-# Copyright (C) 2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# ref: https://cr.yp.to/proto/maildir.html
use strict;
use warnings;
use PublicInbox::MIME;
-use Email::MIME::ContentType;
-$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
use PublicInbox::Git;
use PublicInbox::Import;
use PublicInbox::MDA;
use PublicInbox::Spawn qw(spawn);
+use PublicInbox::InboxWritable;
+use File::Temp qw//;
sub new {
my ($class, $config) = @_;
- my (%mdmap, @mdir, $spamc);
+ my (%mdmap, @mdir, $spamc, $spamdir);
# "publicinboxwatch" is the documented namespace
# "publicinboxlearn" is legacy but may be supported
# indefinitely...
foreach my $pfx (qw(publicinboxwatch publicinboxlearn)) {
my $k = "$pfx.watchspam";
- if (my $spamdir = $config->{$k}) {
- if ($spamdir =~ s/\Amaildir://) {
- $spamdir =~ s!/+\z!!;
+ if (my $dir = $config->{$k}) {
+ if ($dir =~ s/\Amaildir://) {
+ $dir =~ s!/+\z!!;
# skip "new", no MUA has seen it, yet.
- my $cur = "$spamdir/cur";
+ my $cur = "$dir/cur";
+ $spamdir = $cur;
push @mdir, $cur;
$mdmap{$cur} = 'watchspam';
} else {
- warn "unsupported $k=$spamdir\n";
+ warn "unsupported $k=$dir\n";
}
}
}
$spamcheck = undef;
}
}
+
+ # need to make all inboxes writable for spam removal:
+ $config->each_inbox(sub { PublicInbox::InboxWritable->new($_[0]) });
+
foreach $k (keys %$config) {
$k =~ /\Apublicinbox\.([^\.]+)\.watch\z/ or next;
my $name = $1;
$mdre = qr!\A($mdre)/!;
bless {
spamcheck => $spamcheck,
+ spamdir => $spamdir,
mdmap => \%mdmap,
mdir => \@mdir,
mdre => $mdre,
config => $config,
importers => {},
+ opendirs => {}, # dirname => dirhandle (in progress scans)
}, $class;
}
sub _done_for_now {
- $_->done foreach values %{$_[0]->{importers}};
+ my ($self) = @_;
+ my $importers = $self->{importers};
+ foreach my $im (values %$importers) {
+ $im->done;
+ }
}
sub _try_fsn_paths {
- my ($self, $paths) = @_;
- _try_path($self, $_->{path}) foreach @$paths;
+ my ($self, $scan_re, $paths) = @_;
+ foreach (@$paths) {
+ my $path = $_->{path};
+ if ($path =~ $scan_re) {
+ scan($self, $path);
+ } else {
+ _try_path($self, $path);
+ }
+ }
_done_for_now($self);
}
# path must be marked as (S)een
$path =~ /:2,[A-R]*S[T-Za-z]*\z/ or return;
my $mime = _path_to_mime($path) or return;
- _force_mid($mime);
$self->{config}->each_inbox(sub {
my ($ibx) = @_;
eval {
my $im = _importer_for($self, $ibx);
- $im->remove($mime);
- if (my $scrub = _scrubber_for($ibx)) {
+ $im->remove($mime, 'spam');
+ if (my $scrub = $ibx->filter) {
my $scrubbed = $scrub->scrub($mime) or return;
$scrubbed == 100 and return;
- $im->remove($scrubbed);
+ $im->remove($scrubbed, 'spam');
}
};
if ($@) {
})
}
-# used to hash the relevant portions of a message when there are conflicts
-sub _hash_mime2 {
- my ($mime) = @_;
- require Digest::SHA;
- my $dig = Digest::SHA->new('SHA-1');
- $dig->add($mime->header_obj->header_raw('Subject'));
- $dig->add($mime->body_raw);
- $dig->hexdigest;
-}
-
-sub _force_mid {
- my ($mime) = @_;
- # probably a bad idea, but we inject a Message-Id if
- # one is missing, here..
