Patch #1449244: Support Unicode strings in

loewis · loewis · commit bdd0f39de559 · 2007-03-13T10:24:00.000Z
email.message.Message.{set_charset,get_content_charset}.
Will backport.
diff --git a/Lib/email/message.py b/Lib/email/message.py
@@ -238,7 +238,7 @@ def set_charset(self, charset):
             self.del_param('charset')
             self._charset = None
             return
-        if isinstance(charset, str):
+        if isinstance(charset, basestring):
             charset = email.charset.Charset(charset)
         if not isinstance(charset, email.charset.Charset):
             raise TypeError(charset)
@@ -756,7 +756,9 @@ def get_content_charset(self, failobj=None):
                 charset = charset[2]
         # charset character must be in us-ascii range
         try:
-            charset = unicode(charset, 'us-ascii').encode('us-ascii')
+            if isinstance(charset, str):
+                charset = unicode(charset, 'us-ascii')
+            charset = charset.encode('us-ascii')
         except UnicodeError:
             return failobj
         # RFC 2046, $4.1.2 says charsets are not case sensitive
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
@@ -502,6 +502,13 @@ def test_broken_base64_payload(self):
         msg.set_payload(x)
         self.assertEqual(msg.get_payload(decode=True), x)
 
+    def test_get_content_charset(self):
+        msg = Message()
+        msg.set_charset('us-ascii')
+        self.assertEqual('us-ascii', msg.get_content_charset())
+        msg.set_charset(u'us-ascii')
+        self.assertEqual('us-ascii', msg.get_content_charset())
+
 
 
 # Test the email.Encoders module
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -168,6 +168,9 @@ Core and builtins
 Library
 -------
 
+- Patch #1449244: Support Unicode strings in
+  email.message.Message.{set_charset,get_content_charset}.
+
 - Patch #1542681: add entries for "with", "as" and "CONTEXTMANAGERS" to
   pydoc's help keywords.
 
