[prev in list] [next in list] [prev in thread] [next in thread] 

List:       spamassassin-devel
Subject:    [Bug 5114]  New: increamental learning
From:       bugzilla-daemon () issues ! apache ! org
Date:       2006-09-30 12:08:08
Message-ID: 5114.dev () spamassassin ! apache ! org
[Download RAW message or body]

http://issues.apache.org/SpamAssassin/show_bug.cgi?id=5114

           Summary: increamental learning
           Product: Spamassassin
           Version: 3.0.4
          Platform: All
        OS/Version: All
            Status: NEW
          Severity: enhancement
          Priority: P5
         Component: Learner
        AssignedTo: dev@spamassassin.apache.org
        ReportedBy: jerome.bouat@wanadoo.fr


I don't know really how it actually works.

When learning a message as SPAM, does spamassassin check if the message can not
be already detected by current rules ?

If not, here is what currently occur when processing a list of SPAM:
1. The first message is learned.
2. The second message can be detected because of the later learning. Instead it
is learned unnecessarily. Thus the learning database increases unnecessarily.
3. and so on

If a message could be tested for catogorizing before learning it, then it could
decrease the learning database size and increase the categorization efficiency.



------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.
[prev in list] [next in list] [prev in thread] [next in thread]