learn: hoist out remove_or_add subroutine

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

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 71aa50f9d5989b093b4efa50f4312267f8ce6440..56739f88d720bfc12d344d6e4a2c68b73a28926e 100755 (executable)
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,18 +1,15 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# 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
 # public-inbox
-my $usage = "$0 (spam|ham) < /path/to/message";
+my $usage = "$0 <spam|ham|rm> </path/to/message";
 use strict;
 use warnings;
 use PublicInbox::Config;
-use PublicInbox::Git;
-use PublicInbox::Import;
+use PublicInbox::InboxWritable;
 use PublicInbox::MIME;
-use Email::MIME::ContentType;
-$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
 use PublicInbox::Address;
 use PublicInbox::Spamcheck::Spamc;
 my $train = shift or die "usage: $usage\n";
@@ -42,50 +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;
-       foreach my $email (PublicInbox::Address::emails($val)) {
-               $dests{lc($email)} = 1;
-       }
-}
+sub remove_or_add ($$$) {
+       my ($ibx, $train, $addr) = @_;
 
-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);
-               $im->remove($mime);
-               $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;
-       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);
+       $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);
-       } else { # $train eq "ham"
+               $im->remove($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, $dst);
+               PublicInbox::MDA->set_list_headers($mime, $ibx);
 
                # Ham messages are trained when they're marked into
                # a SEEN state, so this is idempotent:
@@ -94,6 +67,34 @@ 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 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
+       while (my ($addr, $ibx) = each %dests) {
+               next unless ref($ibx); # $ibx may be 0
+               remove_or_add($ibx, $train, $addr);
+       }
+}
+
 if ($err) {
        warn $err;
        exit 1;