X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=93aece2e66b6c0d0fecf1d718070e5e213099f7a;hb=7c5ac90b309bbe76468055e8a9289664ef2dfe37;hp=1c051ec1e274a0a9ff166d7ec4a7c779a1d2c8c4;hpb=f850effe0baef8a37ad2eef3ef581b79539cc304;p=public-inbox.git
diff --git a/script/public-inbox-learn b/script/public-inbox-learn
old mode 100755
new mode 100644
index 1c051ec1..93aece2e
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,85 +1,108 @@
#!/usr/bin/perl -w
-# Copyright (C) 2014-2015 all contributors
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2014-2019 all contributors
+# License: AGPL-3.0+
#
# Used for training spam (via SpamAssassin) and removing messages from a
# public-inbox
-my $usage = "$0 (spam|ham) < /path/to/message";
+my $usage = "$0 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 ;
- $data =~ s/\AFrom [^\r\n]*\r?\n//s;
- $data
-});
+ $data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
-# get all recipients
-my %dests;
-foreach my $h (qw(Cc To)) {
- foreach my $recipient (Email::Address->parse($mime->header($h))) {
- $dests{lc($recipient->address)} = 1;
+ 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 = $@;
}
-}
-
-if ($train eq "ham") {
- require PublicInbox::MDA;
- require PublicInbox::Filter;
- PublicInbox::Filter->run($mime);
-}
+ $data
+});
-my $err = 0;
-my @output = qw(> /dev/null > /dev/null);
+sub remove_or_add ($$$$) {
+ my ($ibx, $train, $mime, $addr) = @_;
-# 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 $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") {
+ 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:
$im->add($mime);
}
$im->done;
- my $in = $mime->as_string;
- if (!run([qw(spamc -L), $train], \$in, @output)) {
- $err = 1;
+}
+
+# spam is removed from all known inboxes since it is often Bcc:-ed
+if ($train eq 'spam') {
+ $pi_config->each_inbox(sub {
+ my ($ibx) = @_;
+ $ibx = PublicInbox::InboxWritable->new($ibx);
+ my $im = $ibx->importer(0);
+ $im->remove($mime, 'spam');
+ $im->done;
+ });
+} else {
+ require PublicInbox::MDA;
+
+ # get all recipients
+ my %dests; # address =>
+ for ($mime->header('Cc'), $mime->header('To')) {
+ foreach my $addr (PublicInbox::Address::emails($_)) {
+ $addr = lc($addr);
+ $dests{$addr} //= $pi_config->lookup($addr) // 0;
+ }
}
- $err or eval {
- require PublicInbox::SearchIdx;
- PublicInbox::SearchIdx->new($git_dir, 2)->index_sync;
- };
+ # n.b. message may be cross-posted to multiple public-inboxes
+ 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, $mime, $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, $mime, $ibx->{-primary_address});
+ }
}
-exit $err;
+if ($err) {
+ warn $err;
+ exit 1;
+}