legal alternative to group-list in a group, which is the only + # place group-list appears. + group_list.defects.append(errors.InvalidHeaderDefect( + "end of header in group-list")) + group_list.append(leader) + return group_list, value + if value[0] == ';': + group_list.append(leader) + return group_list, value + token, value = get_mailbox_list(value) + if len(token.all_mailboxes)==0: + if leader is not None: + group_list.append(leader) + group_list.extend(token) + group_list.defects.append(errors.ObsoleteHeaderDefect( + "group-list with empty entries")) + return group_list, value + if leader is not None: + token[:0] = [leader] + group_list.append(token) + return group_list, value + +def get_group(value): + """ group = display-name ":" [group-list] ";" [CFWS] + + """ + group = Group() + token, value = get_display_name(value) + if not value or value[0] != ':': + raise errors.HeaderParseError("expected ':' at end of group " + "display name but found '{}'".format(value)) + group.append(token) + group.append(ValueTerminal(':', 'group-display-name-terminator')) + value = value[1:] + if value and value[0] == ';': + group.append(ValueTerminal(';', 'group-terminator')) + return group, value[1:] + token, value = get_group_list(value) + group.append(token) + if not value: + group.defects.append(errors.InvalidHeaderDefect( + "end of header in group")) + if value[0] != ';': + raise errors.HeaderParseError( + "expected ';' at end of group but found {}".format(value)) + group.append(ValueTerminal(';', 'group-terminator')) + value = value[1:] + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + group.append(token) + return group, value + +def get_address(value): + """ address = mailbox / group + + Note that counter-intuitively, an address can be either a single address or + a list of addresses (a group). This is why the returned Address object has + a 'mailboxes' attribute which treats a single address as a list of length + one. When you need to differentiate between to two cases, extract the single + element, which is either a mailbox or a group token. + + """ + # The formal grammar isn't very helpful when parsing an address. mailbox + # and group, especially when allowing for obsolete forms, start off very + # similarly. It is only when you reach one of @, <, or : that you know + # what you've got. So, we try each one in turn, starting with the more + # likely of the two. We could perhaps make this more efficient by looking + # for a phrase and then branching based on the next character, but that + # would be a premature optimization. + address = Address() + try: + token, value = get_group(value) + except errors.HeaderParseError: + try: + token, value = get_mailbox(value) + except errors.HeaderParseError: + raise errors.HeaderParseError( + "expected address but found '{}'".format(value)) + address.append(token) + return address, value + +def get_address_list(value): + """ address_list = (address *("," address)) / obs-addr-list + obs-addr-list = *([CFWS] ",") address *("," [address / CFWS]) + + We depart from the formal grammar here by continuing to parse until the end + of the input, assuming the input to be entirely composed of an + address-list. This is always true in email parsing, and allows us + to skip invalid addresses to parse additional valid ones. + + """ + address_list = AddressList() + while value: + try: + token, value = get_address(value) + address_list.append(token) + except errors.HeaderParseError as err: + leader = None + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value or value[0] == ',': + address_list.append(leader) + address_list.defects.append(errors.ObsoleteHeaderDefect( + "address-list entry with no content")) + else: + token, value = get_invalid_mailbox(value, ',') + if leader is not None: + token[:0] = [leader] + address_list.append(Address([token])) + address_list.defects.append(errors.InvalidHeaderDefect( + "invalid address in address-list")) + elif value[0] == ',': + address_list.defects.append(errors.ObsoleteHeaderDefect( + "empty element in address-list")) + else: + token, value = get_invalid_mailbox(value, ',') + if leader is not None: + token[:0] = [leader] + address_list.append(Address([token])) + address_list.defects.append(errors.InvalidHeaderDefect( + "invalid address in address-list")) + if value and value[0] != ',': + # Crap after address; treat it as an invalid mailbox. + # The mailbox info will still be available. + mailbox = address_list[-1][0] + mailbox.token_type = 'invalid-mailbox' + token, value = get_invalid_mailbox(value, ',') + mailbox.extend(token) + address_list.defects.append(errors.InvalidHeaderDefect( + "invalid address in address-list")) + if value: # Must be a , at this point. + address_list.append(ValueTerminal(',', 'list-separator')) + value = value[1:] + return address_list, value + +# +# XXX: As I begin to add additional header parsers, I'm realizing we probably +# have two level of parser routines: the get_XXX methods that get a token in +# the grammar, and parse_XXX methods that parse an entire field value. So +# get_address_list above should really be a parse_ method, as probably should +# be get_unstructured. +# + +def parse_mime_version(value): + """ mime-version = [CFWS] 1*digit [CFWS] "." [CFWS] 1*digit [CFWS] + + """ + # The [CFWS] is implicit in the RFC 2045 BNF. + # XXX: This routine is a bit verbose, should factor out a get_int method. + mime_version = MIMEVersion() + if not value: + mime_version.defects.append(errors.HeaderMissingRequiredValue( + "Missing MIME version number (eg: 1.0)")) + return mime_version + if value[0] in CFWS_LEADER: + token, value = get_cfws(value) + mime_version.append(token) + if not value: + mime_version.defects.append(errors.HeaderMissingRequiredValue( + "Expected MIME version number but found only CFWS")) + digits = '' + while value and value[0] != '.' and value[0] not in CFWS_LEADER: + digits += value[0] + value = value[1:] + if not digits.isdigit(): + mime_version.defects.append(errors.InvalidHeaderDefect( + "Expected MIME major version number but found {!r}".format(digits))) + mime_version.append(ValueTerminal(digits, 'xtext')) + else: + mime_version.major = int(digits) + mime_version.append(ValueTerminal(digits, 'digits')) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + mime_version.append(token) + if not value or value[0] != '.': + if mime_version.major is not None: + mime_version.defects.append(errors.InvalidHeaderDefect( + "Incomplete MIME version; found only major number")) + if value: + mime_version.append(ValueTerminal(value, 'xtext')) + return mime_version + mime_version.append(ValueTerminal('.', 'version-separator')) + value = value[1:] + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + mime_version.append(token) + if not value: + if mime_version.major is not None: + mime_version.defects.append(errors.InvalidHeaderDefect( + "Incomplete MIME version; found only major number")) + return mime_version + digits = '' + while value and value[0] not in CFWS_LEADER: + digits += value[0] + value = value[1:] + if not digits.isdigit(): + mime_version.defects.append(errors.InvalidHeaderDefect( + "Expected MIME minor version number but found {!r}".format(digits))) + mime_version.append(ValueTerminal(digits, 'xtext')) + else: + mime_version.minor = int(digits) + mime_version.append(ValueTerminal(digits, 'digits')) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + mime_version.append(token) + if value: + mime_version.defects.append(errors.InvalidHeaderDefect( + "Excess non-CFWS text after MIME version")) + mime_version.append(ValueTerminal(value, 'xtext')) + return mime_version + +def get_invalid_parameter(value): + """ Read everything up to the next ';'. + + This is outside the formal grammar. The InvalidParameter TokenList that is + returned acts like a Parameter, but the data attributes are None. + + """ + invalid_parameter = InvalidParameter() + while value and value[0] != ';': + if value[0] in PHRASE_ENDS: + invalid_parameter.append(ValueTerminal(value[0], + 'misplaced-special')) + value = value[1:] + else: + token, value = get_phrase(value) + invalid_parameter.append(token) + return invalid_parameter, value + +def get_ttext(value): + """ttext = <matches _ttext_matcher> + + We allow any non-TOKEN_ENDS in ttext, but add defects to the token's + defects list if we find non-ttext characters. We also register defects for + *any* non-printables even though the RFC doesn't exclude all of them, + because we follow the spirit of RFC 5322. + + """ + m = _non_token_end_matcher(value) + if not m: + raise errors.HeaderParseError( + "expected ttext but found '{}'".format(value)) + ttext = m.group() + value = value[len(ttext):] + ttext = ValueTerminal(ttext, 'ttext') + _validate_xtext(ttext) + return ttext, value + +def get_token(value): + """token = [CFWS] 1*ttext [CFWS] + + The RFC equivalent of ttext is any US-ASCII chars except space, ctls, or + tspecials. We also exclude tabs even though the RFC doesn't. + + The RFC implies the CFWS but is not explicit about it in the BNF. + + """ + mtoken = Token() + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + mtoken.append(token) + if value and value[0] in TOKEN_ENDS: + raise errors.HeaderParseError( + "expected token but found '{}'".format(value)) + token, value = get_ttext(value) + mtoken.append(token) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + mtoken.append(token) + return mtoken, value + +def get_attrtext(value): + """attrtext = 1*(any non-ATTRIBUTE_ENDS character) + + We allow any non-ATTRIBUTE_ENDS in attrtext, but add defects to the + token's defects list if we find non-attrtext characters. We also register + defects for *any* non-printables even though the RFC doesn't exclude all of + them, because we follow the spirit of RFC 5322. + + """ + m = _non_attribute_end_matcher(value) + if not m: + raise errors.HeaderParseError( + "expected attrtext but found {!r}".format(value)) + attrtext = m.group() + value = value[len(attrtext):] + attrtext = ValueTerminal(attrtext, 'attrtext') + _validate_xtext(attrtext) + return attrtext, value + +def get_attribute(value): + """ [CFWS] 1*attrtext [CFWS] + + This version of the BNF makes the CFWS explicit, and as usual we use a + value terminal for the actual run of characters. The RFC equivalent of + attrtext is the token characters, with the subtraction of '*', "'", and '%'. + We include tab in the excluded set just as we do for token. + + """ + attribute = Attribute() + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + attribute.append(token) + if value and value[0] in ATTRIBUTE_ENDS: + raise errors.HeaderParseError( + "expected token but found '{}'".format(value)) + token, value = get_attrtext(value) + attribute.append(token) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + attribute.append(token) + return attribute, value + +def get_extended_attrtext(value): + """attrtext = 1*(any non-ATTRIBUTE_ENDS character plus '%') + + This is a special parsing routine so that we get a value that + includes % escapes as a single string (which we decode as a single + string later). + + """ + m = _non_extended_attribute_end_matcher(value) + if not m: + raise errors.HeaderParseError( + "expected extended attrtext but found {!r}".format(value)) + attrtext = m.group() + value = value[len(attrtext):] + attrtext = ValueTerminal(attrtext, 'extended-attrtext') + _validate_xtext(attrtext) + return attrtext, value + +def get_extended_attribute(value): + """ [CFWS] 1*extended_attrtext [CFWS] + + This is like the non-extended version except we allow % characters, so that + we can pick up an encoded value as a single string. + + """ + # XXX: should we have an ExtendedAttribute TokenList? + attribute = Attribute() + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + attribute.append(token) + if value and value[0] in EXTENDED_ATTRIBUTE_ENDS: + raise errors.HeaderParseError( + "expected token but found '{}'".format(value)) + token, value = get_extended_attrtext(value) + attribute.append(token) + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + attribute.append(token) + return attribute, value + +def get_section(value): + """ '*' digits + + The formal BNF is more complicated because leading 0s are not allowed. We + check for that and add a defect. We also assume no CFWS is allowed between + the '*' and the digits, though the RFC is not crystal clear on that. + The caller should already have dealt with leading CFWS. + + """ + section = Section() + if not value or value[0] != '*': + raise errors.HeaderParseError("Expected section but found {}".format( + value)) + section.append(ValueTerminal('*', 'section-marker')) + value = value[1:] + if not value or not value[0].isdigit(): + raise errors.HeaderParseError("Expected section number but " + "found {}".format(value)) + digits = '' + while value and value[0].isdigit(): + digits += value[0] + value = value[1:] + if digits[0] == '0' and digits != '0': + section.defects.append(errors.InvalidHeaderError("section number" + "has an invalid leading 0")) + section.number = int(digits) + section.append(ValueTerminal(digits, 'digits')) + return section, value + + +def get_value(value): + """ quoted-string / attribute + + """ + v = Value() + if not value: + raise errors.HeaderParseError("Expected value but found end of string") + leader = None + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value: + raise errors.HeaderParseError("Expected value but found " + "only {}".format(leader)) + if value[0] == '"': + token, value = get_quoted_string(value) + else: + token, value = get_extended_attribute(value) + if leader is not None: + token[:0] = [leader] + v.append(token) + return v, value + +def get_parameter(value): + """ attribute [section] ["*"] [CFWS] "=" value + + The CFWS is implied by the RFC but not made explicit in the BNF. This + simplified form of the BNF from the RFC is made to conform with the RFC BNF + through some extra checks. We do it this way because it makes both error + recovery and working with the resulting parse tree easier. + """ + # It is possible CFWS would also be implicitly allowed between the section + # and the 'extended-attribute' marker (the '*') , but we've never seen that + # in the wild and we will therefore ignore the possibility. + param = Parameter() + token, value = get_attribute(value) + param.append(token) + if not value or value[0] == ';': + param.defects.append(errors.InvalidHeaderDefect("Parameter contains " + "name ({}) but no value".format(token))) + return param, value + if value[0] == '*': + try: + token, value = get_section(value) + param.sectioned = True + param.append(token) + except errors.HeaderParseError: + pass + if not value: + raise errors.HeaderParseError("Incomplete parameter") + if value[0] == '*': + param.append(ValueTerminal('*', 'extended-parameter-marker')) + value = value[1:] + param.extended = True + if value[0] != '=': + raise errors.HeaderParseError("Parameter not followed by '='") + param.append(ValueTerminal('=', 'parameter-separator')) + value = value[1:] + leader = None + if value and value[0] in CFWS_LEADER: + token, value = get_cfws(value) + param.append(token) + remainder = None + appendto = param + if param.extended and value and value[0] == '"': + # Now for some serious hackery to handle the common invalid case of + # double quotes around an extended value. We also accept (with defect) + # a value marked as encoded that isn't really. + qstring, remainder = get_quoted_string(value) + inner_value = qstring.stripped_value + semi_valid = False + if param.section_number == 0: + if inner_value and inner_value[0] == "'": + semi_valid = True + else: + token, rest = get_attrtext(inner_value) + if rest and rest[0] == "'": + semi_valid = True + else: + try: + token, rest = get_extended_attrtext(inner_value) + except: + pass + else: + if not rest: + semi_valid = True + if semi_valid: + param.defects.append(errors.InvalidHeaderDefect( + "Quoted string value for extended parameter is invalid")) + param.append(qstring) + for t in qstring: + if t.token_type == 'bare-quoted-string': + t[:] = [] + appendto = t + break + value = inner_value + else: + remainder = None + param.defects.append(errors.InvalidHeaderDefect( + "Parameter marked as extended but appears to have a " + "quoted string value that is non-encoded")) + if value and value[0] == "'": + token = None + else: + token, value = get_value(value) + if not param.extended or param.section_number > 0: + if not value or value[0] != "'": + appendto.append(token) + if remainder is not None: + assert not value, value + value = remainder + return param, value + param.defects.append(errors.InvalidHeaderDefect( + "Apparent initial-extended-value but attribute " + "was not marked as extended or was not initial section")) + if not value: + # Assume the charset/lang is missing and the token is the value. + param.defects.append(errors.InvalidHeaderDefect( + "Missing required charset/lang delimiters")) + appendto.append(token) + if remainder is None: + return param, value + else: + if token is not None: + for t in token: + if t.token_type == 'extended-attrtext': + break + t.token_type == 'attrtext' + appendto.append(t) + param.charset = t.value + if value[0] != "'": + raise errors.HeaderParseError("Expected RFC2231 char/lang encoding " + "delimiter, but found {!r}".format(value)) + appendto.append(ValueTerminal("'", 'RFC2231 delimiter')) + value = value[1:] + if value and value[0] != "'": + token, value = get_attrtext(value) + appendto.append(token) + param.lang = token.value + if not value or value[0] != "'": + raise errors.HeaderParseError("Expected RFC2231 char/lang encoding " + "delimiter, but found {}".format(value)) + appendto.append(ValueTerminal("'", 'RFC2231 delimiter')) + value = value[1:] + if remainder is not None: + # Treat the rest of value as bare quoted string content. + v = Value() + while value: + if value[0] in WSP: + token, value = get_fws(value) + else: + token, value = get_qcontent(value) + v.append(token) + token = v + else: + token, value = get_value(value) + appendto.append(token) + if remainder is not None: + assert not value, value + value = remainder + return param, value + +def parse_mime_parameters(value): + """ parameter *( ";" parameter ) + + That BNF is meant to indicate this routine should only be called after + finding and handling the leading ';'. There is no corresponding rule in + the formal RFC grammar, but it is more convenient for us for the set of + parameters to be treated as its own TokenList. + + This is 'parse' routine because it consumes the reminaing value, but it + would never be called to parse a full header. Instead it is called to + parse everything after the non-parameter value of a specific MIME header. + + """ + mime_parameters = MimeParameters() + while value: + try: + token, value = get_parameter(value) + mime_parameters.append(token) + except errors.HeaderParseError as err: + leader = None + if value[0] in CFWS_LEADER: + leader, value = get_cfws(value) + if not value: + mime_parameters.append(leader) + return mime_parameters + if value[0] == ';': + if leader is not None: + mime_parameters.append(leader) + mime_parameters.defects.append(errors.InvalidHeaderDefect( + "parameter entry with no content")) + else: + token, value = get_invalid_parameter(value) + if leader: + token[:0] = [leader] + mime_parameters.append(token) + mime_parameters.defects.append(errors.InvalidHeaderDefect( + "invalid parameter {!r}".format(token))) + if value and value[0] != ';': + # Junk after the otherwise valid parameter. Mark it as + # invalid, but it will have a value. + param = mime_parameters[-1] + param.token_type = 'invalid-parameter' + token, value = get_invalid_parameter(value) + param.extend(token) + mime_parameters.defects.append(errors.InvalidHeaderDefect( + "parameter with invalid trailing text {!r}".format(token))) + if value: + # Must be a ';' at this point. + mime_parameters.append(ValueTerminal(';', 'parameter-separator')) + value = value[1:] + return mime_parameters + +def _find_mime_parameters(tokenlist, value): + """Do our best to find the parameters in an invalid MIME header + + """ + while value and value[0] != ';': + if value[0] in PHRASE_ENDS: + tokenlist.append(ValueTerminal(value[0], 'misplaced-special')) + value = value[1:] + else: + token, value = get_phrase(value) + tokenlist.append(token) + if not value: + return + tokenlist.append(ValueTerminal(';', 'parameter-separator')) + tokenlist.append(parse_mime_parameters(value[1:])) + +def parse_content_type_header(value): + """ maintype "/" subtype *( ";" parameter ) + + The maintype and substype are tokens. Theoretically they could + be checked against the official IANA list + x-token, but we + don't do that. + """ + ctype = ContentType() + recover = False + if not value: + ctype.defects.append(errors.HeaderMissingRequiredValue( + "Missing content type specification")) + return ctype + try: + token, value = get_token(value) + except errors.HeaderParseError: + ctype.defects.append(errors.InvalidHeaderDefect( + "Expected content maintype but found {!r}".format(value))) + _find_mime_parameters(ctype, value) + return ctype + ctype.append(token) + # XXX: If we really want to follow the formal grammar we should make + # mantype and subtype specialized TokenLists here. Probably not worth it. + if not value or value[0] != '/': + ctype.defects.append(errors.InvalidHeaderDefect( + "Invalid content type")) + if value: + _find_mime_parameters(ctype, value) + return ctype + ctype.maintype = token.value.strip().lower() + ctype.append(ValueTerminal('/', 'content-type-separator')) + value = value[1:] + try: + token, value = get_token(value) + except errors.HeaderParseError: + ctype.defects.append(errors.InvalidHeaderDefect( + "Expected content subtype but found {!r}".format(value))) + _find_mime_parameters(ctype, value) + return ctype + ctype.append(token) + ctype.subtype = token.value.strip().lower() + if not value: + return ctype + if value[0] != ';': + ctype.defects.append(errors.InvalidHeaderDefect( + "Only parameters are valid after content type, but " + "found {!r}".format(value))) + # The RFC requires that a syntactically invalid content-type be treated + # as text/plain. Perhaps we should postel this, but we should probably + # only do that if we were checking the subtype value against IANA. + del ctype.maintype, ctype.subtype + _find_mime_parameters(ctype, value) + return ctype + ctype.append(ValueTerminal(';', 'parameter-separator')) + ctype.append(parse_mime_parameters(value[1:])) + return ctype + +def parse_content_disposition_header(value): + """ disposition-type *( ";" parameter ) + + """ + disp_header = ContentDisposition() + if not value: + disp_header.defects.append(errors.HeaderMissingRequiredValue( + "Missing content disposition")) + return disp_header + try: + token, value = get_token(value) + except errors.HeaderParseError: + ctype.defects.append(errors.InvalidHeaderDefect( + "Expected content disposition but found {!r}".format(value))) + _find_mime_parameters(disp_header, value) + return disp_header + disp_header.append(token) + disp_header.content_disposition = token.value.strip().lower() + if not value: + return disp_header + if value[0] != ';': + disp_header.defects.append(errors.InvalidHeaderDefect( + "Only parameters are valid after content disposition, but " + "found {!r}".format(value))) + _find_mime_parameters(disp_header, value) + return disp_header + disp_header.append(ValueTerminal(';', 'parameter-separator')) + disp_header.append(parse_mime_parameters(value[1:])) + return disp_header + +def parse_content_transfer_encoding_header(value): + """ mechanism + + """ + # We should probably validate the values, since the list is fixed. + cte_header = ContentTransferEncoding() + if not value: + cte_header.defects.append(errors.HeaderMissingRequiredValue( + "Missing content transfer encoding")) + return cte_header + try: + token, value = get_token(value) + except errors.HeaderParseError: + ctype.defects.append(errors.InvalidHeaderDefect( + "Expected content trnasfer encoding but found {!r}".format(value))) + else: + cte_header.append(token) + cte_header.cte = token.value.strip().lower() + if not value: + return cte_header + while value: + cte_header.defects.append(errors.InvalidHeaderDefect( + "Extra text after content transfer encoding")) + if value[0] in PHRASE_ENDS: + cte_header.append(ValueTerminal(value[0], 'misplaced-special')) + value = value[1:] + else: + token, value = get_phrase(value) + cte_header.append(token) + return cte_header diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/_parseaddr.py b/.venv/lib/python3.12/site-packages/future/backports/email/_parseaddr.py new file mode 100644 index 00000000..5b50cc6b --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/_parseaddr.py @@ -0,0 +1,546 @@ +# 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. +""" + +from __future__ import unicode_literals +from __future__ import print_function +from __future__ import division +from __future__ import absolute_import +from future.builtins import int + +__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(object): + """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() + return EMPTYSTRING.join(aslist) + self.getdomain() + + 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] 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] diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/_policybase.py b/.venv/lib/python3.12/site-packages/future/backports/email/_policybase.py new file mode 100644 index 00000000..c66aea90 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/_policybase.py @@ -0,0 +1,365 @@ +"""Policy framework for the email package. + +Allows fine grained feature control of how the package parses and emits data. +""" +from __future__ import unicode_literals +from __future__ import print_function +from __future__ import division +from __future__ import absolute_import +from future.builtins import super +from future.builtins import str +from future.utils import with_metaclass + +import abc +from future.backports.email import header +from future.backports.email import charset as _charset +from future.backports.email.utils import _has_surrogates + +__all__ = [ + 'Policy', + 'Compat32', + 'compat32', + ] + + +class _PolicyBase(object): + + """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(with_metaclass(abc.ABCMeta, _PolicyBase)): + + 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. + + """ + + raise_on_defect = False + linesep = '\n' + cte_type = '8bit' + max_line_length = 78 + + 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. + """ + + 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: + parts.append(h.encode(linesep=self.linesep, + maxlinelen=self.max_line_length)) + parts.append(self.linesep) + return ''.join(parts) + + +compat32 = Compat32() diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/base64mime.py b/.venv/lib/python3.12/site-packages/future/backports/email/base64mime.py new file mode 100644 index 00000000..296392a6 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/base64mime.py @@ -0,0 +1,121 @@ +# 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. +""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import range +from future.builtins import bytes +from future.builtins import str + +__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-8895-1?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 diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/charset.py b/.venv/lib/python3.12/site-packages/future/backports/email/charset.py new file mode 100644 index 00000000..2385ce68 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/charset.py @@ -0,0 +1,409 @@ +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import str +from future.builtins import next + +# 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 + +from future.backports import email +from future.backports.email import errors +from future.backports.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): + string = str(string) + if codec == UNKNOWN8BIT: + return string.encode('ascii', 'surrogateescape') + else: + return string.encode(codec) + + +class Charset(object): + """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 __ne__(self, other): + return not self.