[Spambayes-checkins] spambayes/spambayes Options.py, 1.56, 1.57 ProxyUI.py, 1.11, 1.12

Richie Hindle richiehindle at users.sourceforge.net
Mon Jul 7 15:00:05 EDT 2003


Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv5271

Modified Files:
	Options.py ProxyUI.py 
Log Message:
Added a new option, no_cache_bulk_ham:

Where message caching is enabled, this option suppresses caching
of messages which are classified as ham and marked as
'Precedence: bulk' or 'Precedence: list'.  If you subscribe to a
high-volume mailing list then your 'Review messages' page can be
overwhelmed with list messages, making training a pain.  Once you've
trained Spambayes on enough list traffic, you can use this option
to prevent that traffic showing up in 'Review messages'.


Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.56
retrieving revision 1.57
diff -C2 -d -r1.56 -r1.57
*** Options.py	24 Jun 2003 06:16:27 -0000	1.56
--- Options.py	7 Jul 2003 21:00:01 -0000	1.57
***************
*** 218,222 ****
       BOOLEAN, RESTORE),
    ),
!            
    # These options control how a message is categorized
    "Categorization" : (
--- 218,222 ----
       BOOLEAN, RESTORE),
    ),
! 
    # These options control how a message is categorized
    "Categorization" : (
***************
*** 258,262 ****
       REAL, RESTORE),
    ),
!  
    # These control various displays in class TestDriver.Driver, and
    # Tester.Test.
--- 258,262 ----
       REAL, RESTORE),
    ),
! 
    # These control various displays in class TestDriver.Driver, and
    # Tester.Test.
***************
*** 389,393 ****
       BOOLEAN, RESTORE),
    ),
!  
    "Classifier": (
      ("max_discriminators", "Maximum number of extreme words", 150,
--- 389,393 ----
       BOOLEAN, RESTORE),
    ),
! 
    "Classifier": (
      ("max_discriminators", "Maximum number of extreme words", 150,
***************
*** 416,420 ****
       worked best, so this does not seem to be corpus-dependent.""",
       REAL, RESTORE),
!  
      ("minimum_prob_strength", "Minimum probability strength", 0.1,
       """When scoring a message, ignore all words with
--- 416,420 ----
       worked best, so this does not seem to be corpus-dependent.""",
       REAL, RESTORE),
! 
      ("minimum_prob_strength", "Minimum probability strength", 0.1,
       """When scoring a message, ignore all words with
***************
*** 423,427 ****
       tests.  0.1 appeared to work well across all corpora.""",
       REAL, RESTORE),
!  
      ("use_gary_combining", "Use gary-combining", False,
       """The combining scheme currently detailed on the Robinson web page.
--- 423,427 ----
       tests.  0.1 appeared to work well across all corpora.""",
       REAL, RESTORE),
! 
      ("use_gary_combining", "Use gary-combining", False,
       """The combining scheme currently detailed on the Robinson web page.
***************
*** 431,435 ****
       spam distributions overlap.""",
       BOOLEAN, RESTORE),
!  
      ("use_chi_squared_combining", "Use chi-squared combining", True,
       """For vectors of random, uniformly distributed probabilities,
--- 431,435 ----
       spam distributions overlap.""",
       BOOLEAN, RESTORE),
! 
      ("use_chi_squared_combining", "Use chi-squared combining", True,
       """For vectors of random, uniformly distributed probabilities,
***************
*** 465,469 ****
      # this option will go away (and become the default), but people *with*
      # strong imbalance need to test it first.
!     
      ("experimental_ham_spam_imbalance_adjustment", "Compensate for unequal numbers of spam and ham", False,
       """If your training database has significantly (3 times) more ham than
--- 465,469 ----
      # this option will go away (and become the default), but people *with*
      # strong imbalance need to test it first.
! 
      ("experimental_ham_spam_imbalance_adjustment", "Compensate for unequal numbers of spam and ham", False,
       """If your training database has significantly (3 times) more ham than
***************
*** 478,487 ****
       BOOLEAN, RESTORE),
    ),
!  
    "Hammie": (
      ("debug_header", "Add debug header", False,
       """Enable debugging information in the header.""",
       BOOLEAN, RESTORE),
!  
      ("debug_header_name", "Debug header name", "X-Spambayes-Debug",
       """Name of a debugging header for spambayes hackers, showing the
--- 478,487 ----
       BOOLEAN, RESTORE),
    ),
! 
    "Hammie": (
      ("debug_header", "Add debug header", False,
       """Enable debugging information in the header.""",
       BOOLEAN, RESTORE),
! 
      ("debug_header_name", "Debug header name", "X-Spambayes-Debug",
       """Name of a debugging header for spambayes hackers, showing the
***************
*** 489,493 ****
       standard header.""",
       HEADER_NAME, RESTORE),
!  
      ("train_on_filter", "Train when filtering", False,
       """Train when filtering?  After filtering a message, hammie can then
--- 489,493 ----
       standard header.""",
       HEADER_NAME, RESTORE),
! 
      ("train_on_filter", "Train when filtering", False,
       """Train when filtering?  After filtering a message, hammie can then
***************
*** 561,565 ****
       that you wish.""",
       HEADER_VALUE, RESTORE),
!  
      ("header_ham_string", "Ham disposition name", "ham",
       """As for Spam Designation, but for emails classified as
--- 561,565 ----
       that you wish.""",
       HEADER_VALUE, RESTORE),
! 
      ("header_ham_string", "Ham disposition name", "ham",
       """As for Spam Designation, but for emails classified as
***************
*** 573,581 ****
       should always be the subject of training.""",
       HEADER_VALUE, RESTORE),
!  
      ("header_score_digits", "Accuracy of reported score", 2,
       """Accuracy of the score in the header in decimal digits""",
       INTEGER, RESTORE),
!     
      ("header_score_logarithm", "Augment score with logarithm", False,
       """Set this to "True", to augment scores of 1.00 or 0.00 by a
--- 573,581 ----
       should always be the subject of training.""",
       HEADER_VALUE, RESTORE),
! 
      ("header_score_digits", "Accuracy of reported score", 2,
       """Accuracy of the score in the header in decimal digits""",
       INTEGER, RESTORE),
! 
      ("header_score_logarithm", "Augment score with logarithm", False,
       """Set this to "True", to augment scores of 1.00 or 0.00 by a
***************
*** 671,675 ****
       """""",
       BOOLEAN, RESTORE),
!     
      ("cache_expiry_days", "Days before cached messages expire", 7,
       """""",
--- 671,675 ----
       """""",
       BOOLEAN, RESTORE),
! 
      ("cache_expiry_days", "Days before cached messages expire", 7,
       """""",
***************
*** 679,687 ****
       """""",
       PATH, DO_NOT_RESTORE),
!     
      ("ham_cache", "Ham cache directory", "pop3proxy-ham-cache",
       """""",
       PATH, DO_NOT_RESTORE),
!     
      ("unknown_cache", "Unknown cache directory", "pop3proxy-unknown-cache",
       """""",
--- 679,687 ----
       """""",
       PATH, DO_NOT_RESTORE),
! 
      ("ham_cache", "Ham cache directory", "pop3proxy-ham-cache",
       """""",
       PATH, DO_NOT_RESTORE),
! 
      ("unknown_cache", "Unknown cache directory", "pop3proxy-unknown-cache",
       """""",
***************
*** 717,720 ****
--- 717,730 ----
       BOOLEAN, RESTORE),
  
