[Spambayes-checkins] spambayes/Outlook2000 addin.py,1.31,1.32 msgstore.py,1.28,1.29

[Tim Peters]

Update of /cvsroot/spambayes/spambayes/Outlook2000
In directory usw-pr-cvs1:/tmp/cvs-serv32322/Outlook2000

Modified Files:
	addin.py msgstore.py 
Log Message:
GetEmailPackageObject():  Put pack code to strip Content-Type:  turns out
there was a superb reason to do this after all, just not the one I
thought there was <wink>.


Index: addin.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/Outlook2000/addin.py,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** addin.py	12 Nov 2002 22:56:24 -0000	1.31
--- addin.py	14 Nov 2002 01:16:11 -0000	1.32
***************
*** 244,248 ****
      push("<h2>Message Stream:</h2><br>")
      push("<PRE>\n")
!     msg = msgstore_message.GetEmailPackageObject()
      push(escape(msg.as_string(), True))
      push("</PRE>\n")
--- 244,248 ----
      push("<h2>Message Stream:</h2><br>")
      push("<PRE>\n")
!     msg = msgstore_message.GetEmailPackageObject(strip_content_type=False)
      push(escape(msg.as_string(), True))
      push("</PRE>\n")

Index: msgstore.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/Outlook2000/msgstore.py,v
retrieving revision 1.28
retrieving revision 1.29
diff -C2 -d -r1.28 -r1.29
*** msgstore.py	13 Nov 2002 18:30:01 -0000	1.28
--- msgstore.py	14 Nov 2002 01:16:11 -0000	1.29
***************
*** 430,434 ****
              self.mapi_object = self.msgstore._OpenEntry(self.id)
  
!     def GetEmailPackageObject(self):
          import email
          text = self._GetMessageText()
--- 430,451 ----
              self.mapi_object = self.msgstore._OpenEntry(self.id)
  
!     def GetEmailPackageObject(self, strip_content_type=True):
!         # Return an email.Message object.
!         # strip_content_type is a hack, and should be left True unless you're
!         # trying to display all the headers for diagnostic purposes.  If we
!         # figure out something better to do, it should go away entirely.
!         # The problem:  suppose a msg is multipart/alternative, with
!         # text/plain and text/html sections.  The latter MIME decorations
!         # are plain missing in what _GetMessageText() returns.  If we leave
!         # the multipart/alternative in the headers anyway, the email
!         # package's "lax parsing" won't complain about not finding any
!         # sections, but since the type *is* multipart/alternative then
!         # anyway, the tokenizer finds no text/* parts at all to tokenize.
!         # As a result, only the headers get tokenized.  By stripping
!         # Content-Type from the headers (if present), the email pkg
!         # considers the body to be text/plain (the default), and so it
!         # does get tokenized.
!         # Short course:  we either have to synthesize non-insane MIME
!         # structure, or eliminate all evidence of original MIME structure.
          import email
          text = self._GetMessageText()
***************
*** 438,441 ****
--- 455,463 ----
              print "FAILED to create email.message from: ", `text`
              raise
+ 
+         if strip_content_type:
+             if msg.has_key('content-type'):
+                 del msg['content-type']
+ 
          return msg