__eq__(other) + + 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 diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/encoders.py b/.venv/lib/python3.12/site-packages/future/backports/email/encoders.py new file mode 100644 index 00000000..15d2eb46 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/encoders.py @@ -0,0 +1,90 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Encodings and related functions.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import str + +__all__ = [ + 'encode_7or8bit', + 'encode_base64', + 'encode_noop', + 'encode_quopri', + ] + + +try: + from base64 import encodebytes as _bencode +except ImportError: + # Py2 compatibility. TODO: test this! + from base64 import encodestring 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(' ', '=20') + + +def encode_base64(msg): + """Encode the message's payload in Base64. + + Also, add an appropriate Content-Transfer-Encoding header. + """ + orig = msg.get_payload() + 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() + 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() + 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 encoding/decode to ASCII + # succeeds, we know the data must be 7bit, otherwise treat it as 8bit. + try: + if isinstance(orig, str): + orig.encode('ascii') + else: + orig.decode('ascii') + except UnicodeError: + charset = msg.get_charset() + output_cset = charset and charset.output_charset + # iso-2022-* is non-ASCII but encodes to a 7-bit representation + if output_cset and output_cset.lower().startswith('iso-2022-'): + msg['Content-Transfer-Encoding'] = '7bit' + else: + msg['Content-Transfer-Encoding'] = '8bit' + else: + msg['Content-Transfer-Encoding'] = '7bit' + if not isinstance(orig, str): + msg.set_payload(orig.decode('ascii', 'surrogateescape')) + + +def encode_noop(msg): + """Do nothing.""" + # Well, not quite *nothing*: in Python3 we have to turn bytes into a string + # in our internal surrogateescaped form in order to keep the model + # consistent. + orig = msg.get_payload() + if not isinstance(orig, str): + msg.set_payload(orig.decode('ascii', 'surrogateescape')) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/errors.py b/.venv/lib/python3.12/site-packages/future/backports/email/errors.py new file mode 100644 index 00000000..0fe599cf --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/errors.py @@ -0,0 +1,111 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""email package exception classes.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import super + + +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""" + +# 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. diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/feedparser.py b/.venv/lib/python3.12/site-packages/future/backports/email/feedparser.py new file mode 100644 index 00000000..935c26e3 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/feedparser.py @@ -0,0 +1,525 @@ +# 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. +""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import object, range, super +from future.utils import implements_iterator, PY3 + +__all__ = ['FeedParser', 'BytesFeedParser'] + +import re + +from future.backports.email import errors +from future.backports.email import message +from future.backports.email._policybase import compat32 + +NLCRE = re.compile('\r\n|\r|\n') +NLCRE_bol = re.compile('(\r\n|\r|\n)') +NLCRE_eol = re.compile('(\r\n|\r|\n)\Z') +NLCRE_crack = re.compile('(\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]{1,}:|[\t ])') +EMPTYSTRING = '' +NL = '\n' + +NeedMoreData = object() + + +# @implements_iterator +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): + # The last partial line pushed into this object. + self._partial = '' + # The list of full, pushed lines, in reverse order + self._lines = [] + # 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._lines.append(self._partial) + self._partial = '' + 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.pop() + # 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 self._eofstack[::-1]: + if ateof(line): + # We're at the false EOF. But push the last line back first. + self._lines.append(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.append(line) + + def push(self, data): + """Push some new data into this object.""" + # Handle any previous leftovers + data, self._partial = self._partial + data, '' + # Crack into lines, but preserve the newlines on the end of each + parts = NLCRE_crack.split(data) + # The *ahem* interesting behaviour of re.split when supplied grouping + # parentheses is that the last element of the resulting list is the + # data after the final RE. In the case of a NL/CR terminated string, + # this is the empty string. + self._partial = parts.pop() + #GAN 29Mar09 bugs 1555570, 1721862 Confusion at 8K boundary ending with \r: + # is there a \n to follow later? + if not self._partial and parts and parts[-1].endswith('\r'): + self._partial = parts.pop(-2)+parts.pop() + # parts is a list of strings, alternating between the line contents + # and the eol character(s). Gather up a list of lines after + # re-attaching the newlines. + lines = [] + for i in range(len(parts) // 2): + lines.append(parts[i*2] + parts[i*2+1]) + self.pushlines(lines) + + def pushlines(self, lines): + # Reverse and insert at the front of the lines. + self._lines[:0] = lines[::-1] + + def __iter__(self): + return self + + def __next__(self): + line = self.readline() + if line == '': + raise StopIteration + return line + + +class FeedParser(object): + """A feed-style parser of email.""" + + def __init__(self, _factory=message.Message, **_3to2kwargs): + if 'policy' in _3to2kwargs: policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] + else: 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._factory = _factory + self.policy = policy + try: + _factory(policy=self.policy) + self._factory_kwds = lambda: {'policy': self.policy} + except TypeError: + # Assume this is an old-style factory + self._factory_kwds = lambda: {} + self._input = BufferedSubFile() + self._msgstack = [] + if PY3: + self._parse = self._parsegen().__next__ + else: + 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): + msg = self._factory(**self._factory_kwds()) + 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(':') + 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')) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/generator.py b/.venv/lib/python3.12/site-packages/future/backports/email/generator.py new file mode 100644 index 00000000..53493d0a --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/generator.py @@ -0,0 +1,498 @@ +# 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.""" +from __future__ import print_function +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import super +from future.builtins import str + +__all__ = ['Generator', 'DecodedGenerator', 'BytesGenerator'] + +import re +import sys +import time +import random +import warnings + +from io import StringIO, BytesIO +from future.backports.email._policybase import compat32 +from future.backports.email.header import Header +from future.backports.email.utils import _has_surrogates +import future.backports.email.charset as _charset + +UNDERSCORE = '_' +NL = '\n' # XXX: no longer used by the code below. + +fcre = re.compile(r'^From ', re.MULTILINE) + + +class Generator(object): + """Generates output from a Message object tree. + + This basic generator writes the message to the given file object as plain + text. + """ + # + # Public interface + # + + def __init__(self, outfp, mangle_from_=True, maxheaderlen=None, **_3to2kwargs): + if 'policy' in _3to2kwargs: policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] + else: 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), 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. The default policy maintains + backward compatibility. + + """ + 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. + + """ + # 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_EMTPY = self._encode('') + # 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. + + # Similarly, we have _XXX and _encoded_XXX attributes that are used on + # source and buffer data, respectively. + _encoded_EMPTY = '' + + def _new_buffer(self): + # BytesGenerator overrides this to return BytesIO. + return StringIO() + + def _encode(self, s): + # BytesGenerator overrides this to encode strings to bytes. + return s + + def _write_lines(self, lines): + # We have to transform the line endings. + if not lines: + return + lines = lines.splitlines(True) + for line in lines[:-1]: + self.write(line.rstrip('\r\n')) + self.write(self._NL) + laststripped = lines[-1].rstrip('\r\n') + self.write(laststripped) + if len(lines[-1]) != len(laststripped): + 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._fp = sfp = self._new_buffer() + self._dispatch(msg) + finally: + self._fp = oldfp + # Write the headers. First we see if the message object wants to + # handle that itself. If not, we'll do it generically. + meth = getattr(msg, '_write_headers', None) + if meth is None: + self._write_headers(msg) + else: + meth(self) + self._fp.write(sfp.getvalue()) + + def _dispatch(self, msg): + # Get the Content-Type: for the message, then try to dispatch to + # self._handle_<maintype>_<subtype>(). If there's no handler for the + # full MIME type, then dispatch to self._handle_<maintype>(). If + # that's missing too, then dispatch to self._writeBody(). + main = msg.get_content_maintype() + sub = msg.get_content_subtype() + specific = UNDERSCORE.join((main, sub)).replace('-', '_') + meth = getattr(self, '_handle_' + specific, None) + if meth is None: + generic = main.replace('-', '_') + meth = getattr(self, '_handle_' + generic, None) + if meth is None: + meth = self._writeBody + meth(msg) + + # + # Default handlers + # + + def _write_headers(self, msg): + for h, v in msg.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: + del msg['content-transfer-encoding'] + msg.set_payload(payload, charset) + payload = msg.get_payload() + if self._mangle_from_: + payload = fcre.sub('>From ', payload) + self._write_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 + '--') + if msg.epilogue is not None: + self.write(self._NL) + 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_boudary = Generator._make_boundary + # at the end of the module. It *is* internal, so we could drop that... + @classmethod + def _make_boundary(cls, text=None): + # Craft a random boundary. If text is given, ensure that the chosen + # boundary doesn't appear in the text. + token = random.randrange(sys.maxsize) + boundary = ('=' * 15) + (_fmt % token) + '==' + if text is None: + return boundary + b = boundary + counter = 0 + while True: + cre = cls._compile_re('^--' + re.escape(b) + '(--)?$', re.MULTILINE) + if not cre.search(text): + break + b = boundary + '.' + str(counter) + counter += 1 + return b + + @classmethod + def _compile_re(cls, s, flags): + return re.compile(s, flags) + +class BytesGenerator(Generator): + """Generates a bytes version of a Message object tree. + + Functionally identical to the base Generator except that the output is + bytes and not string. When surrogates were used in the input to encode + bytes, these are decoded back to bytes for output. 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. + """ + + # Bytes versions of this constant for use in manipulating data from + # the BytesIO buffer. + _encoded_EMPTY = b'' + + def write(self, s): + self._fp.write(str(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_=True, maxheaderlen=78, fmt=None): + """Like Generator.__init__() except that an additional optional + argument is allowed. + + Walks through all subparts of a message. If the subpart is of main + type `text', then it prints the decoded payload of the subpart. + + Otherwise, fmt is a format string that is used instead of the message + payload. fmt is expanded with the following keywords (in + %(keyword)s format): + + type : Full MIME type of the non-text part + maintype : Main MIME type of the non-text part + subtype : Sub-MIME type of the non-text part + filename : Filename of the non-text part + description: Description associated with the non-text part + encoding : Content transfer encoding of the non-text part + + The default value for fmt is None, meaning + + [Non-text (%(type)s) part of message omitted, filename %(filename)s] + """ + Generator.__init__(self, outfp, mangle_from_, maxheaderlen) + if fmt is None: + self._fmt = _FMT + else: + self._fmt = fmt + + def _dispatch(self, msg): + for part in msg.walk(): + maintype = part.get_content_maintype() + if maintype == 'text': + print(part.get_payload(decode=False), file=self) + elif maintype == 'multipart': + # Just skip this + pass + else: + print(self._fmt % { + 'type' : part.get_content_type(), + 'maintype' : part.get_content_maintype(), + 'subtype' : part.get_content_subtype(), + 'filename' : part.get_filename('[no filename]'), + 'description': part.get('Content-Description', + '[no description]'), + 'encoding' : part.get('Content-Transfer-Encoding', + '[no encoding]'), + }, file=self) + + +# Helper used by Generator._make_boundary +_width = len(repr(sys.maxsize-1)) +_fmt = '%%0%dd' % _width + +# Backward compatibility +_make_boundary = Generator._make_boundary diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/header.py b/.venv/lib/python3.12/site-packages/future/backports/email/header.py new file mode 100644 index 00000000..63bf038c --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/header.py @@ -0,0 +1,581 @@ +# Copyright (C) 2002-2007 Python Software Foundation +# Author: Ben Gertzfield, Barry Warsaw +# Contact: email-sig@python.org + +"""Header encoding and decoding functionality.