learn: use "spam" as subject for removal commits

Sometimes an email is an innocent removal "rm" for a
misdirected, off-topic post, while most removed messages are
"spam".  Allow anybody to look at history and easily distinguish
the reason for removing the message.

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 31dc769583bd32777e2d25e16de743fd507a65c0..8c9d1cbad526a7d1e5dd3813f390685a0cd3713b 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -90,7 +90,7 @@ sub _check_path ($$$$) {
 # ('MISMATCH', msg) on mismatch
 # (:MARK, msg) on success
 sub remove {
-       my ($self, $mime) = @_; # mime = Email::MIME
+       my ($self, $mime, $msg) = @_; # mime = Email::MIME
 
        my $mid = mid_mime($mime);
        my $path = mid2path($mid);
@@ -138,10 +138,12 @@ sub remove {
        }
        my $ident = $self->{ident};
        my $now = now2822();
+       $msg ||= 'rm';
+       my $len = length($msg) + 1;
        print $w "commit $ref\nmark :$commit\n",
                "author $ident $now\n",
                "committer $ident $now\n",
-               "data 3\nrm\n\n",
+               "data $len\n$msg\n\n",
                'from ', ($parent ? $parent : $tip), "\n" or wfail;
        print $w "D $path\n\n" or wfail;
        $self->{nchg}++;

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 71aa50f9d5989b093b4efa50f4312267f8ce6440..75294a0a8e44e9368fc0b98d7db38d1d8a71152b 100755 (executable)
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -81,7 +81,7 @@ foreach my $recipient (keys %dests) {
                # 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: