New new script to train bogofilter

[Boris 'pi' Piwinger]

Hi!

Here is the new version of my script. New options allow for
more precise information and for forcing to run until no
error is left.

I started from scratch. Six runs were needed to go down to
zero errors. The program read 22532 ham mails and 15217 spam
mails. The database ended with this:
                       spam   good
.MSG_COUNT              329    283
% of read               2.2    1.3

It turns out, that not a single message was used twice in
training (by accident, but it might cool down worries;-).

I am curious to hear why this is not great and why I should
see problems soon.

pi
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: build-bogofilter-database.pl
URL: <http://www.bogofilter.org/pipermail/bogofilter/attachments/20030704/93523f6d/attachment.pl>