X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=75294a0a8e44e9368fc0b98d7db38d1d8a71152b;hb=7174681c0165008ac16ed1d323f6d95b6d0570a3;hp=81675d0295e320057b8c1ded2dcc925f868e3f8a;hpb=dea396ae54867cc901d586c8af70d5f9fc14f1a8;p=public-inbox.git

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 81675d02..75294a0a 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -8,87 +8,93 @@ my $usage = "$0 (spam|ham) < /path/to/message";
 use strict;
 use warnings;
 use PublicInbox::Config;
-use Email::MIME;
-use Email::Address;
-use IPC::Run qw/run/;
+use PublicInbox::Git;
+use PublicInbox::Import;
+use PublicInbox::MIME;
+use Email::MIME::ContentType;
+$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
+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 {
+my $err;
+my $mime = PublicInbox::MIME->new(eval {
 	local $/;
 	my $data = scalar <STDIN>;
-	$data =~ s/\AFrom [^\r\n]*\r?\n//s;
+	$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+
+	if ($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
 });
 
 # 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;
+	my $val = $mime->header($h) or next;
+	foreach my $email (PublicInbox::Address::emails($val)) {
+		$dests{lc($email)} = 1;
 	}
 }
 
-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);
+if ($train eq 'spam') {
+	$pi_config->each_inbox(sub {
+		my ($ibx) = @_;
+		my $git = $ibx->git;
+		my $name = $ibx->{name};
+		my $addr = $ibx->{-primary_address};
+		my $im = PublicInbox::Import->new($git, $name, $addr, $ibx);
+		$im->remove($mime);
+		$im->done;
+	});
 }
 
-my $in = $mime->as_string;
-my $err = 0;
-my @output = qw(> /dev/null > /dev/null);
+require PublicInbox::MDA if $train eq "ham";
 
 # 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) = ("", "");
-
+	my $git = PublicInbox::Git->new($git_dir);
 	# 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") {
+	my $name = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
+	my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient;
+	my $im = PublicInbox::Import->new($git, $name, $email);
+
+	if ($train eq "spam" || $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
-		if (!run(["ssoma-rm", $git_dir], \$in, \$out, \$err)) {
-			if ($err !~ /^git cat-file .+ failed: 32768$/) {
-				$err = 1;
-			}
-		}
+		$im->remove($mime, $train);
 	} 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;
-
-		local $ENV{GIT_AUTHOR_NAME} = $name;
-		local $ENV{GIT_AUTHOR_EMAIL} = $email;
-		local $ENV{GIT_AUTHOR_DATE} = $date;
 
 		# 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;
-		}
-	}
-	if (!run([qw(spamc -L), $train], \$in, @output)) {
-		$err = 1;
+		$im->add($mime);
 	}
-
-	$err or eval {
-		require PublicInbox::SearchIdx;
-		PublicInbox::SearchIdx->new($git_dir, 2)->index_sync;
-	};
+	$im->done;
 }
 
-exit $err;
+if ($err) {
+	warn $err;
+	exit 1;
+}