From e9d5b6ea2d68564f176fdf70c2d7028e060c62b5 Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Wed, 10 Jan 2024 14:54:36 +0200 Subject: gh-113594: Fix UnicodeEncodeError in TokenList.fold() (GH-113730) It occurred when try to re-encode an unknown-8bit part combined with non-unknown-8bit part. --- Lib/email/_header_value_parser.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'Lib/email/_header_value_parser.py') diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index 0d6bd812475..5b653f66c18 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -2766,6 +2766,7 @@ def _refold_parse_tree(parse_tree, *, policy): encoding = 'utf-8' if policy.utf8 else 'us-ascii' lines = [''] last_ew = None + last_charset = None wrap_as_ew_blocked = 0 want_encoding = False end_ew_not_allowed = Terminal('', 'wrap_as_ew_blocked') @@ -2820,8 +2821,14 @@ def _refold_parse_tree(parse_tree, *, policy): else: # It's a terminal, wrap it as an encoded word, possibly # combining it with previously encoded words if allowed. + if (last_ew is not None and + charset != last_charset and + (last_charset == 'unknown-8bit' or + last_charset == 'utf-8' and charset != 'us-ascii')): + last_ew = None last_ew = _fold_as_ew(tstr, lines, maxlen, last_ew, part.ew_combine_allowed, charset) + last_charset = charset want_encoding = False continue if len(tstr) <= maxlen - len(lines[-1]): -- cgit v1.2.3