From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 2BBB41F45B
	for <meta@public-inbox.org>; Fri, 28 Dec 2018 19:17:36 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH] add filter for gmane archives
Date: Fri, 28 Dec 2018 19:17:36 +0000
Message-Id: <20181228191736.3627-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

Extracted from import_slrnspool, since some spools get converted
to mbox or what not.
---
 lib/PublicInbox/Filter/Gmane.pm | 41 +++++++++++++++++++++++++++++++++
 scripts/import_slrnspool        | 24 ++++---------------
 2 files changed, 45 insertions(+), 20 deletions(-)
 create mode 100644 lib/PublicInbox/Filter/Gmane.pm

diff --git a/lib/PublicInbox/Filter/Gmane.pm b/lib/PublicInbox/Filter/Gmane.pm
new file mode 100644
index 0000000..f9042df
--- /dev/null
+++ b/lib/PublicInbox/Filter/Gmane.pm
@@ -0,0 +1,41 @@
+# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# Filter for importing some archives from gmane
+package PublicInbox::Filter::Gmane;
+use base qw(PublicInbox::Filter::Base);
+use strict;
+use warnings;
+
+sub scrub {
+	my ($self, $mime) = @_;
+	my $hdr = $mime->header_obj;
+
+	# gmane rewrites Received headers, which increases spamminess
+	# Some older archives set Original-To
+	foreach my $x (qw(Received To)) {
+		my @h = $hdr->header_raw("Original-$x");
+		if (@h) {
+			$hdr->header_set($x, @h);
+			$hdr->header_set("Original-$x");
+		}
+	}
+
+	# Approved triggers for the SA HEADER_SPAM rule,
+	# X-From is gmane specific
+	foreach my $drop (qw(Approved X-From)) {
+		$hdr->header_set($drop);
+	}
+
+	# appears to be an old gmane bug:
+	$hdr->header_set('connect()');
+
+	$self->ACCEPT($mime);
+}
+
+sub delivery {
+	my ($self, $mime) = @_;
+	$self->scrub($mime);
+}
+
+1;
diff --git a/scripts/import_slrnspool b/scripts/import_slrnspool
index 1a7d77a..e7ea45c 100755
--- a/scripts/import_slrnspool
+++ b/scripts/import_slrnspool
@@ -35,6 +35,9 @@ if (($ibx->{version} || 1) == 2) {
 					$ibx->{-primary_address});
 }
 
+$ibx->{filter} ||= 'PublicInbox::Filter::Gmane';
+my $filter = $ibx->filter;
+
 sub key {
 	"publicinbox.$ibx->{name}.importslrnspoolstate";
 }
@@ -68,26 +71,7 @@ for (; $exit == 0 && $n < $max; $n++) {
 	print STDERR $fn, "\n";
 
 	my $mime = PublicInbox::MIME->new(eval { local $/; <$fh> });
-	my $hdr = $mime->header_obj;
-
-	# gmane rewrites Received headers, which increases spamminess
-	# Some older archives set Original-To
-	foreach my $x (qw(Received To)) {
-		my @h = $hdr->header_raw("Original-$x");
-		if (@h) {
-			$hdr->header_set($x, @h);
-			$hdr->header_set("Original-$x");
-		}
-	}
-
-	# Approved triggers for the SA HEADER_SPAM rule,
-	# X-From is gmane specific
-	foreach my $drop (qw(Approved X-From)) {
-		$hdr->header_set($drop);
-	}
-
-	# appears to be an old gmane bug:
-	$hdr->header_set('connect()');
+	$filter->scrub($mime);
 	$im->add($mime);
 
 	$ok = $n + 1;
-- 
EW