X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=scripts%2Freport-spam;h=325f57183d2a14bb1365f45af1c949c246c79e22;hb=21fcd8a37c82c1ef654d402cf592f0c9d803aa26;hp=825855b543d16261bd7b6e6e1e58b1cd9e957290;hpb=3e96cf129ba5fc2834b691314c504aa363fd5cf4;p=public-inbox.git

diff --git a/scripts/report-spam b/scripts/report-spam
index 825855b5..325f5718 100755
--- a/scripts/report-spam
+++ b/scripts/report-spam
@@ -1,11 +1,11 @@
 #!/bin/sh
-# Copyright (C) 2008-2013, Eric Wong <e@80x24.org>
-# License: GPLv3 or later
+# Copyright (C) 2008-2014, Eric Wong <e@80x24.org>
+# License: GPLv3 or later <http://www.gnu.org/licenses/gpl-3.0.txt>
 # Usage: report-spam /path/to/message/in/maildir
+# This is intended for use with incron or similar systems.
 # my incrontab(5) looks like this:
-#  /path/to/.maildir/cur IN_MOVED_TO /path/to/report-spam $@/$#
-#  /path/to/.maildir/.INBOX.good/cur IN_MOVED_TO /path/to/report-spam $@/$#
-#  /path/to/.maildir/.INBOX.spam/cur IN_MOVED_TO /path/to/report-spam $@/$#
+#  /path/to/maildir/.INBOX.good/cur IN_MOVED_TO /path/to/report-spam $@/$#
+#  /path/to/maildir/.INBOX.spam/cur IN_MOVED_TO /path/to/report-spam $@/$#
 
 # gigantic emails tend not to be spam (but they suck anyways...)
 bytes=$(stat -c %s $1)
@@ -14,15 +14,32 @@ then
 	exit
 fi
 
-# only tested with the /usr/sbin/sendmail which ships with postfix
+# Only tested with the /usr/sbin/sendmail which ships with postfix
+# *** Why not call spamc directly in this script? ***
+# I route this through my MTA so it gets queued properly.
+# incrond has no concurrency limits and will fork a new process on
+# every single event, which sucks with rename storms when a client
+# commits folder changes.  The sendmail executable exits quickly and
+# queues up the message for training.  This should also ensure fairness
+# to newly arriving mail.  Instead of installing/configuring
+# another queueing system, I reuse the queue in the MTA.
+# See scripts/dc-dlvr for corresponding trainspam/trainham handlers,
+# which are for my personal bayes training, and scripts/dc-dlvr.pre
+# for the pispam/piham handlers for training emails going to public-inbox
+
+DO_SENDMAIL='/usr/sbin/sendmail -oi'
+PI_USER=pi
+
 case $1 in
 *[/.]spam/cur/*) # non-new messages in spam get trained
-	exec /usr/sbin/sendmail -oem -oi $USER+trainspam < $1
+	$DO_SENDMAIL $PI_USER+pispam <$1
+	exec $DO_SENDMAIL $USER+trainspam <$1
 	;;
 *:2,*S*) # otherwise, seen messages only
 	case $1 in
 	*:2,*T*) exit 0 ;; # ignore trashed messages
 	esac
-	exec /usr/sbin/sendmail -oem -oi $USER+trainham < $1
+	$DO_SENDMAIL $PI_USER+piham <$1
+	exec $DO_SENDMAIL $USER+trainham <$1
 	;;
 esac