At Sat Aug 16 14:23:34 2003, Paul Hutchings wrote: > At present each message in the mbox file has all the headers listed, and all > the spamassassin headers that were added when it first passed through - I'm > cautious that I might be doing something dumb and training it that my own > mail server sends spam etc..
sa-learn will strip off SA's markup automatically, so you don't need to worry about that. However, the Bayesian functionality works best when it's trained on broadly similar quantities of spam and ham. If all that mail has come via your mail server, then the Bayesian code should work out that the headers added by your server is not usable as a ham/spam discriminant (and hence won't use it). At least, that's my understanding. Martin -- Martin Radford | "Only wimps use tape backup: _real_ [EMAIL PROTECTED] | men just upload their important stuff -o) Registered Linux user #9257 | on ftp and let the rest of the world /\\ - see http://counter.li.org | mirror it ;)" - Linus Torvalds _\_V ------------------------------------------------------- This SF.Net email sponsored by: Free pre-built ASP.NET sites including Data Reports, E-commerce, Portals, and Forums are available now. Download today and enter to win an XBOX or Visual Studio .NET. http://aspnet.click-url.com/go/psa00100003ave/direct;at.aspnet_072303_01/01 _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
