#!/bin/bash

### Script
#
#  Plesk Spamassassin Auto-learning Script
#  Author: paul@geekniche.com
#
###

### General usage
#
#  Since you're looking for a solution to handle auto-learning on a Plesk system which utilizes
#  spamassassin, I'm going to assume that you're at least a little technically minded.  That
#  being said, this should be relatively straightforward.  Other than this script, you need one
#  other file for it to work, and that's the mailbox list.  It needs to be specially formatted,
#  one domain per line, like so:
#
#   domain.com|user1:user2:user3
#
#  Please note the pipe (|) separator between the domain and the users, and the colon (:) between
#  each user.  In order to run this script all automated-like, enter the following in cron:
#
#   0 * * * *    /var/scripts/autoSpamTrain /var/scripts/spamUserList &> /dev/null
#
#  This command will run the scripti every hour, with the spamUserList file as the first (and 
#  only) argument and discard any errors.  Logging is handled by the script itself.
#
#  Questions, comments, improvements, etc are appreciated.  Please feel free to email me at the
#  email address provided above.
#
###

# Constants
MAILNAMES_PATH="/var/qmail/mailnames"  # Works for both qmail and postfix under Plesk (v9.2).
SPAM_FOLDER=".Spam"  # Name this what you like, but make sure to include the period.
LOG="/var/log/autoSpamTrain.log"  # Put this wherever you like.  /var/log seemed to fit for my needs.

# learnAndFlush args are the following: $1 = domain, $2 = username
function learnAndFlush {
        echo -e "Learning new Bayesian data from spam for $2@$1" >>$LOG
        sa-learn -p ${MAILNAMES_PATH}/$1/$2/.spamassassin/user_prefs --dbpath ${MAILNAMES_PATH}/$1/$2/.spamassassin --spam ${MAILNAMES_PATH}/$1/$2/Maildir/${SPAM_FOLDER}/cur/ >>$LOG
        flush $1 $2
}

function flush {
        echo -e "Removing spam from ${MAILNAMES_PATH}/$1/$2" >>$LOG
        find ${MAILNAMES_PATH}/$1/$2/Maildir/${SPAM_FOLDER}/cur -type f -exec rm {} \;
}

### Main script stars here ###

script_start=$(date +%s)
echo -e "###\n# Script started at " `date` "\n###\n" >>$LOG
FILE=""
 
# Make sure we get file name as command line argument
# Else stop the script

if [ "$1" == "" ]; then
   echo "Must supply proper userlist.  Script go boom now."
   exit
else
   FILE="$1"
   # make sure file exist and readable
   if [ ! -f $FILE ]; then
  	echo "$FILE : does not exists"
  	exit 1
   elif [ ! -r $FILE ]; then
  	echo "$FILE: can not read"
  	exit 2
   fi
fi
# read $FILE using the file descriptors
 
# Set loop separator to end of line
BAKIFS=$IFS
IFS=$(echo -en "\n\b")
exec 3<&0
exec 0<$FILE

while read line
do
	FS="|"
	domain=$(echo $line|cut -d$FS -f1)
	users=$(echo $line|cut -d$FS -f2)
	SaveIFS=$IFS
	IFS=":"
	usersArray=( $users )
	for (( i = 0 ; i < ${#usersArray[@]} ; i++ ))
	do
		learnAndFlush $domain ${usersArray[$i]}
	done
	IFS=$SaveIFS
done
exec 0<&3
 
# restore $IFS which was used to determine what the field separators are
IFS=$BAKIFS
script_end=$(date +%s)
let total="$script_end - $script_start"
echo -e "\n###\n# Script ended at " `date` "\n###\n" >>$LOG
echo "$total seconds to run" >>$LOG
echo -e "\n+++++++++++++++++++++++++++++++++++++++++++++++++++++++\n" >>$LOG
exit 0