merge from HEAD

Author: Richard Jones

CHANGES.txt

@@ -10,6 +10,7 @@ Fixed:
 - Fix references to the old * Registration Permissions
 - Fix missing merge of fix to sf bug 1177057
 - Fix RDBMS indexer indexing UTF-8 words that encode to > 30 chars
+- Handle invalidly-specified charsets in incoming email
 
 
 2005-07-18 0.8.4

roundup/mailgw.py

@@ -72,7 +72,7 @@ class node. Any parts of other types are each stored in separate files
 an exception, the original message is bounced back to the sender with the
 explanatory message given in the exception.
 
-$Id: mailgw.py,v 1.159.2.7 2005-09-26 02:14:07 richard Exp $
+$Id: mailgw.py,v 1.159.2.8 2005-09-28 05:49:23 richard Exp $
 """
 __docformat__ = 'restructuredtext'
 
@@ -223,8 +223,9 @@ def getbody(self):
         # Encode message to unicode
         charset = rfc2822.unaliasCharset(self.getparam("charset"))
         if charset:
-            # Do conversion only if charset specified
-            edata = unicode(data, charset).encode('utf-8')
+            # Do conversion only if charset specified - handle
+            # badly-specified charsets
+            edata = unicode(data, charset, 'replace').encode('utf-8')
             # Convert from dos eol to unix
             edata = edata.replace('\r\n', '\n')
         else: