X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=0d6c989b8ee00be88449d128f2e890239154d034;hb=2fc67a18b7ccd75ea6eb945f18203cbf4bcf228f;hp=8ff1652b07234709fd3e661f0a945c4b6b88d512;hpb=83470f5e60e44d7f70b378f4b250c6584f42f64e;p=public-inbox.git

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
old mode 100755
new mode 100644
index 8ff1652b..0d6c989b
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,10 +1,10 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Used for training spam (via SpamAssassin) and removing messages from a
 # public-inbox
-my $usage = "$0 (spam|ham) < /path/to/message";
+my $usage = "$0 <spam|ham|rm> </path/to/message";
 use strict;
 use warnings;
 use PublicInbox::Config;
@@ -39,49 +39,26 @@ my $mime = PublicInbox::MIME->new(eval {
 	$data
 });
 
-# get all recipients
-my %dests;
-foreach my $h (qw(Cc To)) {
-	my @val = $mime->header($h) or next;
-	for (@val) {
-		foreach my $email (PublicInbox::Address::emails($_)) {
-			$dests{lc($email)} = 1;
-		}
-	}
-}
+sub remove_or_add ($$$$) {
+	my ($ibx, $train, $mime, $addr) = @_;
 
-if ($train eq 'spam') {
-	$pi_config->each_inbox(sub {
-		my ($ibx) = @_;
-		$ibx = PublicInbox::InboxWritable->new($ibx);
-		my $im = $ibx->importer(0);
-		$im->remove($mime, 'spam');
-		$im->done;
-	});
-}
-
-require PublicInbox::MDA if $train eq "ham";
-
-# n.b. message may be cross-posted to multiple public-inboxes
-foreach my $recipient (keys %dests) {
-	my $dst = $pi_config->lookup($recipient) or next;
 	# We do not touch GIT_COMMITTER_* env here so we can track
 	# who trained the message.
-	$dst->{name} = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
-	$dst->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} || $recipient;
-	$dst = PublicInbox::InboxWritable->new($dst);
-	my $im = $dst->importer(0);
+	$ibx->{name} = $ENV{GIT_COMMITTER_NAME} // $ibx->{name};
+	$ibx->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} // $addr;
+	$ibx = PublicInbox::InboxWritable->new($ibx);
+	my $im = $ibx->importer(0);
 
-	if ($train eq "spam" || $train eq "rm") {
+	if ($train eq "rm") {
 		# This needs to be idempotent, as my inotify trainer
 		# may train for each cross-posted message, and this
 		# script already learns for every list in
 		# ~/.public-inbox/config
 		$im->remove($mime, $train);
-	} else { # $train eq "ham"
+	} elsif ($train eq "ham") {
 		# no checking for spam here, we assume the message has
 		# been reviewed by a human at this point:
-		PublicInbox::MDA->set_list_headers($mime, $dst);
+		PublicInbox::MDA->set_list_headers($mime, $ibx);
 
 		# Ham messages are trained when they're marked into
 		# a SEEN state, so this is idempotent:
@@ -90,6 +67,41 @@ foreach my $recipient (keys %dests) {
 	$im->done;
 }
 
+# spam is removed from all known inboxes since it is often Bcc:-ed
+if ($train eq 'spam') {
+	$pi_config->each_inbox(sub {
+		my ($ibx) = @_;
+		$ibx = PublicInbox::InboxWritable->new($ibx);
+		my $im = $ibx->importer(0);
+		$im->remove($mime, 'spam');
+		$im->done;
+	});
+} else {
+	require PublicInbox::MDA;
+
+	# get all recipients
+	my %dests; # address => <PublicInbox::Inbox|0(false)>
+	for ($mime->header('Cc'), $mime->header('To')) {
+		foreach my $addr (PublicInbox::Address::emails($_)) {
+			$addr = lc($addr);
+			$dests{$addr} //= $pi_config->lookup($addr) // 0;
+		}
+	}
+
+	# n.b. message may be cross-posted to multiple public-inboxes
+	my %seen;
+	while (my ($addr, $ibx) = each %dests) {
+		next unless ref($ibx); # $ibx may be 0
+		next if $seen{"$ibx"}++;
+		remove_or_add($ibx, $train, $mime, $addr);
+	}
+	my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_config, $mime);
+	for my $ibx (@$dests) {
+		next if !$seen{"$ibx"}++;
+		remove_or_add($ibx, $train, $mime, $ibx->{-primary_address});
+	}
+}
+
 if ($err) {
 	warn $err;
 	exit 1;