X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=8b8e1b7732938bc8369813866fed9dad59ae6de6;hb=d323a16ced5e3a77136a1ebca4a2f7d5678121c4;hp=4c10b68b994506bd4949e197028bd7caa2d8a7f1;hpb=a479b45117ed69d9311770fa39e6676d38f9cab2;p=public-inbox.git
diff --git a/script/public-inbox-learn b/script/public-inbox-learn
old mode 100644
new mode 100755
index 4c10b68b..8b8e1b77
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,28 +1,45 @@
#!/usr/bin/perl -w
-# Copyright (C) 2014-2020 all contributors
+# Copyright (C) 2014-2021 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 $pi_cfg = PublicInbox::Config->new;
my $err;
-my $mime = PublicInbox::MIME->new(do{
- local $/;
- my $data = ;
+my $mime = PublicInbox::Eml->new(do{
+ defined(my $data = do { local $/; }) or die "read STDIN: $!\n";
$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
if ($train ne 'rm') {
@@ -68,12 +85,12 @@ sub remove_or_add ($$$$) {
}
# spam is removed from all known inboxes since it is often Bcc:-ed
-if ($train eq 'spam') {
- $pi_config->each_inbox(sub {
+if ($train eq 'spam' || ($train eq 'rm' && $opt{all})) {
+ $pi_cfg->each_inbox(sub {
my ($ibx) = @_;
$ibx = PublicInbox::InboxWritable->new($ibx);
my $im = $ibx->importer(0);
- $im->remove($mime, 'spam');
+ $im->remove($mime, $train);
$im->done;
});
} else {
@@ -84,7 +101,7 @@ if ($train eq 'spam') {
for ($mime->header('Cc'), $mime->header('To')) {
foreach my $addr (PublicInbox::Address::emails($_)) {
$addr = lc($addr);
- $dests{$addr} //= $pi_config->lookup($addr) // 0;
+ $dests{$addr} //= $pi_cfg->lookup($addr) // 0;
}
}
@@ -95,9 +112,9 @@ if ($train eq 'spam') {
next if $seen{"$ibx"}++;
remove_or_add($ibx, $train, $mime, $addr);
}
- my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_config, $mime);
+ my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_cfg, $mime);
for my $ibx (@$dests) {
- next if !$seen{"$ibx"}++;
+ next if $seen{"$ibx"}++;
remove_or_add($ibx, $train, $mime, $ibx->{-primary_address});
}
}