X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=8b8e1b7732938bc8369813866fed9dad59ae6de6;hp=817fd5e9ca1f5f9f47ff7b1c1fdde96103f1e2ea;hb=refs%2Fheads%2Fmaster;hpb=975a1b174d40fd957ed869e9ff68f3c6dd6f37df

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 817fd5e9..8b8e1b77 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,93 +1,122 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# 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) < /path/to/message";
+my $help = <<EOF;
+usage: public-inbox-learn [OPTIONS] [spam|ham|rm] </path/to/RFC2822_message
+
+required action argument:
+
+   spam  unindex the message and train as spam
+     rm  remove the message without training as spam
+    ham  index the message (based on To:/Cc: headers) and train as ham
+
+options:
+
+  --all  scan all inboxes on `rm'
+
+See public-inbox-learn(1) man page for full documentation.
+EOF
 use strict;
-use warnings;
 use PublicInbox::Config;
-use PublicInbox::Git;
-use PublicInbox::Import;
-use Email::MIME;
-use Email::MIME::ContentType;
-$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
+use PublicInbox::InboxWritable;
+use PublicInbox::Eml;
 use PublicInbox::Address;
-use PublicInbox::Spawn qw(spawn);
-my $train = shift or die "usage: $usage\n";
-if ($train !~ /\A(?:ham|spam)\z/) {
-	die "`$train' not recognized.\nusage: $usage\n";
+use PublicInbox::Spamcheck::Spamc;
+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 "`$train' not recognized.\n$help";
 }
+die "--all only works with `rm'\n" if $opt{all} && $train ne 'rm';
 
-my $pi_config = PublicInbox::Config->new;
+my $spamc = PublicInbox::Spamcheck::Spamc->new;
+my $pi_cfg = PublicInbox::Config->new;
 my $err;
-my $mime = Email::MIME->new(eval {
-	local $/;
-	my $data = scalar <STDIN>;
-	$data =~ s/\AFrom [^\r\n]*\r?\n//s;
-	eval {
-		my @cmd = (qw(spamc -L), $train);
-		my ($r, $w);
-		pipe($r, $w) or die "pipe failed: $!";
-		open my $null, '>', '/dev/null' or
-					die "failed to open /dev/null: $!";
-		my $nullfd = fileno($null);
-		my %rdr = (0 => fileno($r), 1 => $nullfd, 2 => $nullfd);
-		my $pid = spawn(\@cmd, undef, \%rdr);
-		close $null;
-		close $r or die "close \$r failed: $!";
-		print $w $data or die "print \$w failed: $!";
-		close $w or die "close \$w failed: $!";
-		waitpid($pid, 0);
-		die "spamc failed with: $?\n" if $?;
-	};
-	$err = $@;
-	$data
-});
+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;
 
-# get all recipients
-my %dests;
-foreach my $h (qw(Cc To)) {
-	my $val = $mime->header($h) or next;
-	foreach my $email (PublicInbox::Address::emails($val)) {
-		$dests{lc($email)} = 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 = $@;
 	}
-}
+	\$data
+});
 
-require PublicInbox::MDA if $train eq "ham";
+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 $git = PublicInbox::Git->new($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);
 	}
 	$im->done;
-	eval {
-		require PublicInbox::SearchIdx;
-		PublicInbox::SearchIdx->new($git_dir, 2)->index_sync;
-	};
+}
+
+# spam is removed from all known inboxes since it is often Bcc:-ed
+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, $train);
+		$im->done;
+	});
+} else {
+	require PublicInbox::MDA;
+
+	# get all recipients
+	my %dests; # address => <PublicInbox::Inbox|0(false)>
+	for ($mime->header('Cc'), $mime->header('To')) {
+		foreach my $addr (PublicInbox::Address::emails($_)) {
+			$addr = lc($addr);
+			$dests{$addr} //= $pi_cfg->lookup($addr) // 0;
+		}
+	}
+
+	# 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_cfg, $mime);
+	for my $ibx (@$dests) {
+		next if $seen{"$ibx"}++;
+		remove_or_add($ibx, $train, $mime, $ibx->{-primary_address});
+	}
 }
 
 if ($err) {