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.
54
# In this case, a single email is expected on STDIN,
55
# and a list of category filenames is expected in $2, $3, etc.
56
# The category name in $2 represents the "true" category, and $3 $4 etc
57
# are a complete list of possible categories.
58
# The script writes the classified category name corresponding to the
59
# input email on STDOUT, and if this differs from the true category $2,
60
# then, and only then, the email is learned.
63
# Like "toe", but the input email is always learned.
67
[ -z "$TEMPDIR" ] && TEMPDIR=/tmp
72
CATEGORY=`basename $1`
75
if [ "$?" = "0" ]; then
83
CATEGORY=`basename $1`
85
if [ "$CATEGORY" = "spam" ]; then
86
$BFIL -M -d "$DBPATH" -s
88
$BFIL -M -d "$DBPATH" -n
93
find "$1" -name "wordlist.db" -exec rm {} \;
94
find "$1" -name "*.tmp" -exec rm {} \;
98
if [ -n "`which bogofilter`" ] ; then
99
VER=`bogofilter -V 2>&1 | head -1 | sed -e 's/.*version //'`
101
echo "bogofilter $VER with Robinson-Fischer algorithm"
104
if [ -d "$2" ] ; then
105
if [ -n "`which bogofilter`" ] ; then
108
echo -e "\tbogofilterF is hard-coded for use only with exactly"
109
echo -e "\ttwo categories named 'spam' and 'notspam'."
111
echo "bogofilter appears to be missing"
114
echo "bad target directory $2"
123
cat > "$TEMPDIR/mailtoe.tmp"
124
VERDICT=`cat "$TEMPDIR/mailtoe.tmp" | "$ME" filter "$@"`
125
if [ "x$VERDICT" != "x`basename $TRUECAT`" ] ; then
126
if [ "x`basename $TRUECAT`" = "xspam" ]; then
127
cat "$TEMPDIR/mailtoe.tmp" | $BFIL -d "$DBPATH" -s
129
cat "$TEMPDIR/mailtoe.tmp" | $BFIL -d "$DBPATH" -n
140
cat > "$TEMPDIR/mailfoot.tmp"
141
VERDICT=`cat "$TEMPDIR/mailfoot.tmp" | "$ME" filter "$@"`
142
if [ "x`basename $TRUECAT`" = "xspam" ]; then
143
cat "$TEMPDIR/mailfoot.tmp" | $BFIL -d "$DBPATH" -s
145
cat "$TEMPDIR/mailfoot.tmp" | $BFIL -d "$DBPATH" -n