summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
authorKali Kaneko <kali@leap.se>2013-11-05 11:05:25 -0200
committerKali Kaneko <kali@leap.se>2013-11-05 11:05:25 -0200
commita43e0715274d6c480c8f126953ada590d371caa1 (patch)
tree6bbba5b6b92b5531d1e31e3b9df255fccf20aa04 /src
parent2cda4e40f022a6f49a338b49067e56276121c78e (diff)
parent5be557db1e5eff7fec71e1c65b0cbb4cb54c2ba6 (diff)
Merge tag '0.3.5' into debian
Tag leap.common version 0.3.5
Diffstat (limited to 'src')
-rw-r--r--src/leap/common/mail.py50
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