examples/public-inbox.psgi: document ReverseProxy

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

diff --git a/public-inbox-learn b/public-inbox-learn
index d770f0f7b348fe82b23f04e62d14a405b5575d59..0c7b4199abeea2def7b452101ce83e4e24b9b7a1 100755 (executable)
--- a/public-inbox-learn
+++ b/public-inbox-learn
@@ -1,11 +1,14 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014, Eric Wong <normalperson@yhbt.net> and all contributors
+# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
 # License: AGPLv3 or later (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";
 use strict;
 use warnings;
 use PublicInbox::Config;
-use Email::Simple;
+use Email::MIME;
 use Email::Address;
 use IPC::Run qw/run/;
 my $train = shift or die "usage: $usage\n";
@@ -14,23 +17,26 @@ if ($train !~ /\A(?:ham|spam)\z/) {
 }
 
 my $pi_config = PublicInbox::Config->new;
-my $simple;
-{
-       local $/;
-       $simple = Email::Simple->new(<>);
-}
+my $mime = Email::MIME->new(eval { local $/; <> });
 
 # get all recipients
 my %dests;
 foreach my $h (qw(Cc To)) {
-       foreach my $recipient (Email::Address->parse($simple->header($h))) {
+       foreach my $recipient (Email::Address->parse($mime->header($h))) {
                $dests{lc($recipient->address)} = 1;
        }
 }
 
-my $in = $simple->as_string;
-$simple->body_set("");
+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);
 
@@ -54,19 +60,18 @@ foreach my $recipient (keys %dests) {
                        }
                }
        } else { # $train eq "ham"
-               my $from = $simple->header("From");
-               my @from = Email::Address->parse($from);
-               my $name = $from[0]->name;
-               defined $name or $name = "";
-               my $email = $from[0]->address;
-               defined $email or $email = "";
+               # no checking for spam here, we assume the message has
+               # been reviewed by a human at this point:
+               PublicInbox::MDA->set_list_headers($mime, $dst);
+               my $s  = $mime->as_string;
+
                local $ENV{GIT_AUTHOR_NAME} = $name;
                local $ENV{GIT_AUTHOR_EMAIL} = $email;
-               local $ENV{GIT_AUTHOR_DATE} = $simple->header("Date");
+               local $ENV{GIT_AUTHOR_DATE} = $date;
 
                # Ham messages are trained when they're marked into
-               # a SEEN state, so this is idempotent
-               run([qw(ssoma-mda -1), $git_dir], \$in, \$out, \$err);
+               # a SEEN state, so this is idempotent:
+               run([PublicInbox::MDA->cmd, $git_dir], \$s, \$out, \$err);
                if ($err !~ /CONFLICT/) {
                        $err = 1;
                }
@@ -74,5 +79,11 @@ foreach my $recipient (keys %dests) {
        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;