[Spambayes] Feedback from an ecstatic user

[Tony Meyer]

[Kenny]
> Differences in the counts can also be caused by manual 
> training.  13126 is the number of spams *trained* while 7131 
> is the number of spams *processed* by SpamBayes, so they're 
> counting different things.  If you've ever used the "Train on 
> a message, mbox file or dbx file" option to train on 
> additional spam messages, those messages will be included in 
> the trained count but not in the processed count.

I had forgotten/not realised that - thanks!  I think this is not as it
should be, though (they should be counted somewhere, even if it's in a
separate count), so I'll fix this for 1.1.

=Tony Meyer