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import bytes, range, str, super, zip + +__all__ = [ + 'Header', + 'decode_header', + 'make_header', + ] + +import re +import binascii + +from future.backports import email +from future.backports.email import base64mime +from future.backports.email.errors import HeaderParseError +import future.backports.email.charset as _charset + +# Helpers +from future.backports.email.quoprimime import _max_append, header_decode + +Charset = _charset.Charset + +NL = '\n' +SPACE = ' ' +BSPACE = b' ' +SPACE8 = ' ' * 8 +EMPTYSTRING = '' +MAXLINELEN = 78 +FWS = ' \t' + +USASCII = Charset('us-ascii') +UTF8 = Charset('utf-8') + +# Match encoded-word strings in the form =?charset?q?Hello_World?= +ecre = re.compile(r''' + =\? # literal =? + (?P<charset>[^?]*?) # non-greedy up to the next ? is the charset + \? # literal ? + (?P<encoding>[qb]) # either a "q" or a "b", case insensitive + \? # literal ? + (?P<encoded>.*?) # non-greedy up to the next ?= is the encoded string + \?= # literal ?= + ''', re.VERBOSE | re.IGNORECASE | re.MULTILINE) + +# Field name regexp, including trailing colon, but not separating whitespace, +# according to RFC 2822. Character range is from tilde to exclamation mark. +# For use with .match() +fcre = re.compile(r'[\041-\176]+:$') + +# Find a header embedded in a putative header value. Used to check for +# header injection attack. +_embeded_header = re.compile(r'\n[^ \t]+:') + + +def decode_header(header): + """Decode a message header value without converting charset. + + Returns a list of (string, charset) pairs containing each of the decoded + parts of the header. Charset is None for non-encoded parts of the header, + otherwise a lower-case string containing the name of the character set + specified in the encoded string. + + header may be a string that may or may not contain RFC2047 encoded words, + or it may be a Header object. + + An email.errors.HeaderParseError may be raised when certain decoding error + occurs (e.g. a base64 decoding exception). + """ + # If it is a Header object, we can just return the encoded chunks. + if hasattr(header, '_chunks'): + return [(_charset._encode(string, str(charset)), str(charset)) + for string, charset in header._chunks] + # If no encoding, just return the header with no charset. + if not ecre.search(header): + return [(header, None)] + # First step is to parse all the encoded parts into triplets of the form + # (encoded_string, encoding, charset). For unencoded strings, the last + # two parts will be None. + words = [] + for line in header.splitlines(): + parts = ecre.split(line) + first = True + while parts: + unencoded = parts.pop(0) + if first: + unencoded = unencoded.lstrip() + first = False + if unencoded: + words.append((unencoded, None, None)) + if parts: + charset = parts.pop(0).lower() + encoding = parts.pop(0).lower() + encoded = parts.pop(0) + words.append((encoded, encoding, charset)) + # Now loop over words and remove words that consist of whitespace + # between two encoded strings. + import sys + droplist = [] + for n, w in enumerate(words): + if n>1 and w[1] and words[n-2][1] and words[n-1][0].isspace(): + droplist.append(n-1) + for d in reversed(droplist): + del words[d] + + # The next step is to decode each encoded word by applying the reverse + # base64 or quopri transformation. decoded_words is now a list of the + # form (decoded_word, charset). + decoded_words = [] + for encoded_string, encoding, charset in words: + if encoding is None: + # This is an unencoded word. + decoded_words.append((encoded_string, charset)) + elif encoding == 'q': + word = header_decode(encoded_string) + decoded_words.append((word, charset)) + elif encoding == 'b': + paderr = len(encoded_string) % 4 # Postel's law: add missing padding + if paderr: + encoded_string += '==='[:4 - paderr] + try: + word = base64mime.decode(encoded_string) + except binascii.Error: + raise HeaderParseError('Base64 decoding error') + else: + decoded_words.append((word, charset)) + else: + raise AssertionError('Unexpected encoding: ' + encoding) + # Now convert all words to bytes and collapse consecutive runs of + # similarly encoded words. + collapsed = [] + last_word = last_charset = None + for word, charset in decoded_words: + if isinstance(word, str): + word = bytes(word, 'raw-unicode-escape') + if last_word is None: + last_word = word + last_charset = charset + elif charset != last_charset: + collapsed.append((last_word, last_charset)) + last_word = word + last_charset = charset + elif last_charset is None: + last_word += BSPACE + word + else: + last_word += word + collapsed.append((last_word, last_charset)) + return collapsed + + +def make_header(decoded_seq, maxlinelen=None, header_name=None, + continuation_ws=' '): + """Create a Header from a sequence of pairs as returned by decode_header() + + decode_header() takes a header value string and returns a sequence of + pairs of the format (decoded_string, charset) where charset is the string + name of the character set. + + This function takes one of those sequence of pairs and returns a Header + instance. Optional maxlinelen, header_name, and continuation_ws are as in + the Header constructor. + """ + h = Header(maxlinelen=maxlinelen, header_name=header_name, + continuation_ws=continuation_ws) + for s, charset in decoded_seq: + # None means us-ascii but we can simply pass it on to h.append() + if charset is not None and not isinstance(charset, Charset): + charset = Charset(charset) + h.append(s, charset) + return h + + +class Header(object): + def __init__(self, s=None, charset=None, + maxlinelen=None, header_name=None, + continuation_ws=' ', errors='strict'): + """Create a MIME-compliant header that can contain many character sets. + + Optional s is the initial header value. If None, the initial header + value is not set. You can later append to the header with .append() + method calls. s may be a byte string or a Unicode string, but see the + .append() documentation for semantics. + + Optional charset serves two purposes: it has the same meaning as the + charset argument to the .append() method. It also sets the default + character set for all subsequent .append() calls that omit the charset + argument. If charset is not provided in the constructor, the us-ascii + charset is used both as s's initial charset and as the default for + subsequent .append() calls. + + The maximum line length can be specified explicitly via maxlinelen. For + splitting the first line to a shorter value (to account for the field + header which isn't included in s, e.g. `Subject') pass in the name of + the field in header_name. The default maxlinelen is 78 as recommended + by RFC 2822. + + continuation_ws must be RFC 2822 compliant folding whitespace (usually + either a space or a hard tab) which will be prepended to continuation + lines. + + errors is passed through to the .append() call. + """ + if charset is None: + charset = USASCII + elif not isinstance(charset, Charset): + charset = Charset(charset) + self._charset = charset + self._continuation_ws = continuation_ws + self._chunks = [] + if s is not None: + self.append(s, charset, errors) + if maxlinelen is None: + maxlinelen = MAXLINELEN + self._maxlinelen = maxlinelen + if header_name is None: + self._headerlen = 0 + else: + # Take the separating colon and space into account. + self._headerlen = len(header_name) + 2 + + def __str__(self): + """Return the string value of the header.""" + self._normalize() + uchunks = [] + lastcs = None + lastspace = None + for string, charset in self._chunks: + # We must preserve spaces between encoded and non-encoded word + # boundaries, which means for us we need to add a space when we go + # from a charset to None/us-ascii, or from None/us-ascii to a + # charset. Only do this for the second and subsequent chunks. + # Don't add a space if the None/us-ascii string already has + # a space (trailing or leading depending on transition) + nextcs = charset + if nextcs == _charset.UNKNOWN8BIT: + original_bytes = string.encode('ascii', 'surrogateescape') + string = original_bytes.decode('ascii', 'replace') + if uchunks: + hasspace = string and self._nonctext(string[0]) + if lastcs not in (None, 'us-ascii'): + if nextcs in (None, 'us-ascii') and not hasspace: + uchunks.append(SPACE) + nextcs = None + elif nextcs not in (None, 'us-ascii') and not lastspace: + uchunks.append(SPACE) + lastspace = string and self._nonctext(string[-1]) + lastcs = nextcs + uchunks.append(string) + return EMPTYSTRING.join(uchunks) + + # Rich comparison operators for equality only. BAW: does it make sense to + # have or explicitly disable <, <=, >, >= operators? + def __eq__(self, other): + # other may be a Header or a string. Both are fine so coerce + # ourselves to a unicode (of the unencoded header value), swap the + # args and do another comparison. + return other == str(self) + + def __ne__(self, other): + return not self == other + + def append(self, s, charset=None, errors='strict'): + """Append a string to the MIME header. + + Optional charset, if given, should be a Charset instance or the name + of a character set (which will be converted to a Charset instance). A + value of None (the default) means that the charset given in the + constructor is used. + + s may be a byte string or a Unicode string. If it is a byte string + (i.e. isinstance(s, str) is false), then charset is the encoding of + that byte string, and a UnicodeError will be raised if the string + cannot be decoded with that charset. If s is a Unicode string, then + charset is a hint specifying the character set of the characters in + the string. In either case, when producing an RFC 2822 compliant + header using RFC 2047 rules, the string will be encoded using the + output codec of the charset. If the string cannot be encoded to the + output codec, a UnicodeError will be raised. + + Optional `errors' is passed as the errors argument to the decode + call if s is a byte string. + """ + if charset is None: + charset = self._charset + elif not isinstance(charset, Charset): + charset = Charset(charset) + if not isinstance(s, str): + input_charset = charset.input_codec or 'us-ascii' + if input_charset == _charset.UNKNOWN8BIT: + s = s.decode('us-ascii', 'surrogateescape') + else: + s = s.decode(input_charset, errors) + # Ensure that the bytes we're storing can be decoded to the output + # character set, otherwise an early error is raised. + output_charset = charset.output_codec or 'us-ascii' + if output_charset != _charset.UNKNOWN8BIT: + try: + s.encode(output_charset, errors) + except UnicodeEncodeError: + if output_charset!='us-ascii': + raise + charset = UTF8 + self._chunks.append((s, charset)) + + def _nonctext(self, s): + """True if string s is not a ctext character of RFC822. + """ + return s.isspace() or s in ('(', ')', '\\') + + def encode(self, splitchars=';, \t', maxlinelen=None, linesep='\n'): + r"""Encode a message header into an RFC-compliant format. + + There are many issues involved in converting a given string for use in + an email header. Only certain character sets are readable in most + email clients, and as header strings can only contain a subset of + 7-bit ASCII, care must be taken to properly convert and encode (with + Base64 or quoted-printable) header strings. In addition, there is a + 75-character length limit on any given encoded header field, so + line-wrapping must be performed, even with double-byte character sets. + + Optional maxlinelen specifies the maximum length of each generated + line, exclusive of the linesep string. Individual lines may be longer + than maxlinelen if a folding point cannot be found. The first line + will be shorter by the length of the header name plus ": " if a header + name was specified at Header construction time. The default value for + maxlinelen is determined at header construction time. + + Optional splitchars is a string containing characters which should be + given extra weight by the splitting algorithm during normal header + wrapping. This is in very rough support of RFC 2822's `higher level + syntactic breaks': split points preceded by a splitchar are preferred + during line splitting, with the characters preferred in the order in + which they appear in the string. Space and tab may be included in the + string to indicate whether preference should be given to one over the + other as a split point when other split chars do not appear in the line + being split. Splitchars does not affect RFC 2047 encoded lines. + + Optional linesep is a string to be used to separate the lines of + the value. The default value is the most useful for typical + Python applications, but it can be set to \r\n to produce RFC-compliant + line separators when needed. + """ + self._normalize() + if maxlinelen is None: + maxlinelen = self._maxlinelen + # A maxlinelen of 0 means don't wrap. For all practical purposes, + # choosing a huge number here accomplishes that and makes the + # _ValueFormatter algorithm much simpler. + if maxlinelen == 0: + maxlinelen = 1000000 + formatter = _ValueFormatter(self._headerlen, maxlinelen, + self._continuation_ws, splitchars) + lastcs = None + hasspace = lastspace = None + for string, charset in self._chunks: + if hasspace is not None: + hasspace = string and self._nonctext(string[0]) + import sys + if lastcs not in (None, 'us-ascii'): + if not hasspace or charset not in (None, 'us-ascii'): + formatter.add_transition() + elif charset not in (None, 'us-ascii') and not lastspace: + formatter.add_transition() + lastspace = string and self._nonctext(string[-1]) + lastcs = charset + hasspace = False + lines = string.splitlines() + if lines: + formatter.feed('', lines[0], charset) + else: + formatter.feed('', '', charset) + for line in lines[1:]: + formatter.newline() + if charset.header_encoding is not None: + formatter.feed(self._continuation_ws, ' ' + line.lstrip(), + charset) + else: + sline = line.lstrip() + fws = line[:len(line)-len(sline)] + formatter.feed(fws, sline, charset) + if len(lines) > 1: + formatter.newline() + if self._chunks: + formatter.add_transition() + value = formatter._str(linesep) + if _embeded_header.search(value): + raise