- my $mid = $mime->header_obj->header_raw('Message-Id');
- if (!defined $mid || $mid =~ /\A\s*\z/) {
- $mid = '<' . _hash_mime2($mime) . '@generated>';
- $mime->header_set('Message-Id', $mid);
- }
-}
-
sub _try_path {
my ($self, $path) = @_;
my @p = split(m!/+!, $path);
- return if $p[-1] !~ /\A[a-zA-Z0-9][\w:,=\.]+\z/;
+ return if $p[-1] !~ /\A[a-zA-Z0-9][\-\w:,=\.]+\z/;
if ($p[-1] =~ /:2,([A-Z]+)\z/i) {
my $flags = $1;
return if $flags =~ /[DT]/; # no [D]rafts or [T]rashed mail
my $v = $mime->header_obj->header_raw($wm->[0]);
return unless ($v && $v =~ $wm->[1]);
}
- if (my $scrub = _scrubber_for($inbox)) {
+ if (my $scrub = $inbox->filter) {
my $ret = $scrub->scrub($mime) or return;
$ret == 100 and return;
$mime = $ret;
}
- _force_mid($mime);
$im->add($mime, $self->{spamcheck});
}
+sub quit { trigger_scan($_[0], 'quit') }
+
sub watch {
my ($self) = @_;
- my $cb = sub { _try_fsn_paths($self, \@_) };
- my $mdir = $self->{mdir};
+ my $scan = File::Temp->newdir("public-inbox-watch.$$.scan.XXXXXX",
+ TMPDIR => 1);
+ my $scandir = $self->{scandir} = $scan->dirname;
+ my $re = qr!\A$scandir/!;
+ my $cb = sub { _try_fsn_paths($self, $re, \@_) };
# lazy load here, we may support watching via IMAP IDLE
# in the future...
require Filesys::Notify::Simple;
- my $watcher = Filesys::Notify::Simple->new($mdir);
- $watcher->wait($cb) while (1);
+ my $fsn = Filesys::Notify::Simple->new([@{$self->{mdir}}, $scandir]);
+ $fsn->wait($cb) until $self->{quit};
+}
+
+sub trigger_scan {
+ my ($self, $base) = @_;
+ my $dir = $self->{scandir} or return;
+ open my $fh, '>', "$dir/$base" or die "open $dir/$base failed: $!\n";
+ close $fh or die "close $dir/$base failed: $!\n";
}
sub scan {
- my ($self) = @_;
- my $mdir = $self->{mdir};
- foreach my $dir (@$mdir) {
- my $ok = opendir(my $dh, $dir);
- unless ($ok) {
- warn "failed to open $dir: $!\n";
- next;
- }
+ my ($self, $path) = @_;
+ if ($path =~ /quit\z/) {
+ %{$self->{opendirs}} = ();
+ _done_for_now($self);
+ delete $self->{scandir};
+ $self->{quit} = 1;
+ return;
+ }
+ # else: $path =~ /(cont|full)\z/
+ return if $self->{quit};
+ my $max = 10;
+ my $opendirs = $self->{opendirs};
+ my @dirnames = keys %$opendirs;
+ foreach my $dir (@dirnames) {
+ my $dh = delete $opendirs->{$dir};
+ my $n = $max;
while (my $fn = readdir($dh)) {
_try_path($self, "$dir/$fn");
+ last if --$n < 0;
+ }
+ $opendirs->{$dir} = $dh if $n < 0;
+ }
+ if ($path =~ /full\z/) {
+ foreach my $dir (@{$self->{mdir}}) {
+ next if $opendirs->{$dir}; # already in progress
+ my $ok = opendir(my $dh, $dir);
+ unless ($ok) {
+ warn "failed to open $dir: $!\n";
+ next;
+ }
+ my $n = $max;
+ while (my $fn = readdir($dh)) {
+ _try_path($self, "$dir/$fn");
+ last if --$n < 0;
+ }
+ $opendirs->{$dir} = $dh if $n < 0;
}
- closedir $dh;
}
_done_for_now($self);
+ # do we have more work to do?
+ trigger_scan($self, 'cont') if keys %$opendirs;
}
sub _path_to_mime {
}
sub _importer_for {
- my ($self, $inbox) = @_;
- my $im = $inbox->{-import} ||= eval {
- my $git = $inbox->git;
- my $name = $inbox->{name};
- my $addr = $inbox->{-primary_address};
- PublicInbox::Import->new($git, $name, $addr, $inbox);
- };
-
+ my ($self, $ibx) = @_;
+ my $im = $ibx->importer(0);
my $importers = $self->{importers};
if (scalar(keys(%$importers)) > 2) {
delete $importers->{"$im"};
$importers->{"$im"} = $im;
}
-sub _scrubber_for {
- my ($inbox) = @_;
- my $f = $inbox->{filter};
- if ($f && $f =~ /::/) {
- my @args = (-inbox => $inbox);
- # basic line splitting, only
- # Perhaps we can have proper quote splitting one day...
- ($f, @args) = split(/\s+/, $f) if $f =~ /\s+/;
-
- eval "require $f";
- if ($@) {
- warn $@;
- } else {
- # e.g: PublicInbox::Filter::Vger->new(@args)
- return $f->new(@args);
- }
- }
- undef;
-}
-
sub _spamcheck_cb {
my ($sc) = @_;
sub {