mda: support multiple List-ID matches

[public-inbox.git] / script / public-inbox-learn

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
old mode 100755 (executable)
new mode 100644 (file)
index d2d665d..3073294
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -4,7 +4,7 @@
 #
 # 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;
@@ -39,7 +39,35 @@ my $mime = PublicInbox::MIME->new(eval {
        $data
 });
 
-# spam is removed from all known inboxes
+sub remove_or_add ($$$) {
+       my ($ibx, $train, $addr) = @_;
+
+       # We do not touch GIT_COMMITTER_* env here so we can track
+       # who trained the message.
+       $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 "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, $ibx);
+
+               # Ham messages are trained when they're marked into
+               # a SEEN state, so this is idempotent:
+               $im->add($mime);
+       }
+       $im->done;
+}
+
+# spam is removed from all known inboxes since it is often Bcc:-ed
 if ($train eq 'spam') {
        $pi_config->each_inbox(sub {
                my ($ibx) = @_;
@@ -49,7 +77,7 @@ if ($train eq 'spam') {
                $im->done;
        });
 } else {
-       require PublicInbox::MDA if $train eq "ham";
+       require PublicInbox::MDA;
 
        # get all recipients
        my %dests; # address => <PublicInbox::Inbox|0(false)>
@@ -61,31 +89,16 @@ if ($train eq 'spam') {
        }
 
        # 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 "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);
-               }
-               $im->done;
+       my %seen;
+       while (my ($addr, $ibx) = each %dests) {
+               next unless ref($ibx); # $ibx may be 0
+               next if $seen{"$ibx"}++;
+               remove_or_add($ibx, $train, $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, $ibx->{-primary_address});
        }
 }