HeaderParseError("header value appears to contain " + "an embedded header: {!r}".format(value)) + return value + + def _normalize(self): + # Step 1: Normalize the chunks so that all runs of identical charsets + # get collapsed into a single unicode string. + chunks = [] + last_charset = None + last_chunk = [] + for string, charset in self._chunks: + if charset == last_charset: + last_chunk.append(string) + else: + if last_charset is not None: + chunks.append((SPACE.join(last_chunk), last_charset)) + last_chunk = [string] + last_charset = charset + if last_chunk: + chunks.append((SPACE.join(last_chunk), last_charset)) + self._chunks = chunks + + +class _ValueFormatter(object): + def __init__(self, headerlen, maxlen, continuation_ws, splitchars): + self._maxlen = maxlen + self._continuation_ws = continuation_ws + self._continuation_ws_len = len(continuation_ws) + self._splitchars = splitchars + self._lines = [] + self._current_line = _Accumulator(headerlen) + + def _str(self, linesep): + self.newline() + return linesep.join(self._lines) + + def __str__(self): + return self._str(NL) + + def newline(self): + end_of_line = self._current_line.pop() + if end_of_line != (' ', ''): + self._current_line.push(*end_of_line) + if len(self._current_line) > 0: + if self._current_line.is_onlyws(): + self._lines[-1] += str(self._current_line) + else: + self._lines.append(str(self._current_line)) + self._current_line.reset() + + def add_transition(self): + self._current_line.push(' ', '') + + def feed(self, fws, string, charset): + # If the charset has no header encoding (i.e. it is an ASCII encoding) + # then we must split the header at the "highest level syntactic break" + # possible. Note that we don't have a lot of smarts about field + # syntax; we just try to break on semi-colons, then commas, then + # whitespace. Eventually, this should be pluggable. + if charset.header_encoding is None: + self._ascii_split(fws, string, self._splitchars) + return + # Otherwise, we're doing either a Base64 or a quoted-printable + # encoding which means we don't need to split the line on syntactic + # breaks. We can basically just find enough characters to fit on the + # current line, minus the RFC 2047 chrome. What makes this trickier + # though is that we have to split at octet boundaries, not character + # boundaries but it's only safe to split at character boundaries so at + # best we can only get close. + encoded_lines = charset.header_encode_lines(string, self._maxlengths()) + # The first element extends the current line, but if it's None then + # nothing more fit on the current line so start a new line. + try: + first_line = encoded_lines.pop(0) + except IndexError: + # There are no encoded lines, so we're done. + return + if first_line is not None: + self._append_chunk(fws, first_line) + try: + last_line = encoded_lines.pop() + except IndexError: + # There was only one line. + return + self.newline() + self._current_line.push(self._continuation_ws, last_line) + # Everything else are full lines in themselves. + for line in encoded_lines: + self._lines.append(self._continuation_ws + line) + + def _maxlengths(self): + # The first line's length. + yield self._maxlen - len(self._current_line) + while True: + yield self._maxlen - self._continuation_ws_len + + def _ascii_split(self, fws, string, splitchars): + # The RFC 2822 header folding algorithm is simple in principle but + # complex in practice. Lines may be folded any place where "folding + # white space" appears by inserting a linesep character in front of the + # FWS. The complication is that not all spaces or tabs qualify as FWS, + # and we are also supposed to prefer to break at "higher level + # syntactic breaks". We can't do either of these without intimate + # knowledge of the structure of structured headers, which we don't have + # here. So the best we can do here is prefer to break at the specified + # splitchars, and hope that we don't choose any spaces or tabs that + # aren't legal FWS. (This is at least better than the old algorithm, + # where we would sometimes *introduce* FWS after a splitchar, or the + # algorithm before that, where we would turn all white space runs into + # single spaces or tabs.) + parts = re.split("(["+FWS+"]+)", fws+string) + if parts[0]: + parts[:0] = [''] + else: + parts.pop(0) + for fws, part in zip(*[iter(parts)]*2): + self._append_chunk(fws, part) + + def _append_chunk(self, fws, string): + self._current_line.push(fws, string) + if len(self._current_line) > self._maxlen: + # Find the best split point, working backward from the end. + # There might be none, on a long first line. + for ch in self._splitchars: + for i in range(self._current_line.part_count()-1, 0, -1): + if ch.isspace(): + fws = self._current_line[i][0] + if fws and fws[0]==ch: + break + prevpart = self._current_line[i-1][1] + if prevpart and prevpart[-1]==ch: + break + else: + continue + break + else: + fws, part = self._current_line.pop() + if self._current_line._initial_size > 0: + # There will be a header, so leave it on a line by itself. + self.newline() + if not fws: + # We don't use continuation_ws here because the whitespace + # after a header should always be a space. + fws = ' ' + self._current_line.push(fws, part) + return + remainder = self._current_line.pop_from(i) + self._lines.append(str(self._current_line)) + self._current_line.reset(remainder) + + +class _Accumulator(list): + + def __init__(self, initial_size=0): + self._initial_size = initial_size + super().__init__() + + def push(self, fws, string): + self.append((fws, string)) + + def pop_from(self, i=0): + popped = self[i:] + self[i:] = [] + return popped + + def pop(self): + if self.part_count()==0: + return ('', '') + return super().pop() + + def __len__(self): + return sum((len(fws)+len(part) for fws, part in self), + self._initial_size) + + def __str__(self): + return EMPTYSTRING.join((EMPTYSTRING.join((fws, part)) + for fws, part in self)) + + def reset(self, startval=None): + if startval is None: + startval = [] + self[:] = startval + self._initial_size = 0 + + def is_onlyws(self): + return self._initial_size==0 and (not self or str(self).isspace()) + + def part_count(self): + return super().__len__() diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/headerregistry.py b/.venv/lib/python3.12/site-packages/future/backports/email/headerregistry.py new file mode 100644 index 00000000..9aaad65a --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/headerregistry.py @@ -0,0 +1,592 @@ +"""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 __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +from future.builtins import super +from future.builtins import str +from future.utils import text_to_native_str +from future.backports.email import utils +from future.backports.email import errors +from future.backports.email import _header_value_parser as parser + +class Address(object): + + def __init__(self, display_name='', username='', domain='', addr_spec=None): + """Create an object represeting 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. + + """ + # 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 "Address(display_name={!r}, username={!r}, domain={!r})".format( + 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(object): + + 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 an + 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 "Group(display_name={!r}, addresses={!r}".format( + 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, **_3to2kwargs): + defects = _3to2kwargs['defects']; del _3to2kwargs['defects'] + parse_tree = _3to2kwargs['parse_tree']; del _3to2kwargs['parse_tree'] + 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, **_3to2kwargs): + policy = _3to2kwargs['policy']; del _3to2kwargs['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 only put fws here if it was in the source. + header = parser.Header([ + parser.HeaderLabel([ + parser.ValueTerminal(self.name, 'header-name'), + parser.ValueTerminal(':', 'header-sep')]), + parser.CFWSList([parser.WhiteSpaceTerminal(' ', 'fws')]), + self._parse_tree]) + return header.fold(policy=policy) + + +def _reconstruct_header(cls_name, bases, value): + return type(text_to_native_str(cls_name), bases, {})._reconstruct(value) + + +class UnstructuredHeader(object): + + 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(object): + + """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(object): + + 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(object): + + 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(object): + + # 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'] = dict((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 self._params.copy() + + +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(object): + + 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(object): + + """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(text_to_native_str('_'+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) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/iterators.py b/.venv/lib/python3.12/site-packages/future/backports/email/iterators.py new file mode 100644 index 00000000..82d320f8 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/iterators.py @@ -0,0 +1,74 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Various types of useful iterators and generators.""" +from __future__ import print_function +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__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(): + for subsubpart in subpart.walk(): + yield subsubpart + + +# 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): + for line in StringIO(payload): + yield line + + +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) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/message.py b/.venv/lib/python3.12/site-packages/future/backports/email/message.py new file mode 100644 index 00000000..d8d9615d --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/message.py @@ -0,0 +1,882 @@ +# -*- coding: utf-8 -*- +# Copyright (C) 2001-2007 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Basic message object for the email package object model.""" +from __future__ import absolute_import, division, unicode_literals +from future.builtins import list, range, str, zip + +__all__ = ['Message'] + +import re +import uu +import base64 +import binascii +from io import BytesIO, StringIO + +# Intrapackage imports +from future.utils import as_native_str +from future.backports.email import utils +from future.backports.email import errors +from future.backports.email._policybase import compat32 +from future.backports.email import charset as _charset +from future.backports.email._encoded_words import decode_b +Charset = _charset.Charset + +SEMISPACE = '; ' + +# Regular expression that matches `special' characters in parameters, the +# existence of which force quoting of the parameter value. +tspecials = re.compile(r'[ \(\)<>@,;:\\"/\[\]\?=]') + + +def _splitparam(param): + # Split header parameters. BAW: this may be too simple. It isn't + # strictly RFC 2045 (section 5.1) compliant, but it catches most headers + # found in the wild. We may eventually need a full fledged parser. + # RDM: we might have a Header here; for now just stringify it. + a, sep, b = str(param).partition(';') + if not sep: + return a.strip(), None + return a.strip(), b.strip() + +def _formatparam(param, value=None, quote=True): + """Convenience function to format and return a key=value pair. + + This will quote the value if needed or if quote is true. If value is a + three tuple (charset, language, value), it will be encoded according + to RFC2231 rules. If it contains non-ascii characters it will likewise + be encoded according to RFC2231 rules, using the utf-8 charset and + a null language. + """ + if value is not None and len(value) > 0: + # A tuple is used for RFC 2231 encoded parameter values where items + # are (charset, language, value). charset is a string, not a Charset + # instance. RFC 2231 encoded values are never quoted, per RFC. + if isinstance(value, tuple): + # Encode as per RFC 2231 + param += '*' + value = utils.encode_rfc2231(value[2], value[0], value[1]) + return '%s=%s' % (param, value) + else: + try: + value.encode('ascii') + except UnicodeEncodeError: + param += '*' + value = utils.encode_rfc2231(value, 'utf-8', '') + return '%s=%s' % (param, value) + # BAW: Please check this. I think that if quote is set it should + # force quoting even if not necessary. + if quote or tspecials.search(value): + return '%s="%s"' % (param, utils.quote(value)) + else: + return '%s=%s' % (param, value) + else: + return param + +def _parseparam(s): + # RDM This might be a Header, so for now stringify it. + s = ';' + str(s) + plist = [] + while s[:1] == ';': + s = s[1:] + end = s.find(';') + while end > 0 and (s.count('"', 0, end) - s.count('\\"', 0, end)) % 2: + end = s.find(';', end + 1) + if end < 0: + end = len(s) + f = s[:end] + if '=' in f: + i = f.index('=') + f = f[:i].strip().lower() + '=' + f[i+1:].strip() + plist.append(f.strip()) + s = s[end:] + return plist + + +def _unquotevalue(value): + # This is different than utils.collapse_rfc2231_value() because it doesn't + # try to convert the value to a unicode. Message.get_param() and + # Message.get_params() are both currently defined to return the tuple in + # the face of RFC 2231 parameters. + if isinstance(value, tuple): + return value[0], value[1], utils.unquote(value[2]) + else: + return utils.unquote(value) + + +class Message(object): + """Basic message object. + + A message object is defined as something that has a bunch of RFC 2822 + headers and a payload. It may optionally have an envelope header + (a.k.a. Unix-From or From_ header). If the message is a container (i.e. a + multipart or a message/rfc822), then the payload is a list of Message + objects, otherwise it is a string. + + Message objects implement part of the `mapping' interface, which assumes + there is exactly one occurrence of the header per message. Some headers + do in fact appear