From bc6b44cd7feee7e83ef1dcf26092808f92f757d9 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Mon, 28 Oct 2019 10:45:16 +0000
Subject: [PATCH] learn: only map recipient list on "ham" or "rm"

It's assumed that "spam" can end up anywhere due to Bcc:, so we
need to scan every single inbox.  However, "rm" is usually more
targeted and and "ham" obviously only belongs in some inboxes.
---
 script/public-inbox-learn | 71 +++++++++++++++++++--------------------
 1 file changed, 35 insertions(+), 36 deletions(-)

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 8ff1652b..d2d665d5 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -39,17 +39,7 @@ 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;
-		}
-	}
-}
-
+# spam is removed from all known inboxes
 if ($train eq 'spam') {
 	$pi_config->each_inbox(sub {
 		my ($ibx) = @_;
@@ -58,36 +48,45 @@ if ($train eq 'spam') {
 		$im->remove($mime, 'spam');
 		$im->done;
 	});
-}
+} else {
+	require PublicInbox::MDA if $train eq "ham";
 
-require PublicInbox::MDA if $train eq "ham";
+	# get all recipients
+	my %dests; # address => <PublicInbox::Inbox|0(false)>
+	for ($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
-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 = $dst->importer(0);
+	# n.b. message may be cross-posted to multiple public-inboxes
+	while (my ($addr, $dst) = each %dests) {
+		next unless ref($dst);
+		# 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} || $addr;
+		$dst = PublicInbox::InboxWritable->new($dst);
+		my $im = $dst->importer(0);
 
-	if ($train eq "spam" || $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 { # $train eq "ham"
-		# no checking for spam here, we assume the message has
-		# been reviewed by a human at this point:
-		PublicInbox::MDA->set_list_headers($mime, $dst);
+		if ($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, $train);
+		} elsif ($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);
 
-		# Ham messages are trained when they're marked into
-		# a SEEN state, so this is idempotent:
-		$im->add($mime);
+			# Ham messages are trained when they're marked into
+			# a SEEN state, so this is idempotent:
+			$im->add($mime);
+		}
+		$im->done;
 	}
-	$im->done;
 }
 
 if ($err) {
-- 
2.44.0