3
# Copyright (C) 2002 Laird Breyer
5
# This program is free software; you can redistribute it and/or modify
6
# it under the terms of the GNU General Public License as published by
7
# the Free Software Foundation; either version 2 of the License, or
8
# (at your option) any later version.
10
# This program is distributed in the hope that it will be useful,
11
# but WITHOUT ANY WARRANTY; without even the implied warranty of
12
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13
# GNU General Public License for more details.
15
# You should have received a copy of the GNU General Public License
16
# along with this program; if not, write to the Free Software
17
# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
19
# Author: Laird Breyer <laird@lbreyer.com>
21
# IMPLEMENTATION NOTES
23
# This script follows the mailcross testsuite interface
24
# requirements. Type man mailcross for details.
26
# The script accepts one of more commands on the command line,
27
# and may read STDIN and write STDOUT as follows:
30
# In this case, a single email is expected on STDIN,
31
# and a list of category filenames is expected in $2, $3, etc.
32
# The script writes the category name corresponding to the
33
# input email on STDOUT.
36
# In this case, a standard mbox stream is expected on STDIN,
37
# while a suitable category file name is expected in $2. No output
38
# is written to STDOUT.
41
# In this case, a directory is expected in $2, which is examined
42
# for old database information. If any old databases are found, they
43
# are purged or reset. No output is written to STDOUT.
45
# If $1 == "describe":
46
# In this case, STDIN and the command line are ignored. A single
47
# line is written on STDOUT, describing the filter functionality.
49
# If $1 == "bootstrap":
50
# In this case, the current script is copied to the directory $2,
51
# provided the classifier we're wrapping exists on the system.
55
TRAIN="sb_mboxtrain.py"
56
[ -z "$TEMPDIR" ] && TEMPDIR=/tmp
61
CATEGORY=`basename $1`
63
$SB -f -d "${DBPATH}/spambayes.db" | grep '^X-Spambayes-Classification:' | sed -e 's/^.*spam.*/spam/' -e 's/^[^s].*$/notspam/'
67
CATEGORY=`basename $1`
69
if [ ! -e "${DBPATH}/spambayes.db" ]; then
70
# bug: -n switch must be last
71
$SB -d "${DBPATH}/spambayes.db" -n
73
cat > "${TEMPDIR}/mbox.tmp"
74
if [ "$CATEGORY" = "spam" ]; then
75
$TRAIN -d "${DBPATH}/spambayes.db" -s "${TEMPDIR}/mbox.tmp"
77
$TRAIN -d "${DBPATH}/spambayes.db" -g "${TEMPDIR}/mbox.tmp"
79
rm -f "${TEMPDIR}/mbox.tmp"
83
find "$1" -name "spambayes.db" -exec rm {} \;
84
find "$1" -name "*.tmp" -exec rm {} \;
88
if [ -n "`which $SB`" ] ; then
91
echo "SpamBayes $VER with default settings"
95
if [ -n "`which $SB`" -a -n "`which $TRAIN`" ] ; then
98
echo -e "\tspambayes is hard-coded for use only with exactly"
99
echo -e "\ttwo categories named 'spam' and 'notspam'."
101
echo "spambayes appears to be missing"
104
echo "bad target directory $2"
113
cat > "$TEMPDIR/mailtoe.tmp"
114
VERDICT=`cat $TEMPDIR/mailtoe.tmp | $ME filter "$@"`
115
if [ "x$VERDICT" != "x`basename $TRUECAT`" ] ; then
116
if [ "`basename $TRUECAT`" = "spam" ]; then
117
cat "$TEMPDIR/mailtoe.tmp" | $SB -d "${DBPATH}/spambayes.db" -s > /dev/null
119
cat "$TEMPDIR/mailtoe.tmp" | $SB -d "${DBPATH}/spambayes.db" -g > /dev/null
131
cat > "$TEMPDIR/mailfoot.tmp"
132
VERDICT=`cat "$TEMPDIR/mailfoot.tmp" | $ME filter "$@"`
133
if [ "`basename $TRUECAT`" = "spam" ]; then
134
cat "$TEMPDIR/mailfoot.tmp" | $SB -d "${DBPATH}/spambayes.db" -s > /dev/null
136
cat "$TEMPDIR/mailfoot.tmp" | $SB -d "${DBPATH}/spambayes.db" -g > /dev/null