v2writable: simplify barrier vs checkpoints

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

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 38c83243f8971e63859fe4261b7ba4d521ff2335..c51f95856a137d7f0f4dac7c855e3cf741a732cd 100755 (executable)
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,6 +1,6 @@
 #!/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) 2014-2018 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
@@ -11,8 +11,6 @@ use PublicInbox::Config;
 use PublicInbox::Git;
 use PublicInbox::Import;
 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";
@@ -51,6 +49,18 @@ foreach my $h (qw(Cc To)) {
        }
 }
 
+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, 'spam');
+               $im->done;
+       });
+}
+
 require PublicInbox::MDA if $train eq "ham";
 
 # n.b. message may be cross-posted to multiple public-inboxes
@@ -69,7 +79,7 @@ foreach my $recipient (keys %dests) {
                # 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: