patch: when importing from email, RFC2047-decode From/Subject headers
authorJulien Cristau <julien.cristau@logilab.fr>
Thu, 03 Mar 2016 18:34:19 +0100
changeset 28341 8286f551b7ee
parent 28340 c100dbd593e2
child 28342 bd05d38a1002
patch: when importing from email, RFC2047-decode From/Subject headers Reported at https://bugs.debian.org/737498
mercurial/mail.py
mercurial/patch.py
tests/test-import-git.t
--- a/mercurial/mail.py	Wed Mar 02 22:39:03 2016 +0000
+++ b/mercurial/mail.py	Thu Mar 03 18:34:19 2016 +0100
@@ -332,3 +332,21 @@
     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'))
--- a/mercurial/patch.py	Wed Mar 02 22:39:03 2016 +0000
+++ b/mercurial/patch.py	Thu Mar 03 18:34:19 2016 +0100
@@ -31,6 +31,7 @@
     diffhelpers,
     encoding,
     error,
+    mail,
     mdiff,
     pathutil,
     scmutil,
@@ -210,8 +211,8 @@
     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'
--- a/tests/test-import-git.t	Wed Mar 02 22:39:03 2016 +0000
+++ b/tests/test-import-git.t	Thu Mar 03 18:34:19 2016 +0100
@@ -822,4 +822,27 @@
   > EOF
   applying patch from stdin
 
+Test email metadata
+
+  $ hg revert -qa
+  $ hg --encoding utf-8 import - <<EOF
+  > From: =?UTF-8?q?Rapha=C3=ABl=20Hertzog?= <hertzog@debian.org>
+  > 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 <hertzog@debian.org> (esc)
+  date:        * (glob)
+  summary:     \xc5\xa7\xe2\x82\xac\xc3\x9f\xe1\xb9\xaa (esc)
+  
+
   $ cd ..