[SAtalk] Testing and weighting rules against corpus of spam/non-spam

they running these tests? 2. I would like to run my entire rulebase against a ham/spam corpus, and arrive at statistically "best" weighting of rules. How is this done? Cordially, Eric hart ehart [nospam] npi.net === All NPI email scanned for spam and viruses by SpamRejector(tm). SpamRejector.net ===

[SAtalk] More complex rules

t's mail name ("ehart" for example). It would then test the subject field to see if this stored mail name is contained in the subject. Any help appreciated! Cordially, Eric -- Eric Hart Network Performance, Inc. (NPI) ehart

re[2]: [SAtalk] More complex rules

question is, *can* I use storage here? How is it done? As to the eval rules, I've seen some mention of them elsewhere, and will give it a try. Thanks again, Eric > At 01:48 AM 8/18/03 -0400, Eric Hart wrote: >1. I want to find a string that matches on the regular >expression /

[SAtalk] Information on writing rules

RL IF expressions in SA rules. CF processing algorithm Thanks! - Eric -- Eric Hart Network Performance, Inc. (NPI) ehart <&

re[2]: [SAtalk] Information on writing rules

> Good afternoon, Eric, Hi Eric! On Mon, 21 Jul 2003, Eric Hart wrote: > I've been writing custom SA rules for awhile, and have a pretty good > grasp now on regular expresssions and BODY and HEADER rules. Search as > I might, I have not found sources of information on advan