multiple times (e.g. Received) and for those headers, + you must use the explicit API to set or get all the headers. Not all of + the mapping methods are implemented. + """ + def __init__(self, policy=compat32): + self.policy = policy + self._headers = list() + self._unixfrom = None + self._payload = None + self._charset = None + # Defaults for multipart messages + self.preamble = self.epilogue = None + self.defects = [] + # Default content type + self._default_type = 'text/plain' + + @as_native_str(encoding='utf-8') + def __str__(self): + """Return the entire formatted message as a string. + This includes the headers, body, and envelope header. + """ + return self.as_string() + + def as_string(self, unixfrom=False, maxheaderlen=0): + """Return the entire formatted message as a (unicode) string. + Optional `unixfrom' when True, means include the Unix From_ envelope + header. + + This is a convenience method and may not generate the message exactly + as you intend. For more flexibility, use the flatten() method of a + Generator instance. + """ + from future.backports.email.generator import Generator + fp = StringIO() + g = Generator(fp, mangle_from_=False, maxheaderlen=maxheaderlen) + g.flatten(self, unixfrom=unixfrom) + return fp.getvalue() + + def is_multipart(self): + """Return True if the message consists of multiple parts.""" + return isinstance(self._payload, list) + + # + # Unix From_ line + # + def set_unixfrom(self, unixfrom): + self._unixfrom = unixfrom + + def get_unixfrom(self): + return self._unixfrom + + # + # Payload manipulation. + # + def attach(self, payload): + """Add the given payload to the current payload. + + The current payload will always be a list of objects after this method + is called. If you want to set the payload to a scalar object, use + set_payload() instead. + """ + if self._payload is None: + self._payload = [payload] + else: + self._payload.append(payload) + + def get_payload(self, i=None, decode=False): + """Return a reference to the payload. + + The payload will either be a list object or a string. If you mutate + the list object, you modify the message's payload in place. Optional + i returns that index into the payload. + + Optional decode is a flag indicating whether the payload should be + decoded or not, according to the Content-Transfer-Encoding header + (default is False). + + When True and the message is not a multipart, the payload will be + decoded if this header's value is `quoted-printable' or `base64'. If + some other encoding is used, or the header is missing, or if the + payload has bogus data (i.e. bogus base64 or uuencoded data), the + payload is returned as-is. + + If the message is a multipart and the decode flag is True, then None + is returned. + """ + # Here is the logic table for this code, based on the email5.0.0 code: + # i decode is_multipart result + # ------ ------ ------------ ------------------------------ + # None True True None + # i True True None + # None False True _payload (a list) + # i False True _payload element i (a Message) + # i False False error (not a list) + # i True False error (not a list) + # None False False _payload + # None True False _payload decoded (bytes) + # Note that Barry planned to factor out the 'decode' case, but that + # isn't so easy now that we handle the 8 bit data, which needs to be + # converted in both the decode and non-decode path. + if self.is_multipart(): + if decode: + return None + if i is None: + return self._payload + else: + return self._payload[i] + # For backward compatibility, Use isinstance and this error message + # instead of the more logical is_multipart test. + if i is not None and not isinstance(self._payload, list): + raise TypeError('Expected list, got %s' % type(self._payload)) + payload = self._payload + # cte might be a Header, so for now stringify it. + cte = str(self.get('content-transfer-encoding', '')).lower() + # payload may be bytes here. + if isinstance(payload, str): + payload = str(payload) # for Python-Future, so surrogateescape works + if utils._has_surrogates(payload): + bpayload = payload.encode('ascii', 'surrogateescape') + if not decode: + try: + payload = bpayload.decode(self.get_param('charset', 'ascii'), 'replace') + except LookupError: + payload = bpayload.decode('ascii', 'replace') + elif decode: + try: + bpayload = payload.encode('ascii') + except UnicodeError: + # This won't happen for RFC compliant messages (messages + # containing only ASCII codepoints in the unicode input). + # If it does happen, turn the string into bytes in a way + # guaranteed not to fail. + bpayload = payload.encode('raw-unicode-escape') + if not decode: + return payload + if cte == 'quoted-printable': + return utils._qdecode(bpayload) + elif cte == 'base64': + # XXX: this is a bit of a hack; decode_b should probably be factored + # out somewhere, but I haven't figured out where yet. + value, defects = decode_b(b''.join(bpayload.splitlines())) + for defect in defects: + self.policy.handle_defect(self, defect) + return value + elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'): + in_file = BytesIO(bpayload) + out_file = BytesIO() + try: + uu.decode(in_file, out_file, quiet=True) + return out_file.getvalue() + except uu.Error: + # Some decoding problem + return bpayload + if isinstance(payload, str): + return bpayload + return payload + + def set_payload(self, payload, charset=None): + """Set the payload to the given value. + + Optional charset sets the message's default character set. See + set_charset() for details. + """ + self._payload = payload + if charset is not None: + self.set_charset(charset) + + def set_charset(self, charset): + """Set the charset of the payload to a given character set. + + charset can be a Charset instance, a string naming a character set, or + None. If it is a string it will be converted to a Charset instance. + If charset is None, the charset parameter will be removed from the + Content-Type field. Anything else will generate a TypeError. + + The message will be assumed to be of type text/* encoded with + charset.input_charset. It will be converted to charset.output_charset + and encoded properly, if needed, when generating the plain text + representation of the message. MIME headers (MIME-Version, + Content-Type, Content-Transfer-Encoding) will be added as needed. + """ + if charset is None: + self.del_param('charset') + self._charset = None + return + if not isinstance(charset, Charset): + charset = Charset(charset) + self._charset = charset + if 'MIME-Version' not in self: + self.add_header('MIME-Version', '1.0') + if 'Content-Type' not in self: + self.add_header('Content-Type', 'text/plain', + charset=charset.get_output_charset()) + else: + self.set_param('charset', charset.get_output_charset()) + if charset != charset.get_output_charset(): + self._payload = charset.body_encode(self._payload) + if 'Content-Transfer-Encoding' not in self: + cte = charset.get_body_encoding() + try: + cte(self) + except TypeError: + self._payload = charset.body_encode(self._payload) + self.add_header('Content-Transfer-Encoding', cte) + + def get_charset(self): + """Return the Charset instance associated with the message's payload. + """ + return self._charset + + # + # MAPPING INTERFACE (partial) + # + def __len__(self): + """Return the total number of headers, including duplicates.""" + return len(self._headers) + + def __getitem__(self, name): + """Get a header value. + + Return None if the header is missing instead of raising an exception. + + Note that if the header appeared multiple times, exactly which + occurrence gets returned is undefined. Use get_all() to get all + the values matching a header field name. + """ + return self.get(name) + + def __setitem__(self, name, val): + """Set the value of a header. + + Note: this does not overwrite an existing header with the same field + name. Use __delitem__() first to delete any existing headers. + """ + max_count = self.policy.header_max_count(name) + if max_count: + lname = name.lower() + found = 0 + for k, v in self._headers: + if k.lower() == lname: + found += 1 + if found >= max_count: + raise ValueError("There may be at most {} {} headers " + "in a message".format(max_count, name)) + self._headers.append(self.policy.header_store_parse(name, val)) + + def __delitem__(self, name): + """Delete all occurrences of a header, if present. + + Does not raise an exception if the header is missing. + """ + name = name.lower() + newheaders = list() + for k, v in self._headers: + if k.lower() != name: + newheaders.append((k, v)) + self._headers = newheaders + + def __contains__(self, name): + return name.lower() in [k.lower() for k, v in self._headers] + + def __iter__(self): + for field, value in self._headers: + yield field + + def keys(self): + """Return a list of all the message's header field names. + + These will be sorted in the order they appeared in the original + message, or were added to the message, and may contain duplicates. + Any fields deleted and re-inserted are always appended to the header + list. + """ + return [k for k, v in self._headers] + + def values(self): + """Return a list of all the message's header values. + + These will be sorted in the order they appeared in the original + message, or were added to the message, and may contain duplicates. + Any fields deleted and re-inserted are always appended to the header + list. + """ + return [self.policy.header_fetch_parse(k, v) + for k, v in self._headers] + + def items(self): + """Get all the message's header fields and values. + + These will be sorted in the order they appeared in the original + message, or were added to the message, and may contain duplicates. + Any fields deleted and re-inserted are always appended to the header + list. + """ + return [(k, self.policy.header_fetch_parse(k, v)) + for k, v in self._headers] + + def get(self, name, failobj=None): + """Get a header value. + + Like __getitem__() but return failobj instead of None when the field + is missing. + """ + name = name.lower() + for k, v in self._headers: + if k.lower() == name: + return self.policy.header_fetch_parse(k, v) + return failobj + + # + # "Internal" methods (public API, but only intended for use by a parser + # or generator, not normal application code. + # + + def set_raw(self, name, value): + """Store name and value in the model without modification. + + This is an "internal" API, intended only for use by a parser. + """ + self._headers.append((name, value)) + + def raw_items(self): + """Return the (name, value) header pairs without modification. + + This is an "internal" API, intended only for use by a generator. + """ + return iter(self._headers.copy()) + + # + # Additional useful stuff + # + + def get_all(self, name, failobj=None): + """Return a list of all the values for the named field. + + These will be sorted in the order they appeared in the original + message, and may contain duplicates. Any fields deleted and + re-inserted are always appended to the header list. + + If no such fields exist, failobj is returned (defaults to None). + """ + values = [] + name = name.lower() + for k, v in self._headers: + if k.lower() == name: + values.append(self.policy.header_fetch_parse(k, v)) + if not values: + return failobj + return values + + def add_header(self, _name, _value, **_params): + """Extended header setting. + + name is the header field to add. keyword arguments can be used to set + additional parameters for the header field, with underscores converted + to dashes. Normally the parameter will be added as key="value" unless + value is None, in which case only the key will be added. If a + parameter value contains non-ASCII characters it can be specified as a + three-tuple of (charset, language, value), in which case it will be + encoded according to RFC2231 rules. Otherwise it will be encoded using + the utf-8 charset and a language of ''. + + Examples: + + msg.add_header('content-disposition', 'attachment', filename='bud.gif') + msg.add_header('content-disposition', 'attachment', + filename=('utf-8', '', 'Fußballer.ppt')) + msg.add_header('content-disposition', 'attachment', + filename='Fußballer.ppt')) + """ + parts = [] + for k, v in _params.items(): + if v is None: + parts.append(k.replace('_', '-')) + else: + parts.append(_formatparam(k.replace('_', '-'), v)) + if _value is not None: + parts.insert(0, _value) + self[_name] = SEMISPACE.join(parts) + + def replace_header(self, _name, _value): + """Replace a header. + + Replace the first matching header found in the message, retaining + header order and case. If no matching header was found, a KeyError is + raised. + """ + _name = _name.lower() + for i, (k, v) in zip(range(len(self._headers)), self._headers): + if k.lower() == _name: + self._headers[i] = self.policy.header_store_parse(k, _value) + break + else: + raise KeyError(_name) + + # + # Use these three methods instead of the three above. + # + + def get_content_type(self): + """Return the message's content type. + + The returned string is coerced to lower case of the form + `maintype/subtype'. If there was no Content-Type header in the + message, the default type as given by get_default_type() will be + returned. Since according to RFC 2045, messages always have a default + type this will always return a value. + + RFC 2045 defines a message's default type to be text/plain unless it + appears inside a multipart/digest container, in which case it would be + message/rfc822. + """ + missing = object() + value = self.get('content-type', missing) + if value is missing: + # This should have no parameters + return self.get_default_type() + ctype = _splitparam(value)[0].lower() + # RFC 2045, section 5.2 says if its invalid, use text/plain + if ctype.count('/') != 1: + return 'text/plain' + return ctype + + def get_content_maintype(self): + """Return the message's main content type. + + This is the `maintype' part of the string returned by + get_content_type(). + """ + ctype = self.get_content_type() + return ctype.split('/')[0] + + def get_content_subtype(self): + """Returns