+     ("no_cache_bulk_ham", "Suppress caching of bulk ham", False,
+      """Where message caching is enabled, this option suppresses caching
+      of messages which are classified as ham and marked as
+      'Precedence: bulk' or 'Precedence: list'.  If you subscribe to a
+      high-volume mailing list then your 'Review messages' page can be
+      overwhelmed with list messages, making training a pain.  Once you've
+      trained Spambayes on enough list traffic, you can use this option
+      to prevent that traffic showing up in 'Review messages'.""",
+      BOOLEAN, RESTORE),
+ 
      ("add_mailid_to", "Add unique spambayes id", (),
       """If you wish to be able to find a specific message (via the 'find'
***************
*** 858,862 ****
       """""",
       IMAP_FOLDER, DO_NOT_RESTORE),
!     
      ("spam_folder", "Folder for suspected spam", "",
       """""",
--- 868,872 ----
       """""",
       IMAP_FOLDER, DO_NOT_RESTORE),
! 
      ("spam_folder", "Folder for suspected spam", "",
       """""",
***************
*** 899,903 ****
       IMAP_FOLDER, DO_NOT_RESTORE),
    ),
!  
    "globals" : (
      ("verbose", "Verbose", False,
--- 909,913 ----
       IMAP_FOLDER, DO_NOT_RESTORE),
    ),
! 
    "globals" : (
      ("verbose", "Verbose", False,

Index: ProxyUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ProxyUI.py,v
retrieving revision 1.11
retrieving revision 1.12
diff -C2 -d -r1.11 -r1.12
*** ProxyUI.py	26 May 2003 00:00:53 -0000	1.11
--- ProxyUI.py	7 Jul 2003 21:00:02 -0000	1.12
***************
*** 84,87 ****
--- 84,88 ----
      ('pop3proxy',           'listen_ports'),
      ('pop3proxy',           'cache_messages'),
+     ('pop3proxy',           'no_cache_bulk_ham'),
      ('html_ui',             'display_to'),
      ('Header Options',      None),
***************
*** 489,493 ****
          # we have a few extra checks
          errmsg = UserInterface.UserInterface.verifyInput(self, parms)
!         
          # check for equal number of pop3servers and ports
          slist = list(parms['pop3proxy_remote_servers'])
--- 490,494 ----
          # we have a few extra checks
          errmsg = UserInterface.UserInterface.verifyInput(self, parms)
! 
          # check for equal number of pop3servers and ports
          slist = list(parms['pop3proxy_remote_servers'])





More information about the Spambayes-checkins mailing list