# HG changeset patch # User Julien Cristau # Date 2016-03-03 17:34:19 # Node ID 8286f551b7ee485a11b75ee0efd6d85c303667c2 # Parent c100dbd593e2a78fd065aa975a43d0c9ce263dcb patch: when importing from email, RFC2047-decode From/Subject headers Reported at https://bugs.debian.org/737498 diff --git a/mercurial/mail.py b/mercurial/mail.py --- a/mercurial/mail.py +++ b/mercurial/mail.py @@ -332,3 +332,21 @@ def mimeencode(ui, s, charsets=None, dis if not display: s, cs = _encode(ui, s, charsets) return mimetextqp(s, 'plain', cs) + +def headdecode(s): + '''Decodes RFC-2047 header''' + uparts = [] + for part, charset in email.Header.decode_header(s): + if charset is not None: + try: + uparts.append(part.decode(charset)) + continue + except UnicodeDecodeError: + pass + try: + uparts.append(part.decode('UTF-8')) + continue + except UnicodeDecodeError: + pass + uparts.append(part.decode('ISO-8859-1')) + return encoding.tolocal(u' '.join(uparts).encode('UTF-8')) diff --git a/mercurial/patch.py b/mercurial/patch.py --- a/mercurial/patch.py +++ b/mercurial/patch.py @@ -31,6 +31,7 @@ from . import ( diffhelpers, encoding, error, + mail, mdiff, pathutil, scmutil, @@ -210,8 +211,8 @@ def extract(ui, fileobj): try: msg = email.Parser.Parser().parse(fileobj) - subject = msg['Subject'] - data['user'] = msg['From'] + subject = msg['Subject'] and mail.headdecode(msg['Subject']) + data['user'] = msg['From'] and mail.headdecode(msg['From']) if not subject and not data['user']: # Not an email, restore parsed headers if any subject = '\n'.join(': '.join(h) for h in msg.items()) + '\n' diff --git a/tests/test-import-git.t b/tests/test-import-git.t --- a/tests/test-import-git.t +++ b/tests/test-import-git.t @@ -822,4 +822,27 @@ Test corner case involving copies and mu > EOF applying patch from stdin +Test email metadata + + $ hg revert -qa + $ hg --encoding utf-8 import - < From: =?UTF-8?q?Rapha=C3=ABl=20Hertzog?= + > Subject: [PATCH] =?UTF-8?q?=C5=A7=E2=82=AC=C3=9F=E1=B9=AA?= + > + > diff --git a/a b/a + > --- a/a + > +++ b/a + > @@ -1,1 +1,2 @@ + > a + > +a + > EOF + applying patch from stdin + $ hg --encoding utf-8 log -r . + changeset: 2:* (glob) + tag: tip + user: Rapha\xc3\xabl Hertzog (esc) + date: * (glob) + summary: \xc5\xa7\xe2\x82\xac\xc3\x9f\xe1\xb9\xaa (esc) + + $ cd ..