X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=ad1329859ce253304507046547667ad21c45464e;hb=ec294cdbc5392fdb136572dbcedb250798023703;hp=0c7b4199abeea2def7b452101ce83e4e24b9b7a1;hpb=052f26f3ada1042afa5acadbecc48b487f4e2d52;p=public-inbox.git

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 0c7b4199..ad132985 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,89 +1,95 @@
 #!/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) 2014-2019 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 $usage = "$0 <spam|ham|rm> </path/to/message";
 use strict;
 use warnings;
 use PublicInbox::Config;
-use Email::MIME;
-use Email::Address;
-use IPC::Run qw/run/;
+use PublicInbox::InboxWritable;
+use PublicInbox::MIME;
+use PublicInbox::Address;
+use PublicInbox::Spamcheck::Spamc;
 my $train = shift or die "usage: $usage\n";
-if ($train !~ /\A(?:ham|spam)\z/) {
+if ($train !~ /\A(?:ham|spam|rm)\z/) {
 	die "`$train' not recognized.\nusage: $usage\n";
 }
 
+my $spamc = PublicInbox::Spamcheck::Spamc->new;
 my $pi_config = PublicInbox::Config->new;
-my $mime = Email::MIME->new(eval { local $/; <> });
+my $err;
+my $mime = PublicInbox::MIME->new(eval {
+	local $/;
+	my $data = scalar <STDIN>;
+	$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 
-# get all recipients
-my %dests;
-foreach my $h (qw(Cc To)) {
-	foreach my $recipient (Email::Address->parse($mime->header($h))) {
-		$dests{lc($recipient->address)} = 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 = $@;
 	}
-}
-
-my ($name, $email, $date);
-
-if ($train eq "ham") {
-	require PublicInbox::MDA;
-	require PublicInbox::Filter;
-	PublicInbox::Filter->run($mime);
-	($name, $email, $date) = PublicInbox::MDA->author_info($mime);
-}
-
-my $in = $mime->as_string;
-my $err = 0;
-my @output = qw(> /dev/null > /dev/null);
+	$data
+});
 
-# 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 = $dst->{mainrepo} or next;
-	my ($out, $err) = ("", "");
+# spam is removed from all known inboxes since it is often Bcc:-ed
+if ($train eq 'spam') {
+	$pi_config->each_inbox(sub {
+		my ($ibx) = @_;
+		$ibx = PublicInbox::InboxWritable->new($ibx);
+		my $im = $ibx->importer(0);
+		$im->remove($mime, 'spam');
+		$im->done;
+	});
+} else {
+	require PublicInbox::MDA if $train eq "ham";
 
-	# We do not touch GIT_COMMITTER_* env here so we can track
-	# who trained the message.
-	# We will not touch GIT_AUTHOR_* when learning spam messages, either
-	if ($train eq "spam") {
-		# 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
-		if (!run(["ssoma-rm", $git_dir], \$in, \$out, \$err)) {
-			if ($err !~ /^git cat-file .+ failed: 32768$/) {
-				$err = 1;
-			}
+	# get all recipients
+	my %dests; # address => <PublicInbox::Inbox|0(false)>
+	for ($mime->header('Cc'), $mime->header('To')) {
+		foreach my $addr (PublicInbox::Address::emails($_)) {
+			$addr = lc($addr);
+			$dests{$addr} //= $pi_config->lookup($addr) // 0;
 		}
-	} else { # $train eq "ham"
-		# no checking for spam here, we assume the message has
-		# been reviewed by a human at this point:
-		PublicInbox::MDA->set_list_headers($mime, $dst);
-		my $s  = $mime->as_string;
+	}
+
+	# n.b. message may be cross-posted to multiple public-inboxes
+	while (my ($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);
 
-		local $ENV{GIT_AUTHOR_NAME} = $name;
-		local $ENV{GIT_AUTHOR_EMAIL} = $email;
-		local $ENV{GIT_AUTHOR_DATE} = $date;
+		if ($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:
-		run([PublicInbox::MDA->cmd, $git_dir], \$s, \$out, \$err);
-		if ($err !~ /CONFLICT/) {
-			$err = 1;
+			# Ham messages are trained when they're marked into
+			# a SEEN state, so this is idempotent:
+			$im->add($mime);
 		}
+		$im->done;
 	}
-	if (!run([qw(spamc -L), $train], \$in, @output)) {
-		$err = 1;
-	}
-
-	$err or eval {
-		require PublicInbox::SearchIdx;
-		PublicInbox::SearchIdx->new($git_dir, 2)->index_sync;
-	};
 }
 
-exit $err;
+if ($err) {
+	warn $err;
+	exit 1;
+}