From 3e96cf129ba5fc2834b691314c504aa363fd5cf4 Mon Sep 17 00:00:00 2001
From: Eric Wong <normalperson@yhbt.net>
Date: Thu, 9 Jan 2014 23:13:37 +0000
Subject: initial commit

---
 scripts/dc-dlvr            | 64 ++++++++++++++++++++++++++++++++++++++++++++++
 scripts/import_gmane_spool | 51 ++++++++++++++++++++++++++++++++++++
 scripts/report-spam        | 28 ++++++++++++++++++++
 3 files changed, 143 insertions(+)
 create mode 100755 scripts/dc-dlvr
 create mode 100755 scripts/import_gmane_spool
 create mode 100755 scripts/report-spam

(limited to 'scripts')

diff --git a/scripts/dc-dlvr b/scripts/dc-dlvr
new file mode 100755
index 00000000..96009662
--- /dev/null
+++ b/scripts/dc-dlvr
@@ -0,0 +1,64 @@
+#!/bin/sh
+# Copyright (C) 2008-2013, Eric Wong <e@80x24.org>
+# License: GPLv3 or later
+# to use with postfix main.cf: mailbox_command = /etc/dc-dlvr "$EXTENSION"
+DELIVER=/usr/lib/dovecot/deliver
+
+# my personal preference is to use a catchall account to avoid generating
+# backscatter, as invalid emails are usually spam
+case $USER in
+catchall) exec $DELIVER ;;
+esac
+
+# change if your spamc/spamd listens elsewhere
+spamc='spamc -U /run/spamd.sock'
+
+# allow plus addressing to train spam filters, $1 is the $EXTENSION
+# which may be "trainspam" or "trainham".  Only allow spam training
+# when $CLIENT_ADDRESS is empty (local client)
+case $1,$CLIENT_ADDRESS in
+trainspam,) exec $spamc -L spam > /dev/null 2>&1 ;;
+trainham,) exec $spamc -L ham > /dev/null 2>&1 ;;
+esac
+
+TMPMSG=$(mktemp -t dc-dlvr.orig.$USER.XXXXXX || exit 1)
+rm_list=$TMPMSG
+
+# pre-filter, for infrequently read lists which do their own spam filtering:
+if test -r ~/.dc-dlvr.pre
+then
+	set -e
+	cat > $TMPMSG
+	DEFAULT_INBOX=$(. ~/.dc-dlvr.pre)
+	if test xINBOX != x"$DEFAULT_INBOX"
+	then
+		$DELIVER -m $DEFAULT_INBOX < $TMPMSG
+		exec rm -f $rm_list
+	fi
+	PREMSG=$(mktemp -t dc-dlvr.orig.$USER.XXXXXX || exit 1)
+	rm_list="$rm_list $PREMSG"
+	set +e
+	mv -f $TMPMSG $PREMSG
+	$spamc -E --headers < $PREMSG > $TMPMSG
+else
+	$spamc -E --headers > $TMPMSG
+fi
+err=$?
+
+# normal delivery
+set -e
+
+case $err in
+1) $DELIVER -m INBOX.spam < $TMPMSG ;;
+*)
+	# users may override normal delivery and have it go elsewhere
+	if test -r ~/.dc-dlvr.rc
+	then
+		. ~/.dc-dlvr.rc
+	else
+		$DELIVER -m INBOX < $TMPMSG
+	fi
+	;;
+esac
+
+exec rm -f $rm_list
diff --git a/scripts/import_gmane_spool b/scripts/import_gmane_spool
new file mode 100755
index 00000000..b5573e15
--- /dev/null
+++ b/scripts/import_gmane_spool
@@ -0,0 +1,51 @@
+#!/usr/bin/perl -w
+# Copyright (C) 2013, Eric Wong <normalperson@yhbt.net> and all contributors
+# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+#
+# One-off script to convert an slrnpull news spool from gmane
+use strict;
+use warnings;
+use Parallel::ForkManager;
+use Email::Simple;
+use PublicInbox::Filter;
+use IPC::Run qw(run);
+my $usage = "import_nntp_spool SLRNPULL_ROOT/news/foo/bar MAIN_REPO FAIL_REPO";
+my $spool = shift @ARGV or die "Usage: $usage\n";
+my $main_repo = shift @ARGV or die "Usage: $usage\n";
+my $fail_repo = shift @ARGV or die "Usage: $usage\n";
+my $nproc = `nproc 2>/dev/null` || 4;
+my $pm = Parallel::ForkManager->new($nproc);
+my @args = ('public-inbox-mda', $main_repo, $fail_repo);
+
+foreach my $n (<$spool/*>) {
+	$n =~ m{/\d+\z} or next;
+	$pm->start and next;
+	if (open my $fh, '<', $n) {
+		local $/;
+		my $s = Email::Simple->new(<$fh>);
+
+		# gmane rewrites Received headers, which increases spamminess
+		my @h = $s->header("Original-Received");
+		if (@h) {
+			$s->header_set("Received", @h);
+			$s->header_set("Original-Received");
+		}
+
+		# triggers for the SA HEADER_SPAM rule
+		foreach my $drop (qw(Approved)) { $s->header_set($drop) }
+
+		# appears to be an old gmane bug:
+		$s->header_set("connect()");
+
+		my $orig = $s->as_string;
+		close $fh or die "close failed: $!\n";
+		eval { run(\@args, \$orig) };
+		die "fail $n: $?\n" if $?;
+		die "fail $n: $@\n" if $@;
+	} else {
+		warn "Failed to open $n: $!\n";
+	}
+	$pm->finish;
+}
+
+$pm->wait_all_children;
diff --git a/scripts/report-spam b/scripts/report-spam
new file mode 100755
index 00000000..825855b5
--- /dev/null
+++ b/scripts/report-spam
@@ -0,0 +1,28 @@
+#!/bin/sh
+# Copyright (C) 2008-2013, Eric Wong <e@80x24.org>
+# License: GPLv3 or later
+# Usage: report-spam /path/to/message/in/maildir
+# 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 $@/$#
+
+# gigantic emails tend not to be spam (but they suck anyways...)
+bytes=$(stat -c %s $1)
+if test $bytes -gt 512000
+then
+	exit
+fi
+
+# only tested with the /usr/sbin/sendmail which ships with postfix
+case $1 in
+*[/.]spam/cur/*) # non-new messages in spam get trained
+	exec /usr/sbin/sendmail -oem -oi $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
+	;;
+esac
-- 
cgit v1.2.3-24-ge0c7