diff options
| author | shadchin <[email protected]> | 2026-02-07 19:56:35 +0300 |
|---|---|---|
| committer | shadchin <[email protected]> | 2026-02-07 20:23:53 +0300 |
| commit | 19d43a3e6fb4cb8ea11747d7d7bca7a3542fbb44 (patch) | |
| tree | 0b1418938140a0b6470953bef6069454ffdf1bd0 /contrib/tools/python3/Lib/email/_header_value_parser.py | |
| parent | 0879409bfc0891ab8103828a3bdbf0e960475fec (diff) | |
Update Python 3 to 3.13.12
commit_hash:71d3efea437a769b2b7910d196120bb02587046e
Diffstat (limited to 'contrib/tools/python3/Lib/email/_header_value_parser.py')
| -rw-r--r-- | contrib/tools/python3/Lib/email/_header_value_parser.py | 50 |
1 files changed, 49 insertions, 1 deletions
diff --git a/contrib/tools/python3/Lib/email/_header_value_parser.py b/contrib/tools/python3/Lib/email/_header_value_parser.py index 91243378dc0..51727688c05 100644 --- a/contrib/tools/python3/Lib/email/_header_value_parser.py +++ b/contrib/tools/python3/Lib/email/_header_value_parser.py @@ -101,6 +101,12 @@ def make_quoted_pairs(value): return str(value).replace('\\', '\\\\').replace('"', '\\"') +def make_parenthesis_pairs(value): + """Escape parenthesis and backslash for use within a comment.""" + return str(value).replace('\\', '\\\\') \ + .replace('(', '\\(').replace(')', '\\)') + + def quote_string(value): escaped = make_quoted_pairs(value) return f'"{escaped}"' @@ -874,6 +880,12 @@ class MessageID(MsgID): class InvalidMessageID(MessageID): token_type = 'invalid-message-id' +class MessageIDList(TokenList): + token_type = 'message-id-list' + + @property + def message_ids(self): + return [x for x in self if x.token_type=='msg-id'] class Header(TokenList): token_type = 'header' @@ -933,7 +945,7 @@ class WhiteSpaceTerminal(Terminal): return ' ' def startswith_fws(self): - return True + return self and self[0] in WSP class ValueTerminal(Terminal): @@ -2171,6 +2183,32 @@ def parse_message_id(value): return message_id +def parse_message_ids(value): + """in-reply-to = "In-Reply-To:" 1*msg-id CRLF + references = "References:" 1*msg-id CRLF + """ + message_id_list = MessageIDList() + while value: + if value[0] == ',': + # message id list separated with commas - this is invalid, + # but happens rather frequently in the wild + message_id_list.defects.append( + errors.InvalidHeaderDefect("comma in msg-id list")) + message_id_list.append( + WhiteSpaceTerminal(' ', 'invalid-comma-replacement')) + value = value[1:] + continue + try: + token, value = get_msg_id(value) + message_id_list.append(token) + except errors.HeaderParseError as ex: + token = get_unstructured(value) + message_id_list.append(InvalidMessageID(token)) + message_id_list.defects.append( + errors.InvalidHeaderDefect("Invalid msg-id: {!r}".format(ex))) + break + return message_id_list + # # 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 @@ -2788,6 +2826,9 @@ def _steal_trailing_WSP_if_exists(lines): if lines and lines[-1] and lines[-1][-1] in WSP: wsp = lines[-1][-1] lines[-1] = lines[-1][:-1] + # gh-142006: if the line is now empty, remove it entirely. + if not lines[-1]: + lines.pop() return wsp def _refold_parse_tree(parse_tree, *, policy): @@ -2924,6 +2965,13 @@ def _refold_parse_tree(parse_tree, *, policy): [ValueTerminal(make_quoted_pairs(p), 'ptext') for p in newparts] + [ValueTerminal('"', 'ptext')]) + if part.token_type == 'comment': + newparts = ( + [ValueTerminal('(', 'ptext')] + + [ValueTerminal(make_parenthesis_pairs(p), 'ptext') + if p.token_type == 'ptext' else p + for p in newparts] + + [ValueTerminal(')', 'ptext')]) if not part.as_ew_allowed: wrap_as_ew_blocked += 1 newparts.append(end_ew_not_allowed) |
