X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=75294a0a8e44e9368fc0b98d7db38d1d8a71152b;hb=7174681c0165008ac16ed1d323f6d95b6d0570a3;hp=a696d348bd5cfc519a02cbb2c383672208a145ef;hpb=3fc59df0d633a17e0c5e43d633d12e8772c06ec3;p=public-inbox.git diff --git a/script/public-inbox-learn b/script/public-inbox-learn index a696d348..75294a0a 100755 --- a/script/public-inbox-learn +++ b/script/public-inbox-learn @@ -16,7 +16,7 @@ $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"; } @@ -27,15 +27,18 @@ my $mime = PublicInbox::MIME->new(eval { local $/; my $data = scalar ; $data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; - eval { - if ($train eq 'ham') { - $spamc->hamlearn(\$data); - } else { - $spamc->spamlearn(\$data); - } - die "spamc failed with: $?\n" if $?; - }; - $err = $@; + + if ($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 }); @@ -48,6 +51,18 @@ foreach my $h (qw(Cc To)) { } } +if ($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; + }); +} + require PublicInbox::MDA if $train eq "ham"; # n.b. message may be cross-posted to multiple public-inboxes @@ -61,12 +76,12 @@ foreach my $recipient (keys %dests) { my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient; my $im = PublicInbox::Import->new($git, $name, $email); - if ($train eq "spam") { + 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 - $im->remove($mime); + $im->remove($mime, $train); } else { # $train eq "ham" # no checking for spam here, we assume the message has # been reviewed by a human at this point: