X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=79f3ead5c722cda3d17cea9f4fc8ea185fa39530;hb=d1525c3b35e9aa1bb14143996a7fa2b6e34cba3e;hp=299f75a0e58ae319d6e46ee068db1f20c1af10dd;hpb=b1e4d474efcccaa5c5b5e71aac75c8f7836f1d91;p=public-inbox.git diff --git a/script/public-inbox-learn b/script/public-inbox-learn old mode 100755 new mode 100644 index 299f75a0..79f3ead5 --- a/script/public-inbox-learn +++ b/script/public-inbox-learn @@ -39,6 +39,34 @@ my $mime = PublicInbox::MIME->new(eval { $data }); +sub remove_or_add ($$$) { + my ($ibx, $train, $addr) = @_; + + # We do not touch GIT_COMMITTER_* env here so we can track + # who trained the message. + $ibx->{name} = $ENV{GIT_COMMITTER_NAME} // $ibx->{name}; + $ibx->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} // $addr; + $ibx = PublicInbox::InboxWritable->new($ibx); + my $im = $ibx->importer(0); + + if ($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, $ibx); + + # Ham messages are trained when they're marked into + # a SEEN state, so this is idempotent: + $im->add($mime); + } + $im->done; +} + # spam is removed from all known inboxes since it is often Bcc:-ed if ($train eq 'spam') { $pi_config->each_inbox(sub { @@ -49,7 +77,7 @@ if ($train eq 'spam') { $im->done; }); } else { - require PublicInbox::MDA if $train eq "ham"; + require PublicInbox::MDA; # get all recipients my %dests; # address => @@ -61,31 +89,15 @@ if ($train eq 'spam') { } # 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 = $dst->importer(0); - - if ($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: - $im->add($mime); - } - $im->done; + my %seen; + while (my ($addr, $ibx) = each %dests) { + next unless ref($ibx); # $ibx may be 0 + next if $seen{"$ibx"}++; + remove_or_add($ibx, $train, $addr); + } + my $ibx = PublicInbox::MDA->inbox_for_list_id($pi_config, $mime); + if ($ibx && !$seen{"$ibx"}) { + remove_or_add($ibx, $train, $ibx->{-primary_address}); } }