diff options
author | Ivan Alejandro <ivanalejandro0@gmail.com> | 2013-10-31 12:38:33 -0300 |
---|---|---|
committer | Ivan Alejandro <ivanalejandro0@gmail.com> | 2013-10-31 12:38:33 -0300 |
commit | 2f095a949d5f96f6967e14ff5f0a60396edef1f7 (patch) | |
tree | e7d8755fd99c251d60312e523bc98dedf5ea0325 /src/leap/common | |
parent | ae7932016656c52439fd6cdddbd1d3412202cef2 (diff) | |
parent | 6c0541c3b8827eb9a5be9ae46d58925b399afc09 (diff) |
Merge remote-tracking branch 'chiiph/bug/refactor_mail_utils' into develop
Diffstat (limited to 'src/leap/common')
-rw-r--r-- | src/leap/common/mail.py | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/src/leap/common/mail.py b/src/leap/common/mail.py new file mode 100644 index 0000000..2f2146d --- /dev/null +++ b/src/leap/common/mail.py @@ -0,0 +1,50 @@ +# -*- coding: utf-8 -*- +# mail.py +# Copyright (C) 2013 LEAP +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +""" +Utility functions for email. +""" +import email +import re + +from leap.common.check import leap_assert_type + + +def get_email_charset(content, default="utf-8"): + """ + Mini parser to retrieve the charset of an email. + + :param content: mail contents + :type content: unicode + :param default: optional default value for encoding + :type default: str or None + + :returns: the charset as parsed from the contents + :rtype: str + """ + leap_assert_type(content, unicode) + + charset = default + try: + em = email.message_from_string(content.encode("utf-8", "replace")) + # Miniparser for: Content-Type: <something>; charset=<charset> + charset_re = r'''charset=(?P<charset>[\w|\d|-]*)''' + charset = re.findall(charset_re, em["Content-Type"])[0] + if charset is None or len(charset) == 0: + charset = default + except Exception: + pass + return charset |