BAYES_99 on all mail

[A J Thew <aj...@gmail.com>]

As reported in another thread and also in open bugs

http://issues.apache.org/SpamAssassin/show_bug.cgi?id=4787

sa-learn --dump magic gives

0.000          0          3          0  non-token data: bayes db version
0.000          0    2095462          0  non-token data: nspam
0.000          0    1360667          0  non-token data: nham
0.000          0     995727          0  non-token data: ntokens
0.000          0 1195121816          0  non-token data: oldest atime
0.000          0 1195831225          0  non-token data: newest atime
0.000          0 1195831080          0  non-token data: last journal sync atime
0.000          0 1195362090          0  non-token data: last expiry atime
0.000          0      76594          0  non-token data: last expire atime delta
0.000          0     750937          0  non-token data: last expire
reduction count

This runs on a machine that mainly gets spam which I realise will not help...

Thanks

A Thew

Re: BAYES_99 on all mail

[Dave Koontz <dk...@mbc.edu>]

Do you have Auto Learning enabled?  That helps balance the number of ham
and spam messages your system learns.  My experience has been that the
Bayes database does this eventually if it's feed far more spam than
ham.  If your spam level is very high, you may want to look at both
auto-learn as well as having your mta re-feed good messages back to
sa-learn.  You may need a cron job to remove the bayes_seen DB to
accomplish this.

Either way, you likely will need to remove the old bayes db and start
fresh.  The tips above just help it to maintain itself properly with a
clean DB.

A J Thew wrote:
> As reported in another thread and also in open bugs
>
> http://issues.apache.org/SpamAssassin/show_bug.cgi?id=4787
>
> sa-learn --dump magic gives
>
> 0.000          0          3          0  non-token data: bayes db version
> 0.000          0    2095462          0  non-token data: nspam
> 0.000          0    1360667          0  non-token data: nham
> 0.000          0     995727          0  non-token data: ntokens
> 0.000          0 1195121816          0  non-token data: oldest atime
> 0.000          0 1195831225          0  non-token data: newest atime
> 0.000          0 1195831080          0  non-token data: last journal sync atime
> 0.000          0 1195362090          0  non-token data: last expiry atime
> 0.000          0      76594          0  non-token data: last expire atime delta
> 0.000          0     750937          0  non-token data: last expire
> reduction count
>
> This runs on a machine that mainly gets spam which I realise will not help...
>
> Thanks
>
> A Thew
>