user/dev discussion of public-inbox itself
 help / color / Atom feed
* [PATCH] add filter for gmane archives
@ 2018-12-28 19:17 Eric Wong
  0 siblings, 0 replies; 1+ messages in thread
From: Eric Wong @ 2018-12-28 19:17 UTC (permalink / raw)
  To: meta

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


^ permalink raw reply	[flat|nested] 1+ messages in thread

only message in thread, back to index

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-12-28 19:17 [PATCH] add filter for gmane archives Eric Wong

user/dev discussion of public-inbox itself

Archives are clonable:
	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.org/gmane.mail.public-inbox.general

 note: .onion URLs require Tor: https://www.torproject.org/
       or Tor2web: https://www.tor2web.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox