diff options
| author | Konstantin Ryabitsev <konstantin@linuxfoundation.org> | 2020-12-28 13:04:02 -0500 |
|---|---|---|
| committer | Konstantin Ryabitsev <konstantin@linuxfoundation.org> | 2020-12-28 13:04:02 -0500 |
| commit | f7622a9c8d5ad88c199e4151d50510285b6c7aeb (patch) | |
| tree | 6fa529fd15c0717690f17269a01c6244cc80e29b | |
| parent | ba02bab54366ef4a90eb9405e4d64a9e33c3fd82 (diff) | |
| download | b4-f7622a9c8d5ad88c199e4151d50510285b6c7aeb.tar.gz | |
Save to/cc headers as-is for tracking
If we clean the to/cc headers to get rid of all unicode escaping, we run
into a Python bug that is unable to properly parse addresses, e.g.:
In [5]: from email import utils
In [6]: utils.getaddresses(['foo <foo@bar.com>'])
Out[6]: [('foo', 'foo@bar.com')]
In [7]: utils.getaddresses(['Shuming [范書銘] <shumingf@realtek.com>'])
Out[7]:
[('', 'Shuming'),
('', ''),
('', '范書銘'),
('', ''),
('', 'shumingf@realtek.com')]
If we store the headers as-is from the original message, we are less
likely to run into this bug, as all non-ascii sequences should be
qp-escaped in the original headers:
=?big5?B?U2h1bWluZyBbrVOu0bvKXQ==?= <shumingf@realtek.com>
This doesn't fix the underlying bug in Python, but works around it.
Reported-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
| -rw-r--r-- | b4/__init__.py | 11 | ||||
| -rw-r--r-- | b4/mbox.py | 4 | ||||
| -rw-r--r-- | b4/pr.py | 4 |
3 files changed, 12 insertions, 7 deletions
diff --git a/b4/__init__.py b/b4/__init__.py index ee07f16..32b5c02 100644 --- a/b4/__init__.py +++ b/b4/__init__.py @@ -2375,11 +2375,16 @@ def git_get_toplevel(path=None): return topdir -def format_addrs(pairs): +def format_addrs(pairs, clean=True): addrs = set() for pair in pairs: - # Remove any quoted-printable header junk from the name - addrs.add(email.utils.formataddr((LoreMessage.clean_header(pair[0]), LoreMessage.clean_header(pair[1])))) + pair = list(pair) + if pair[0] == pair[1]: + pair[0] = '' + if clean: + # Remove any quoted-printable header junk from the name + pair[0] = LoreMessage.clean_header(pair[0]) + addrs.add(email.utils.formataddr(pair)) # noqa return ', '.join(addrs) @@ -294,8 +294,8 @@ def thanks_record_am(lser, cherrypick=None): 'subject': lmsg.full_subject, 'fromname': lmsg.fromname, 'fromemail': lmsg.fromemail, - 'to': b4.format_addrs(allto), - 'cc': b4.format_addrs(allcc), + 'to': b4.format_addrs(allto, clean=False), + 'cc': b4.format_addrs(allcc, clean=False), 'references': b4.LoreMessage.clean_header(lmsg.msg['References']), 'sentdate': b4.LoreMessage.clean_header(lmsg.msg['Date']), 'quote': b4.make_quote(lmsg.body, maxlines=5), @@ -225,8 +225,8 @@ def thanks_record_pr(lmsg): 'subject': lmsg.full_subject, 'fromname': lmsg.fromname, 'fromemail': lmsg.fromemail, - 'to': b4.format_addrs(allto), - 'cc': b4.format_addrs(allcc), + 'to': b4.format_addrs(allto, clean=False), + 'cc': b4.format_addrs(allcc, clean=False), 'references': b4.LoreMessage.clean_header(lmsg.msg['References']), 'remote': lmsg.pr_repo, 'ref': lmsg.pr_ref, |