From 29beb70160d15ffe46cb07e9d9468acfcda34db7 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Mon, 28 Oct 2019 10:45:19 +0000 Subject: [PATCH] learn: hoist out remove_or_add subroutine We'll be reusing it for List-ID processing in the next commit. --- script/public-inbox-learn | 56 ++++++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 25 deletions(-) diff --git a/script/public-inbox-learn b/script/public-inbox-learn index 299f75a0..56739f88 100755 --- 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') { $pi_config->each_inbox(sub { @@ -61,31 +89,9 @@ if ($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); - } - $im->done; + while (my ($addr, $ibx) = each %dests) { + next unless ref($ibx); # $ibx may be 0 + remove_or_add($ibx, $train, $addr); } } -- 2.44.0