[EMAIL PROTECTED] said: :-Run foo-filter first in the chain, and everything that gets past it :-(i.e, not-likely to be spam) will then hit TMDA.
Yes, that would work. The reason I wanted to do in in the middle of the TMDA pipeline is that the (potentially expensive) classification operation could be avoided in all but the relatively few cases where confirmation was indicated (about 10% of the time for me). The whitelists and blacklists handle the simple cases, presumably cheaply. Another nice thing is that the entire process would then be integrated with TMDA and you get to use things like TMDA-pending, rather than having Yet Another Tool involved. Of course the filter-then-TMDA versus TMDA-then-filter issue depends to a certain extent on the relative expense of filter versus TMDA, and for all I know bayesian filtering might be faster than TMDA... If I can find the time I'll hack it both ways and report. Thanks! _____________________________________________ tmda-users mailing list ([EMAIL PROTECTED]) http://tmda.net/lists/listinfo/tmda-users
