X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=817fd5e9ca1f5f9f47ff7b1c1fdde96103f1e2ea;hb=975a1b174d40fd957ed869e9ff68f3c6dd6f37df;hp=c79f24790e32870478a31d6c5202fada392ca738;hpb=23a4e44bedabe5b8b651346cabc2a870c5377a30;p=public-inbox.git diff --git a/script/public-inbox-learn b/script/public-inbox-learn index c79f2479..817fd5e9 100755 --- a/script/public-inbox-learn +++ b/script/public-inbox-learn @@ -11,18 +11,38 @@ 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::Address; -use IPC::Run qw/run/; +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"; } my $pi_config = PublicInbox::Config->new; +my $err; my $mime = Email::MIME->new(eval { local $/; my $data = scalar ; $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 }); @@ -35,20 +55,12 @@ foreach my $h (qw(Cc To)) { } } -if ($train eq "ham") { - require PublicInbox::MDA; - require PublicInbox::Filter; - PublicInbox::Filter->run($mime); -} - -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. @@ -72,15 +84,13 @@ foreach my $recipient (keys %dests) { $im->add($mime); } $im->done; - my $in = $mime->as_string; - if (!run([qw(spamc -L), $train], \$in, @output)) { - $err = 1; - } - - $err or eval { + eval { require PublicInbox::SearchIdx; PublicInbox::SearchIdx->new($git_dir, 2)->index_sync; }; } -exit $err; +if ($err) { + warn $err; + exit 1; +}