X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=fb2d86ec141ff11741d6681975d9a0feb7579c44;hb=4f1a683dc895a7bd4cf79e58b39faea256045921;hp=ad1329859ce253304507046547667ad21c45464e;hpb=ec294cdbc5392fdb136572dbcedb250798023703;p=public-inbox.git
diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index ad132985..fb2d86ec 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,28 +1,46 @@
#!/usr/bin/perl -w
-# Copyright (C) 2014-2019 all contributors
+# Copyright (C) 2014-2020 all contributors
# License: AGPL-3.0+
#
# Used for training spam (via SpamAssassin) and removing messages from a
# public-inbox
-my $usage = "$0 0);
+GetOptions(\%opt, qw(all help|h)) or die $help;
+
+my $train = shift or die $help;
if ($train !~ /\A(?:ham|spam|rm)\z/) {
- die "`$train' not recognized.\nusage: $usage\n";
+ die "`$train' not recognized.\n$help";
}
+die "--all only works with `rm'\n" if $opt{all} && $train ne 'rm';
my $spamc = PublicInbox::Spamcheck::Spamc->new;
my $pi_config = PublicInbox::Config->new;
my $err;
-my $mime = PublicInbox::MIME->new(eval {
+my $mime = PublicInbox::Eml->new(do{
local $/;
- my $data = scalar ;
+ my $data = ;
$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
if ($train ne 'rm') {
@@ -36,20 +54,48 @@ my $mime = PublicInbox::MIME->new(eval {
};
$err = $@;
}
- $data
+ \$data
});
+sub remove_or_add ($$$$) {
+ my ($ibx, $train, $mime, $addr) = @_;
+
+ # We do not touch GIT_COMMITTER_* env here so we can track
+ # who trained the message.
+ $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 "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, $train);
+ } elsif ($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, $ibx);
+
+ # Ham messages are trained when they're marked into
+ # a SEEN state, so this is idempotent:
+ $im->add($mime);
+ }
+ $im->done;
+}
+
# spam is removed from all known inboxes since it is often Bcc:-ed
-if ($train eq 'spam') {
+if ($train eq 'spam' || ($train eq 'rm' && $opt{all})) {
$pi_config->each_inbox(sub {
my ($ibx) = @_;
$ibx = PublicInbox::InboxWritable->new($ibx);
my $im = $ibx->importer(0);
- $im->remove($mime, 'spam');
+ $im->remove($mime, $train);
$im->done;
});
} else {
- require PublicInbox::MDA if $train eq "ham";
+ require PublicInbox::MDA;
# get all recipients
my %dests; # address =>
@@ -61,31 +107,16 @@ if ($train eq 'spam') {
}
# n.b. message may be cross-posted to multiple public-inboxes
- while (my ($addr, $dst) = each %dests) {
- next unless ref($dst);
- # We do not touch GIT_COMMITTER_* env here so we can track
- # who trained the message.
- $dst->{name} = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
- $dst->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} || $addr;
- $dst = PublicInbox::InboxWritable->new($dst);
- my $im = $dst->importer(0);
-
- if ($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, $train);
- } elsif ($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);
-
- # Ham messages are trained when they're marked into
- # a SEEN state, so this is idempotent:
- $im->add($mime);
- }
- $im->done;
+ my %seen;
+ while (my ($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});
}
}