X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=8b8e1b7732938bc8369813866fed9dad59ae6de6;hp=0c7b4199abeea2def7b452101ce83e4e24b9b7a1;hb=refs%2Fheads%2Fmaster;hpb=052f26f3ada1042afa5acadbecc48b487f4e2d52 diff --git a/script/public-inbox-learn b/script/public-inbox-learn index 0c7b4199..8b8e1b77 100755 --- a/script/public-inbox-learn +++ b/script/public-inbox-learn @@ -1,89 +1,125 @@ #!/usr/bin/perl -w -# Copyright (C) 2014-2015 all contributors -# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt) +# Copyright (C) 2014-2021 all contributors +# License: AGPL-3.0+ # # Used for training spam (via SpamAssassin) and removing messages from a # public-inbox -my $usage = "$0 (spam|ham) < /path/to/message"; -use strict; -use warnings; -use PublicInbox::Config; -use Email::MIME; -use Email::Address; -use IPC::Run qw/run/; -my $train = shift or die "usage: $usage\n"; -if ($train !~ /\A(?:ham|spam)\z/) { - die "`$train' not recognized.\nusage: $usage\n"; -} +my $help = <new; -my $mime = Email::MIME->new(eval { local $/; <> }); +required action argument: -# get all recipients -my %dests; -foreach my $h (qw(Cc To)) { - foreach my $recipient (Email::Address->parse($mime->header($h))) { - $dests{lc($recipient->address)} = 1; - } -} + spam unindex the message and train as spam + rm remove the message without training as spam + ham index the message (based on To:/Cc: headers) and train as ham -my ($name, $email, $date); +options: -if ($train eq "ham") { - require PublicInbox::MDA; - require PublicInbox::Filter; - PublicInbox::Filter->run($mime); - ($name, $email, $date) = PublicInbox::MDA->author_info($mime); + --all scan all inboxes on `rm' + +See public-inbox-learn(1) man page for full documentation. +EOF +use strict; +use PublicInbox::Config; +use PublicInbox::InboxWritable; +use PublicInbox::Eml; +use PublicInbox::Address; +use PublicInbox::Spamcheck::Spamc; +use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev); +my %opt = (all => 0); +GetOptions(\%opt, qw(all help|h)) or die $help; + +my $train = shift or die $help; +if ($train !~ /\A(?:ham|spam|rm)\z/) { + die "`$train' not recognized.\n$help"; } +die "--all only works with `rm'\n" if $opt{all} && $train ne 'rm'; -my $in = $mime->as_string; -my $err = 0; -my @output = qw(> /dev/null > /dev/null); +my $spamc = PublicInbox::Spamcheck::Spamc->new; +my $pi_cfg = PublicInbox::Config->new; +my $err; +my $mime = PublicInbox::Eml->new(do{ + defined(my $data = do { local $/; }) or die "read STDIN: $!\n"; + $data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; + + if ($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 +}); -# n.b. message may be cross-posted to multiple public-inboxes -foreach my $recipient (keys %dests) { - my $dst = $pi_config->lookup($recipient) or next; - my $git_dir = $dst->{mainrepo} or next; - my ($out, $err) = ("", ""); +sub remove_or_add ($$$$) { + my ($ibx, $train, $mime, $addr) = @_; # We do not touch GIT_COMMITTER_* env here so we can track # who trained the message. - # We will not touch GIT_AUTHOR_* when learning spam messages, either - if ($train eq "spam") { + $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 - if (!run(["ssoma-rm", $git_dir], \$in, \$out, \$err)) { - if ($err !~ /^git cat-file .+ failed: 32768$/) { - $err = 1; - } - } - } else { # $train eq "ham" + $im->remove($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); - my $s = $mime->as_string; - - local $ENV{GIT_AUTHOR_NAME} = $name; - local $ENV{GIT_AUTHOR_EMAIL} = $email; - local $ENV{GIT_AUTHOR_DATE} = $date; + PublicInbox::MDA->set_list_headers($mime, $ibx); # 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); } - if (!run([qw(spamc -L), $train], \$in, @output)) { - $err = 1; + $im->done; +} + +# spam is removed from all known inboxes since it is often Bcc:-ed +if ($train eq 'spam' || ($train eq 'rm' && $opt{all})) { + $pi_cfg->each_inbox(sub { + my ($ibx) = @_; + $ibx = PublicInbox::InboxWritable->new($ibx); + my $im = $ibx->importer(0); + $im->remove($mime, $train); + $im->done; + }); +} else { + require PublicInbox::MDA; + + # get all recipients + my %dests; # address => + for ($mime->header('Cc'), $mime->header('To')) { + foreach my $addr (PublicInbox::Address::emails($_)) { + $addr = lc($addr); + $dests{$addr} //= $pi_cfg->lookup($addr) // 0; + } } - $err or eval { - require PublicInbox::SearchIdx; - PublicInbox::SearchIdx->new($git_dir, 2)->index_sync; - }; + # n.b. message may be cross-posted to multiple public-inboxes + 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, $mime, $addr); + } + my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_cfg, $mime); + for my $ibx (@$dests) { + next if $seen{"$ibx"}++; + remove_or_add($ibx, $train, $mime, $ibx->{-primary_address}); + } } -exit $err; +if ($err) { + warn $err; + exit 1; +}