the message's sub-content type. + + This is the `subtype' part of the string returned by + get_content_type(). + """ + ctype = self.get_content_type() + return ctype.split('/')[1] + + def get_default_type(self): + """Return the `default' content type. + + Most messages have a default content type of text/plain, except for + messages that are subparts of multipart/digest containers. Such + subparts have a default content type of message/rfc822. + """ + return self._default_type + + def set_default_type(self, ctype): + """Set the `default' content type. + + ctype should be either "text/plain" or "message/rfc822", although this + is not enforced. The default content type is not stored in the + Content-Type header. + """ + self._default_type = ctype + + def _get_params_preserve(self, failobj, header): + # Like get_params() but preserves the quoting of values. BAW: + # should this be part of the public interface? + missing = object() + value = self.get(header, missing) + if value is missing: + return failobj + params = [] + for p in _parseparam(value): + try: + name, val = p.split('=', 1) + name = name.strip() + val = val.strip() + except ValueError: + # Must have been a bare attribute + name = p.strip() + val = '' + params.append((name, val)) + params = utils.decode_params(params) + return params + + def get_params(self, failobj=None, header='content-type', unquote=True): + """Return the message's Content-Type parameters, as a list. + + The elements of the returned list are 2-tuples of key/value pairs, as + split on the `=' sign. The left hand side of the `=' is the key, + while the right hand side is the value. If there is no `=' sign in + the parameter the value is the empty string. The value is as + described in the get_param() method. + + Optional failobj is the object to return if there is no Content-Type + header. Optional header is the header to search instead of + Content-Type. If unquote is True, the value is unquoted. + """ + missing = object() + params = self._get_params_preserve(missing, header) + if params is missing: + return failobj + if unquote: + return [(k, _unquotevalue(v)) for k, v in params] + else: + return params + + def get_param(self, param, failobj=None, header='content-type', + unquote=True): + """Return the parameter value if found in the Content-Type header. + + Optional failobj is the object to return if there is no Content-Type + header, or the Content-Type header has no such parameter. Optional + header is the header to search instead of Content-Type. + + Parameter keys are always compared case insensitively. The return + value can either be a string, or a 3-tuple if the parameter was RFC + 2231 encoded. When it's a 3-tuple, the elements of the value are of + the form (CHARSET, LANGUAGE, VALUE). Note that both CHARSET and + LANGUAGE can be None, in which case you should consider VALUE to be + encoded in the us-ascii charset. You can usually ignore LANGUAGE. + The parameter value (either the returned string, or the VALUE item in + the 3-tuple) is always unquoted, unless unquote is set to False. + + If your application doesn't care whether the parameter was RFC 2231 + encoded, it can turn the return value into a string as follows: + + param = msg.get_param('foo') + param = email.utils.collapse_rfc2231_value(rawparam) + + """ + if header not in self: + return failobj + for k, v in self._get_params_preserve(failobj, header): + if k.lower() == param.lower(): + if unquote: + return _unquotevalue(v) + else: + return v + return failobj + + def set_param(self, param, value, header='Content-Type', requote=True, + charset=None, language=''): + """Set a parameter in the Content-Type header. + + If the parameter already exists in the header, its value will be + replaced with the new value. + + If header is Content-Type and has not yet been defined for this + message, it will be set to "text/plain" and the new parameter and + value will be appended as per RFC 2045. + + An alternate header can specified in the header argument, and all + parameters will be quoted as necessary unless requote is False. + + If charset is specified, the parameter will be encoded according to RFC + 2231. Optional language specifies the RFC 2231 language, defaulting + to the empty string. Both charset and language should be strings. + """ + if not isinstance(value, tuple) and charset: + value = (charset, language, value) + + if header not in self and header.lower() == 'content-type': + ctype = 'text/plain' + else: + ctype = self.get(header) + if not self.get_param(param, header=header): + if not ctype: + ctype = _formatparam(param, value, requote) + else: + ctype = SEMISPACE.join( + [ctype, _formatparam(param, value, requote)]) + else: + ctype = '' + for old_param, old_value in self.get_params(header=header, + unquote=requote): + append_param = '' + if old_param.lower() == param.lower(): + append_param = _formatparam(param, value, requote) + else: + append_param = _formatparam(old_param, old_value, requote) + if not ctype: + ctype = append_param + else: + ctype = SEMISPACE.join([ctype, append_param]) + if ctype != self.get(header): + del self[header] + self[header] = ctype + + def del_param(self, param, header='content-type', requote=True): + """Remove the given parameter completely from the Content-Type header. + + The header will be re-written in place without the parameter or its + value. All values will be quoted as necessary unless requote is + False. Optional header specifies an alternative to the Content-Type + header. + """ + if header not in self: + return + new_ctype = '' + for p, v in self.get_params(header=header, unquote=requote): + if p.lower() != param.lower(): + if not new_ctype: + new_ctype = _formatparam(p, v, requote) + else: + new_ctype = SEMISPACE.join([new_ctype, + _formatparam(p, v, requote)]) + if new_ctype != self.get(header): + del self[header] + self[header] = new_ctype + + def set_type(self, type, header='Content-Type', requote=True): + """Set the main type and subtype for the Content-Type header. + + type must be a string in the form "maintype/subtype", otherwise a + ValueError is raised. + + This method replaces the Content-Type header, keeping all the + parameters in place. If requote is False, this leaves the existing + header's quoting as is. Otherwise, the parameters will be quoted (the + default). + + An alternative header can be specified in the header argument. When + the Content-Type header is set, we'll always also add a MIME-Version + header. + """ + # BAW: should we be strict? + if not type.count('/') == 1: + raise ValueError + # Set the Content-Type, you get a MIME-Version + if header.lower() == 'content-type': + del self['mime-version'] + self['MIME-Version'] = '1.0' + if header not in self: + self[header] = type + return + params = self.get_params(header=header, unquote=requote) + del self[header] + self[header] = type + # Skip the first param; it's the old type. + for p, v in params[1:]: + self.set_param(p, v, header, requote) + + def get_filename(self, failobj=None): + """Return the filename associated with the payload if present. + + The filename is extracted from the Content-Disposition header's + `filename' parameter, and it is unquoted. If that header is missing + the `filename' parameter, this method falls back to looking for the + `name' parameter. + """ + missing = object() + filename = self.get_param('filename', missing, 'content-disposition') + if filename is missing: + filename = self.get_param('name', missing, 'content-type') + if filename is missing: + return failobj + return utils.collapse_rfc2231_value(filename).strip() + + def get_boundary(self, failobj=None): + """Return the boundary associated with the payload if present. + + The boundary is extracted from the Content-Type header's `boundary' + parameter, and it is unquoted. + """ + missing = object() + boundary = self.get_param('boundary', missing) + if boundary is missing: + return failobj + # RFC 2046 says that boundaries may begin but not end in w/s + return utils.collapse_rfc2231_value(boundary).rstrip() + + def set_boundary(self, boundary): + """Set the boundary parameter in Content-Type to 'boundary'. + + This is subtly different than deleting the Content-Type header and + adding a new one with a new boundary parameter via add_header(). The + main difference is that using the set_boundary() method preserves the + order of the Content-Type header in the original message. + + HeaderParseError is raised if the message has no Content-Type header. + """ + missing = object() + params = self._get_params_preserve(missing, 'content-type') + if params is missing: + # There was no Content-Type header, and we don't know what type + # to set it to, so raise an exception. + raise errors.HeaderParseError('No Content-Type header found') + newparams = list() + foundp = False + for pk, pv in params: + if pk.lower() == 'boundary': + newparams.append(('boundary', '"%s"' % boundary)) + foundp = True + else: + newparams.append((pk, pv)) + if not foundp: + # The original Content-Type header had no boundary attribute. + # Tack one on the end. BAW: should we raise an exception + # instead??? + newparams.append(('boundary', '"%s"' % boundary)) + # Replace the existing Content-Type header with the new value + newheaders = list() + for h, v in self._headers: + if h.lower() == 'content-type': + parts = list() + for k, v in newparams: + if v == '': + parts.append(k) + else: + parts.append('%s=%s' % (k, v)) + val = SEMISPACE.join(parts) + newheaders.append(self.policy.header_store_parse(h, val)) + + else: + newheaders.append((h, v)) + self._headers = newheaders + + def get_content_charset(self, failobj=None): + """Return the charset parameter of the Content-Type header. + + The returned string is always coerced to lower case. If there is no + Content-Type header, or if that header has no charset parameter, + failobj is returned. + """ + missing = object() + charset = self.get_param('charset', missing) + if charset is missing: + return failobj + if isinstance(charset, tuple): + # RFC 2231 encoded, so decode it, and it better end up as ascii. + pcharset = charset[0] or 'us-ascii' + try: + # LookupError will be raised if the charset isn't known to + # Python. UnicodeError will be raised if the encoded text + # contains a character not in the charset. + as_bytes = charset[2].encode('raw-unicode-escape') + charset = str(as_bytes, pcharset) + except (LookupError, UnicodeError): + charset = charset[2] + # charset characters must be in us-ascii range + try: + charset.encode('us-ascii') + except UnicodeError: + return failobj + # RFC 2046, $4.1.2 says charsets are not case sensitive + return charset.lower() + + def get_charsets(self, failobj=None): + """Return a list containing the charset(s) used in this message. + + The returned list of items describes the Content-Type headers' + charset parameter for this message and all the subparts in its + payload. + + Each item will either be a string (the value of the charset parameter + in the Content-Type header of that part) or the value of the + 'failobj' parameter (defaults to None), if the part does not have a + main MIME type of "text", or the charset is not defined. + + The list will contain one string for each part of the message, plus + one for the container message (i.e. self), so that a non-multipart + message will still return a list of length 1. + """ + return [part.get_content_charset(failobj) for part in self.walk()] + + # I.e. def walk(self): ... + from future.backports.email.iterators import walk diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/__init__.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/__init__.py new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/__init__.py diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/application.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/application.py new file mode 100644 index 00000000..5cbfb174 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/application.py @@ -0,0 +1,39 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Keith Dart +# Contact: email-sig@python.org + +"""Class representing application/* type MIME documents.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +from future.backports.email import encoders +from future.backports.email.mime.nonmultipart import MIMENonMultipart + +__all__ = ["MIMEApplication"] + + +class MIMEApplication(MIMENonMultipart): + """Class for generating application/* MIME documents.""" + + def __init__(self, _data, _subtype='octet-stream', + _encoder=encoders.encode_base64, **_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, **_params) + self.set_payload(_data) + _encoder(self) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/audio.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/audio.py new file mode 100644 index 00000000..4989c114 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/audio.py @@ -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.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__all__ = ['MIMEAudio'] + +import sndhdr + +from io import BytesIO +from future.backports.email import encoders +from future.backports.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, **_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, **_params) + self.set_payload(_audiodata) + _encoder(self) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/base.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/base.py new file mode 100644 index 00000000..e77f3ca4 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/base.py @@ -0,0 +1,25 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Base class for MIME specializations.""" +from __future__ import absolute_import, division, unicode_literals +from future.backports.email import message + +__all__ = ['MIMEBase'] + + +class MIMEBase(message.Message): + """Base class for MIME specializations.""" + + def __init__(self, _maintype, _subtype, **_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. + """ + message.Message.__init__(self) + ctype = '%s/%s' % (_maintype, _subtype) + self.add_header('Content-Type', ctype, **_params) + self['MIME-Version'] = '1.0' diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/image.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/image.py new file mode 100644 index 00000000..a0360246 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/image.py @@ -0,0 +1,48 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Class representing image/* type MIME documents.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__all__ = ['MIMEImage'] + +import imghdr + +from future.backports.email import encoders +from future.backports.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, **_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, **_params) + self.set_payload(_imagedata) + _encoder(self) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/message.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/message.py new file mode 100644 index 00000000..7f920751 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/message.py @@ -0,0 +1,36 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Class representing message/* MIME documents.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__all__ = ['MIMEMessage'] + +from future.backports.email import message +from future.backports.email.mime.nonmultipart import MIMENonMultipart + + +class MIMEMessage(MIMENonMultipart): + """Class representing message/* MIME documents.""" + + def __init__(self, _msg, _subtype='rfc822'): + """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) + 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') diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/multipart.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/multipart.py new file mode 100644 index 00000000..6d7ed3dc --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/multipart.py @@ -0,0 +1,49 @@ +# Copyright (C) 2002-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Base class for MIME multipart/* type messages.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__all__ = ['MIMEMultipart'] + +from future.backports.email.mime.base import MIMEBase + + +class MIMEMultipart(MIMEBase): + """Base class for MIME multipart/* type messages.""" + + def __init__(self, _subtype='mixed', boundary=None, _subparts=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, **_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) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/nonmultipart.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/nonmultipart.py new file mode 100644 index 00000000..08c37c36 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/nonmultipart.py @@ -0,0 +1,24 @@ +# 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.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__all__ = ['MIMENonMultipart'] + +from future.backports.email import errors +from future.backports.email.mime.base import MIMEBase + + +class MIMENonMultipart(MIMEBase): + """Base class for MIME 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/*') diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/mime/text.py b/.venv/lib/python3.12/site-packages/future/backports/email/mime/text.py new file mode 100644 index 00000000..6269f4a6 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/mime/text.py @@ -0,0 +1,44 @@ +# Copyright (C) 2001-2006 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Class representing text/* type MIME documents.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__all__ = ['MIMEText'] + +from future.backports.email.encoders import encode_7or8bit +from future.backports.email.mime.nonmultipart import MIMENonMultipart + + +class MIMEText(MIMENonMultipart): + """Class for generating text/* type MIME documents.""" + + def __init__(self, _text, _subtype='plain', _charset=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, + **{'charset': _charset}) + + self.set_payload(_text, _charset) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/parser.py b/.venv/lib/python3.12/site-packages/future/backports/email/parser.py new file mode 100644 index 00000000..79f0e5a3 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/parser.py @@ -0,0 +1,135 @@ +# 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.""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import + +__all__ = ['Parser', 'HeaderParser', 'BytesParser', 'BytesHeaderParser'] + +import warnings +from io import StringIO, TextIOWrapper + +from future.backports.email.feedparser import FeedParser, BytesFeedParser +from future.backports.email.message import Message +from future.backports.email._policybase import compat32 + + +class Parser(object): + def __init__(self, _class=Message, **_3to2kwargs): + """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. + + """ + if 'policy' in _3to2kwargs: policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] + else: policy = compat32 + 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(object): + + 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') + with fp: + return self.parser.parse(fp, headersonly) + + + 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) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/policy.py b/.venv/lib/python3.12/site-packages/future/backports/email/policy.py new file mode 100644 index 00000000..2f609a23 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/policy.py @@ -0,0 +1,193 @@ +"""This will be the home for the policy that hooks in the new +code that adds all the email6 features. +""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import super + +from future.standard_library.email._policybase import (Policy, Compat32, + compat32, _extend_docstrings) +from future.standard_library.email.utils import _has_surrogates +from future.standard_library.email.headerregistry import HeaderRegistry as HeaderRegistry + +__all__ = [ + 'Compat32', + 'compat32', + 'Policy', + 'EmailPolicy', + 'default', + 'strict', + 'SMTP', + 'HTTP', + ] + +@_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: + + 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.) + """ + + refold_source = 'long' + header_factory = HeaderRegistry() + + 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: + 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 + return self.header_factory(name, ''.join(value.splitlines())) + + 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. + + """ + folded = self._fold(name, value, refold_binary=self.cte_type=='7bit') + return folded.encode('ascii', '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) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/quoprimime.py b/.venv/lib/python3.12/site-packages/future/backports/email/quoprimime.py new file mode 100644 index 00000000..b69d158b --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/quoprimime.py @@ -0,0 +1,326 @@ +# 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. +""" +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future.builtins import bytes, chr, dict, int, range, super + +__all__ = [ + 'body_decode', + 'body_encode', + 'body_length', + 'decode', + 'decodestring', + 'header_decode', + 'header_encode', + 'header_length', + 'quote', + 'unquote', + ] + +import re +import io + +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_HEADER_MAP = dict((c, '=%02X' % c) for c in range(256)) +_QUOPRI_BODY_MAP = _QUOPRI_HEADER_MAP.copy() + +# Safe header bytes which need no encoding. +for c in bytes(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 bytes(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 '=%02X' % 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 = [] + for octet in header_bytes: + encoded.append(_QUOPRI_HEADER_MAP[octet]) + # Now add the RFC chrome to each encoded chunk and glue the chunks + # together. + return '=?%s?q?%s?=' % (charset, EMPTYSTRING.join(encoded)) + + +class _body_accumulator(io.StringIO): + + def __init__(self, maxlinelen, eol, *args, **kw): + super().__init__(*args, **kw) + self.eol = eol + self.maxlinelen = self.room = maxlinelen + + def write_str(self, s): + """Add string s to the accumulated body.""" + self.write(s) + self.room -= len(s) + + def newline(self): + """Write eol, then start new line.""" + self.write_str(self.eol) + self.room = self.maxlinelen + + def write_soft_break(self): + """Write a soft break, then start a new line.""" + self.write_str('=') + self.newline() + + def write_wrapped(self, s, extra_room=0): + """Add a soft line break if needed, then write s.""" + if self.room < len(s) + extra_room: + self.write_soft_break() + self.write_str(s) + + def write_char(self, c, is_last_char): + if not is_last_char: + # Another character follows on this line, so we must leave + # extra room, either for it or a soft break, and whitespace + # need not be quoted. + self.write_wrapped(c, extra_room=1) + elif c not in ' \t': + # For this and remaining cases, no more characters follow, + # so there is no need to reserve extra room (since a hard + # break will immediately follow). + self.write_wrapped(c) + elif self.room >= 3: + # It's a whitespace character at end-of-line, and we have room + # for the three-character quoted encoding. + self.write(quote(c)) + elif self.room == 2: + # There's room for the whitespace character and a soft break. + self.write(c) + self.write_soft_break() + else: + # There's room only for a soft break. The quoted whitespace + # will be the only content on the subsequent line. + self.write_soft_break() + self.write(quote(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 + + # The last line may or may not end in eol, but all other lines do. + last_has_eol = (body[-1] in '\r\n') + + # This accumulator will make it easier to build the encoded body. + encoded_body = _body_accumulator(maxlinelen, eol) + + lines = body.splitlines() + last_line_no = len(lines) - 1 + for line_no, line in enumerate(lines): + last_char_index = len(line) - 1 + for i, c in enumerate(line): + if body_check(ord(c)): + c = quote(c) + encoded_body.write_char(c, i==last_char_index) + # Add an eol if input line had eol. All input lines have eol except + # possibly the last one. + if line_no < last_line_no or last_has_eol: + encoded_body.newline() + + return encoded_body.getvalue() + + + +# 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-8895-1?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, re.ASCII) diff --git a/.venv/lib/python3.12/site-packages/future/backports/email/utils.py b/.venv/lib/python3.12/site-packages/future/backports/email/utils.py new file mode 100644 index 00000000..4abebf7c --- /dev/null +++ b/.venv/lib/python3.12/site-packages/future/backports/email/utils.py @@ -0,0 +1,400 @@ +# Copyright (C) 2001-2010 Python Software Foundation +# Author: Barry Warsaw +# Contact: email-sig@python.org + +"""Miscellaneous utilities.""" + +from __future__ import unicode_literals +from __future__ import division +from __future__ import absolute_import +from future import utils +from future.builtins import bytes, int, str + +__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 +if utils.PY2: + re.ASCII = 0 +import time +import base64 +import random +import socket +from future.backports import datetime +from future.backports.urllib.parse import quote as url_quote, unquote as url_unquote +import warnings +from io import StringIO + +from future.backports.email._parseaddr import quote +from future.backports.email._parseaddr import AddressList as _AddressList +from future.backports.email._parseaddr import mktime_tz + +from future.backports.email._parseaddr import parsedate, parsedate_tz, _parsedate_tz + +from quopri import decodestring as _qdecode + +# Intrapackage imports +from future.backports.email.encoders import _bencode, _qencode +from future.backports.email.charset import Charset + +COMMASPACE = ', ' +EMPTYSTRING = '' +UEMPTYSTRING = '' +CRLF = '\r\n' +TICK = "'" + +specialsre = re.compile(r'[][\\()<>@,:;".]') +escapesre = re.compile(r'[\\"]') + +# How to figure out if we are processing strings that come from a byte +# source with undecodable characters. +_has_surrogates = re.compile( + '([^\ud800-\udbff]|\A)[\udc00-\udfff]([^\udc00-\udfff]|\Z)').search + +# 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. + original_bytes = string.encode('ascii', 'surrogateescape') + return original_bytes.decode('ascii', '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 an 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: + now = time.localtime(timeval) + # Calculate timezone offset, based on whether the local zone has + # daylight savings time, and whether DST is in effect. + if time.daylight and now[-1]: + offset = time.altzone + else: + offset = time.timezone + hours, minutes = divmod(abs(offset), 3600) + # Remember offset is in seconds west of UTC, but the timezone is in + # minutes east of UTC, so the signs differ. + if offset > 0: + sign = '-' + else: + sign = '+' + zone = '%s%02d%02d' % (sign, hours, minutes // 60) + else: + now = time.gmtime(timeval) + # Timezone offset is always -0000 + if usegmt: + zone = 'GMT' + else: + zone = '-0000' + return _format_timetuple_and_zone(now, zone) + +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: + + <20020201195627.33539.96671@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 = time.time() + utcdate = time.strftime('%Y%m%d%H%M%S', time.gmtime(timeval)) + pid = os.getpid() + randint = random.randrange(100000) + if idstring is None: + idstring = '' + else: + idstring = '.' + idstring + if domain is None: + domain = socket.getfqdn() + msgid = '<%s.%s.%s%s@%s>' % (utcdate, pid, randint, idstring, domain) + return msgid + + +def parsedate_to_datetime(data): + _3to2list = list(_parsedate_tz(data)) + dtuple, tz, = [_3to2list[:-1]] + _3to2list[-1:] + if tz is None: + return datetime.datetime(*dtuple[:6]) + return datetime.datetime(*dtuple[:6], + tzinfo=datetime.timezone(datetime.timedelta(seconds=tz))) + + +def parseaddr(addr): + 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 = url_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 = url_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 + 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) |