X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=5cd08d490bf0273bce85ce4d148bdb09035ad288;hb=256b3566e4d57a64bb349a7b896da10381a2a363;hp=3073294a18bb526138d24e6898325157726c9586;hpb=dc84f78e4b3c7f5c8384fbf5a6b538ac1826a604;p=public-inbox.git

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
old mode 100644
new mode 100755
index 3073294a..5cd08d49
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,5 +1,5 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2020 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
@@ -9,20 +9,25 @@ use strict;
 use warnings;
 use PublicInbox::Config;
 use PublicInbox::InboxWritable;
-use PublicInbox::MIME;
+use PublicInbox::Eml;
 use PublicInbox::Address;
 use PublicInbox::Spamcheck::Spamc;
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
+my %opt = (all => 0);
+GetOptions(\%opt, 'all') or die "bad command-line args\n";
+
 my $train = shift or die "usage: $usage\n";
 if ($train !~ /\A(?:ham|spam|rm)\z/) {
 	die "`$train' not recognized.\nusage: $usage\n";
 }
+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 <STDIN>;
+	my $data = <STDIN>;
 	$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 
 	if ($train ne 'rm') {
@@ -36,11 +41,11 @@ 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 +73,12 @@ sub remove_or_add ($$$) {
 }
 
 # 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);
 		$im->done;
 	});
 } else {
@@ -93,12 +98,12 @@ if ($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 $dests = PublicInbox::MDA->inboxes_for_list_id($pi_config, $mime);
 	for my $ibx (@$dests) {
-		next if !$seen{"$ibx"}++;
-		remove_or_add($ibx, $train, $ibx->{-primary_address});
+		next if $seen{"$ibx"}++;
+		remove_or_add($ibx, $train, $mime, $ibx->{-primary_address});
 	}
 }