[plug] OT: SPAM

[Cameron Patrick]

Craig Ringer wrote:

| It's worth using it to check the effectiveness of your filters, but
| I wouldn't recommend using it with sa-learn unless you plan to use
| MimeDefang or similar.

FWIW I'd say something similar about the sample that I posted.  In
particular it contains X-Security: headers created by the virus filter
that I use (bizarrely named html-trap.procmail - can't remember where
I got it from) and Received: headers which will be present in all of
the spam I gave you but none of the spam (or real mail) that you will
ever get.

The whole point of a bayesian filter is that you train it on /your/
mail rather than someone else's.

Cameron.