learn: use "spam" as subject for removal commits

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

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index c79f24790e32870478a31d6c5202fada392ca738..75294a0a8e44e9368fc0b98d7db38d1d8a71152b 100755 (executable)
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -10,19 +10,35 @@ use warnings;
 use PublicInbox::Config;
 use PublicInbox::Git;
 use PublicInbox::Import;
-use Email::MIME;
+use PublicInbox::MIME;
+use Email::MIME::ContentType;
+$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
 use PublicInbox::Address;
-use IPC::Run qw/run/;
+use PublicInbox::Spamcheck::Spamc;
 my $train = shift or die "usage: $usage\n";
-if ($train !~ /\A(?:ham|spam)\z/) {
+if ($train !~ /\A(?:ham|spam|rm)\z/) {
        die "`$train' not recognized.\nusage: $usage\n";
 }
 
+my $spamc = PublicInbox::Spamcheck::Spamc->new;
 my $pi_config = PublicInbox::Config->new;
-my $mime = Email::MIME->new(eval {
+my $err;
+my $mime = PublicInbox::MIME->new(eval {
        local $/;
        my $data = scalar <STDIN>;
-       $data =~ s/\AFrom [^\r\n]*\r?\n//s;
+       $data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+
+       if ($train ne 'rm') {
+               eval {
+                       if ($train eq 'ham') {
+                               $spamc->hamlearn(\$data);
+                       } elsif ($train eq 'spam') {
+                               $spamc->spamlearn(\$data);
+                       }
+                       die "spamc failed with: $?\n" if $?;
+               };
+               $err = $@;
+       }
        $data
 });
 
@@ -35,33 +51,37 @@ foreach my $h (qw(Cc To)) {
        }
 }
 
-if ($train eq "ham") {
-       require PublicInbox::MDA;
-       require PublicInbox::Filter;
-       PublicInbox::Filter->run($mime);
+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;
+       });
 }
 
-my $err = 0;
-my @output = qw(> /dev/null > /dev/null);
+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 = $dst->{mainrepo} or next;
-       my ($out, $err) = ("", "");
        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->{inbox};
+       my $name = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
        my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient;
        my $im = PublicInbox::Import->new($git, $name, $email);
 
-       if ($train eq "spam") {
+       if ($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);
+               $im->remove($mime, $train);
        } else { # $train eq "ham"
                # no checking for spam here, we assume the message has
                # been reviewed by a human at this point:
@@ -72,15 +92,9 @@ foreach my $recipient (keys %dests) {
                $im->add($mime);
        }
        $im->done;
-       my $in = $mime->as_string;
-       if (!run([qw(spamc -L), $train], \$in, @output)) {
-               $err = 1;
-       }
-
-       $err or eval {
-               require PublicInbox::SearchIdx;
-               PublicInbox::SearchIdx->new($git_dir, 2)->index_sync;
-       };
 }
 
-exit $err;
+if ($err) {
+       warn $err;
+       exit 1;
+}