No ext_urls

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

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
old mode 100644 (file)
new mode 100755 (executable)
index 79f3ead..8b8e1b7
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,28 +1,45 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2021 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
-my $usage = "$0 <spam|ham|rm> </path/to/message";
+my $help = <<EOF;
+usage: public-inbox-learn [OPTIONS] [spam|ham|rm] </path/to/RFC2822_message
+
+required action argument:
+
+   spam  unindex the message and train as spam
+     rm  remove the message without training as spam
+    ham  index the message (based on To:/Cc: headers) and train as ham
+
+options:
+
+  --all  scan all inboxes on `rm'
+
+See public-inbox-learn(1) man page for full documentation.
+EOF
 use strict;
-use warnings;
 use PublicInbox::Config;
 use PublicInbox::InboxWritable;
-use PublicInbox::MIME;
+use PublicInbox::Eml;
 use PublicInbox::Address;
 use PublicInbox::Spamcheck::Spamc;
-my $train = shift or die "usage: $usage\n";
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
+my %opt = (all => 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(eval {
-       local $/;
-       my $data = scalar <STDIN>;
+my $mime = PublicInbox::Eml->new(do{
+       defined(my $data = do { local $/; <STDIN> }) or die "read STDIN: $!\n";
        $data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 
        if ($train ne 'rm') {
@@ -36,11 +53,11 @@ my $mime = PublicInbox::MIME->new(eval {
                };
                $err = $@;
        }
-       $data
+       \$data
 });
 
-sub remove_or_add ($$$) {
-       my ($ibx, $train, $addr) = @_;
+sub remove_or_add ($$$$) {
+       my ($ibx, $train, $mime, $addr) = @_;
 
        # We do not touch GIT_COMMITTER_* env here so we can track
        # who trained the message.
@@ -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;
                }
        }
 
@@ -93,11 +110,12 @@ if ($train eq 'spam') {
        while (my ($addr, $ibx) = each %dests) {
                next unless ref($ibx); # $ibx may be 0
                next if $seen{"$ibx"}++;
-               remove_or_add($ibx, $train, $addr);
+               remove_or_add($ibx, $train, $mime, $addr);
        }
-       my $ibx = PublicInbox::MDA->inbox_for_list_id($pi_config, $mime);
-       if ($ibx && !$seen{"$ibx"}) {
-               remove_or_add($ibx, $train, $ibx->{-primary_address});
+       my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_cfg, $mime);
+       for my $ibx (@$dests) {
+               next if $seen{"$ibx"}++;
+               remove_or_add($ibx, $train, $mime, $ibx->{-primary_address});
        }
 }