From: W. Trevor King <wking@tremily.us>
Date: Fri, 7 Nov 2014 07:32:03 +0000 (-0800)
Subject: ssoma-mda: Handle Subject:s that aren't RFC-2047-encoded too
X-Git-Url: http://git.tremily.us/?a=commitdiff_plain;h=22ae96b272be1e0337859286768833a0b073ea75;p=ssoma-mda.git

ssoma-mda: Handle Subject:s that aren't RFC-2047-encoded too

If the string is not RFC-2047 encoded, the charset from decode_header
is None:

  >>> import email.header
  >>> email.header.decode_header('hello')
  [('hello', None)]

so str(decoded, charset) will fail with:

  TypeError: str() argument 2 must be str, not None

Avoid that by checking charset before attempting to decode with
charset.  Since that's a bit awkward, pull it out into its own
_decode_header function.

The Simonsen example is from RFC 2047 [1].

[1]: http://tools.ietf.org/html/rfc2047#section-8
---

diff --git a/ssoma-mda b/ssoma-mda
index abae180..f02b1b1 100755
--- a/ssoma-mda
+++ b/ssoma-mda
@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# -*- coding: utf-8 -*-
 # Copyright (C) 2013, Eric Wong <normalperson@yhbt.net> and all contributors
 # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
 # Try to keep this small as it may be invoked frequently for each message
@@ -219,14 +220,32 @@ def message_id_path(message_id):
     return _os_path.join(hash[:2], hash[2:])
 
 
+def _decode_header(string):
+    """Wrap email.header.decode_header to assemble a string.
+
+    >>> _decode_header(string='hello')
+    'hello'
+    >>> _decode_header(string='=?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?=')
+    'Keld Jørn Simonsen'
+    """
+    chunks = []
+    for decoded, charset in _email_header.decode_header(string):
+        if charset:
+            decoded = str(decoded, charset)
+        chunks.append(decoded)
+    return ''.join(chunks)
+
+
 def get_commit_message(message):
-    """Unwrap and decode the message subject for use as a commit message."""
+    r"""Unwrap and decode the message subject for use as a commit message.
+
+    >>> get_commit_message(
+    ...     message={'Subject': '=?ISO-8859-1?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?=\n\t=?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?='})
+    'If you can read this you understand the example.'
+    """
     commit_message = message.get('Subject', '<no subject>')
     commit_message = _FOLDING_WHITESPACE_REGEX.sub(' ', commit_message)
-    commit_message = ''.join(
-        str(decoded, charset) for decoded, charset
-        in _email_header.decode_header(commit_message))
-    return commit_message
+    return _decode_header(string=commit_message)
 
 
 def get_author(message):