#!/bin/bash
#Copyright 2003 William Stearns <wstearns@pobox.com>
#GPL'd.
#Is razor-report enough, or do we need to do some equivalent of spamassassin -r -d -a?

if [ -z "$HOME" ]; then
	HOME="/home/wstearns/"
fi

LOCKFILE=$HOME/learnspam.lock
[ -f "$LOCKFILE" ] && exit 0
trap "rm -f $LOCKFILE" EXIT
touch $LOCKFILE
renice +15 -p $$ >/dev/null 2>&1


#User settings:
#wildcards OK, relative dirs, OK, absolute dirs aren't.
SpamFolders="verified-spam"

#wildcards OK, relative dirs, OK, absolute dirs aren't.
HamFolders="verified-ham"

#The following are the machines (and optional usernames) to which we'll
#ssh to learn these spams into their respective bayesian databases. 
#The user we ssh under needs to have ssh set up, and needs write
#privileges to the (we assume shared) bayesian and whitelist databases.
ReportServers="localhost spamtrap@somemachine spam@somebox.domain.org"

MailDir="$HOME/mail/"
ArchiveDir="$HOME/mail/archives/"
#End of user settings

if [ -f $HOME/agent ]; then
	. $HOME/agent
	export SSH_AUTH_SOCK SSH_AGENT_PID SSH_ASKPASS
else
	echo SSH agent info not in $HOME/agent, please place there.
fi
export LC_ALL=C

cd "$MailDir"	#So wildcards work

for OneFolder in $SpamFolders ; do
	if [ -f "$MailDir/$OneFolder" ]; then
		echo "Reporting $MailDir/$OneFolder to the razor database."
		razor-report "$MailDir/$OneFolder"
		#I used to have pyzor grab the mailbox directly (with --mbox),
		#but it crashes on some messages, so any following ones never
		#get reported.  This uses more forks, but gets almost all reported.
		formail -s pyzor report <"$MailDir/$OneFolder"
		formail -s dccproc -t many -o /dev/null <"$MailDir/$OneFolder"
	fi
done

for Server in $ReportServers ; do
	for OneFolder in $HamFolders ; do
		if [ -f "$MailDir/$OneFolder" ]; then
			echo "========== $Server: HHHH $OneFolder"
			#sa-learn --no-rebuild --showdots --mbox --ham "$MailDir/$OneFolder"
			cat "$MailDir/$OneFolder" | ssh -o BatchMode=yes -o Compression=yes $Server \
			 'export TF=`mktemp -q /tmp/ham.XXXXXX </dev/null` && cat >>$TF && nice sa-learn --no-rebuild --showdots --mbox --ham $TF 2>&1 && [ -f $TF ] && rm -f $TF && echo Successful.' 2>/dev/null
		fi
	done

	for OneFolder in $SpamFolders ; do
		if [ -f "$MailDir/$OneFolder" ]; then
			echo "========== $Server: SSSS $OneFolder"
			#sa-learn --no-rebuild --showdots --mbox --spam "$MailDir/$OneFolder"
			cat "$MailDir/$OneFolder" | ssh -o BatchMode=yes -o Compression=yes $Server \
			 'export TF=`mktemp -q /tmp/spam.XXXXXX </dev/null` && cat >>$TF && nice sa-learn --no-rebuild --showdots --mbox --spam $TF 2>&1 && [ -f $TF ] && rm -f $TF && echo Successful.' 2>/dev/null
		fi
	done

	echo "========== $Server: rebuild"
	#sa-learn --rebuild
	ssh -o BatchMode=yes $Server 'sa-learn --rebuild 2>&1' 2>/dev/null
done

DateStamp=`date +%Y%m%d%H%M`
for OneFolder in $SpamFolders $HamFolders ; do
	if [ -f "$MailDir/$OneFolder" ]; then
		echo "Saving to $OneFolder.$DateStamp"
		mv "$MailDir/$OneFolder" "$ArchiveDir/$OneFolder.$DateStamp"
		bzip2 -9 "$ArchiveDir/$OneFolder.$DateStamp"
	fi
done