| -----Original Message----- | From: Theo Van Dinter [mailto:[EMAIL PROTECTED] | Sent: Thursday, October 02, 2003 9:13 AM | | Just to check: are you learning to journal, and did you sync | the journal before "dump magic"?
I'm not sure I understand your question. If you are asking if I tried a --rebuild. Yes. It had no effect. The exact process I did was: 1. Installed SA 2.60. with no existing Bayes database. 2. copied over my spam and ham mbox files 3. Ran sa-learn --ham --mbox --showdots /path/ham and sa-learn --spam --mbox --showdots /path/spam 4. I got the first set of results. 5. ran sa-learn --forget /path/ham and sa-learn --forget /path/spam. 6. Redid step 3 and got the second set of results. Last night I ran a new spam corpus, using the sa-learn -D --spam --mbox /path/newspam Now my magic looks like (after running a sa-learn --rebuild to make sure) 0.000 0 2 0 non-token data: bayes db version 0.000 0 0 0 non-token data: nspam 0.000 0 0 0 non-token data: nham 0.000 0 0 0 non-token data: ntokens 0.000 0 0 0 non-token data: oldest atime 0.000 0 1065039199 0 non-token data: newest atime 0.000 0 1065130077 0 non-token data: last journal sync atime 0.000 0 0 0 non-token data: last expiry atime 0.000 0 0 0 non-token data: last expire atime delta 0.000 0 0 0 non-token data: last expire reduction count I just don't know what the problem is. I think I'm going to delete the database and start over. It takes forever to forget and learn the spam. <<Dan>> ------------------------------------------------------- This sf.net email is sponsored by:ThinkGeek Welcome to geek heaven. http://thinkgeek.com/sf _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
