[Spambayes-checkins] spambayes pop3proxy.py,1.90,1.91

[Tony Meyer]

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv2977

Modified Files:
	pop3proxy.py 
Log Message:
Fix some old option names.

Change notate_to and notate_subject options to tuples - if empty, do nothing
(like old False), otherwise if classification is in option value, then mutate the
header (old True meant only spam messages).

Add no_cache_large_messages option.  If messages are bigger than this, don't
cache them (to avoid caching messages with massive attachments that are
already correctly classified).

Make pop3proxy and hammie use the storage.open_storage function.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.90
retrieving revision 1.91
diff -C2 -d -r1.90 -r1.91
*** pop3proxy.py	18 Aug 2003 04:52:53 -0000	1.90
--- pop3proxy.py	25 Aug 2003 09:00:33 -0000	1.91
***************
*** 447,453 ****
                       len(args) == 2 and args[1] == '99999999')):
                      cls = msg.GetClassification()
!                     if cls == options["Hammie", "header_ham_string"]:
                          state.numHams += 1
!                     elif cls == options["Hammie", "header_spam_string"]:
                          state.numSpams += 1
                      else:
--- 447,453 ----
                       len(args) == 2 and args[1] == '99999999')):
                      cls = msg.GetClassification()
!                     if cls == options["Headers", "header_ham_string"]:
                          state.numHams += 1
!                     elif cls == options["Headers", "header_spam_string"]:
                          state.numSpams += 1
                      else:
***************
*** 457,469 ****
                      # "Precedence: list" ham if the options say so.
                      isSuppressedBulkHam = \
!                         (cls == options["Hammie", "header_ham_string"] and
                           options["pop3proxy", "no_cache_bulk_ham"] and
                           msg.get('precedence') in ['bulk', 'list'])
  
                      # Cache the message.  Don't pollute the cache with test
                      # messages or suppressed bulk ham.
                      if (not state.isTest and
                          options["pop3proxy", "cache_messages"] and
!                         not isSuppressedBulkHam):
                          # Write the message into the Unknown cache.
                          message = state.unknownCorpus.makeMessage(msg.getId())
--- 457,475 ----
                      # "Precedence: list" ham if the options say so.
                      isSuppressedBulkHam = \
!                         (cls == options["Headers", "header_ham_string"] and
                           options["pop3proxy", "no_cache_bulk_ham"] and
                           msg.get('precedence') in ['bulk', 'list'])
  
+                     # Suppress large messages if the options say so.
+                     size_limit = options["pop3proxy",
+                                          "no_cache_large_messages"]
+                     isTooBig = size_limit > 0 and \
+                                len(messageText) > size_limit
+ 
                      # Cache the message.  Don't pollute the cache with test
                      # messages or suppressed bulk ham.
                      if (not state.isTest and
                          options["pop3proxy", "cache_messages"] and
!                         not isSuppressedBulkHam and not isTooBig):
                          # Write the message into the Unknown cache.
                          message = state.unknownCorpus.makeMessage(msg.getId())
***************
*** 610,629 ****
          filename = options["Storage", "persistent_storage_file"]
          filename = os.path.expanduser(filename)
!         if self.useDB:
!             if '::' in filename:
!                 sql_types = {"pgsql" : storage.PGClassifier,
!                              "mysql" : storage.mySQLClassifier,
!                              }
!                 sql_type, rest = filename.split('::', 1)
!                 if sql_types.has_key(sql_type.lower()):
!                     self.bayes = sql_types[sql_type.lower()](filename)
!                 else:
!                     # yikes! raise some sort of NoSuchClassifierError
!                     pass
!             else:
!                 self.bayes = storage.DBDictClassifier(filename)
!         else:
!             self.bayes = storage.PickledClassifier(filename)
!         print "Done."
  
          # Don't set up the caches and training objects when running the self-test,
--- 616,620 ----
          filename = options["Storage", "persistent_storage_file"]
          filename = os.path.expanduser(filename)
!         self.bayes = storage.open_storage(filename, self.useDB)
  
          # Don't set up the caches and training objects when running the self-test,
***************
*** 759,763 ****
  def stop(state):
      state.bayes.store()
!     # should we be calling socket.shutdown(2) and close() for each
      # BayesProxy object?
  
--- 750,754 ----
  def stop(state):
      state.bayes.store()
!     # should we be calling socket.shutdown(2) and close_when_done() for each
      # BayesProxy object?