diff options
author | Eric Wong <e@80x24.org> | 2016-04-25 09:50:01 +0000 |
---|---|---|
committer | Eric Wong <e@80x24.org> | 2016-04-25 09:50:32 +0000 |
commit | fe3d2447badd595df784541556311137b920b0a2 (patch) | |
tree | 6e37ab61406654680fd6757593cf810370055ecb /script/public-inbox-learn | |
parent | 51c59323fffbfbb6ebc60f58da905e88ac323da5 (diff) | |
download | public-inbox-fe3d2447badd595df784541556311137b920b0a2.tar.gz |
By converting to using ourt git-fast-import-based Import module. This should allow us to be more easily installed.
Diffstat (limited to 'script/public-inbox-learn')
-rwxr-xr-x | script/public-inbox-learn | 31 |
1 files changed, 11 insertions, 20 deletions
diff --git a/script/public-inbox-learn b/script/public-inbox-learn index 81675d02..0af1e94c 100755 --- a/script/public-inbox-learn +++ b/script/public-inbox-learn @@ -8,6 +8,8 @@ my $usage = "$0 (spam|ham) < /path/to/message"; use strict; use warnings; use PublicInbox::Config; +use PublicInbox::Git; +use PublicInbox::Import; use Email::MIME; use Email::Address; use IPC::Run qw/run/; @@ -32,16 +34,12 @@ foreach my $h (qw(Cc To)) { } } -my ($name, $email, $date); - if ($train eq "ham") { require PublicInbox::MDA; require PublicInbox::Filter; PublicInbox::Filter->run($mime); - ($name, $email, $date) = PublicInbox::MDA->author_info($mime); } -my $in = $mime->as_string; my $err = 0; my @output = qw(> /dev/null > /dev/null); @@ -50,37 +48,30 @@ 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. - # We will not touch GIT_AUTHOR_* when learning spam messages, either + my $name = $ENV{GIT_COMMITTER_NAME} || $dst->{listname}; + my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient; + my $im = PublicInbox::Import->new($git, $name, $email); + if ($train eq "spam") { # 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 - if (!run(["ssoma-rm", $git_dir], \$in, \$out, \$err)) { - if ($err !~ /^git cat-file .+ failed: 32768$/) { - $err = 1; - } - } + $im->remove($mime); } else { # $train eq "ham" # no checking for spam here, we assume the message has # been reviewed by a human at this point: PublicInbox::MDA->set_list_headers($mime, $dst); - my $s = $mime->as_string; - - local $ENV{GIT_AUTHOR_NAME} = $name; - local $ENV{GIT_AUTHOR_EMAIL} = $email; - local $ENV{GIT_AUTHOR_DATE} = $date; # Ham messages are trained when they're marked into # a SEEN state, so this is idempotent: - run([PublicInbox::MDA->cmd, $git_dir], \$s, \$out, \$err); - if ($err !~ /CONFLICT/) { - $err = 1; - } + $im->add($mime); } + $im->done; + my $in = $mime->as_string; if (!run([qw(spamc -L), $train], \$in, @output)) { $err = 1; } |