learn: support multiple To/Cc headers

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

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index c51f95856a137d7f0f4dac7c855e3cf741a732cd..8ff1652b07234709fd3e661f0a945c4b6b88d512 100755 (executable)
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,5 +1,5 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2019 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
@@ -8,8 +8,7 @@ my $usage = "$0 (spam|ham) < /path/to/message";
 use strict;
 use warnings;
 use PublicInbox::Config;
-use PublicInbox::Git;
-use PublicInbox::Import;
+use PublicInbox::InboxWritable;
 use PublicInbox::MIME;
 use PublicInbox::Address;
 use PublicInbox::Spamcheck::Spamc;
@@ -43,19 +42,19 @@ my $mime = PublicInbox::MIME->new(eval {
 # get all recipients
 my %dests;
 foreach my $h (qw(Cc To)) {
-       my $val = $mime->header($h) or next;
-       foreach my $email (PublicInbox::Address::emails($val)) {
-               $dests{lc($email)} = 1;
+       my @val = $mime->header($h) or next;
+       for (@val) {
+               foreach my $email (PublicInbox::Address::emails($_)) {
+                       $dests{lc($email)} = 1;
+               }
        }
 }
 
 if ($train eq 'spam') {
        $pi_config->each_inbox(sub {
                my ($ibx) = @_;
-               my $git = $ibx->git;
-               my $name = $ibx->{name};
-               my $addr = $ibx->{-primary_address};
-               my $im = PublicInbox::Import->new($git, $name, $addr, $ibx);
+               $ibx = PublicInbox::InboxWritable->new($ibx);
+               my $im = $ibx->importer(0);
                $im->remove($mime, 'spam');
                $im->done;
        });
@@ -66,13 +65,12 @@ 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;
-       my $git_dir = $dst->{mainrepo} or next;
-       my $git = PublicInbox::Git->new($git_dir);
        # We do not touch GIT_COMMITTER_* env here so we can track
        # who trained the message.
-       my $name = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
-       my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient;
-       my $im = PublicInbox::Import->new($git, $name, $email);
+       $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);
 
        if ($train eq "spam" || $train eq "rm") {
                # This needs to be idempotent, as my inotify trainer