On Wed, Nov 29, 2006, Marc Perkel wrote: > I don't think it's off topic at all. That's very interesting. I'm going > to experiment with your list. If you have a longer list I'd be > interested in that too.
Sure. <http://tehran.lain.pl/stuff/sa/w_popular.cf> Masscheck results: <http://tehran.lain.pl/stuff/sa/w_popular.txt> And thingees I use for generating the list: A patch for mimedump at <http://tehran.lain.pl/stuff/mimedump.diff> A procmailrc: <http://tehran.lain.pl/stuff/procmailrc-spamtrap> A script that does the thing: <http://tehran.lain.pl/stuff/spamwords> Although the method is very crude, it produces virtually no false positives. Check the masscheck results! It requires no maintenance, neither from lusers nor from me. The maintenance was a hassle big enough for me not to use Bayes. If I only had a decent amount of spam, I could do wonders with this little thingee. -- ## List details at http://www.exim.org/mailman/listinfo/exim-users ## Exim details at http://www.exim.org/ ## Please use the Wiki with this list - http://www.exim.org/eximwiki/
