sub new {
my ($class, $config) = @_;
- my (%mdmap, @mdir, $spamc);
- my %uniq; # directory => count
- my %imap; # url => [inbox objects] or 'watchspam'
+ my (%mdmap, $spamc);
+ my (%imap, %nntp); # url => [inbox objects] or 'watchspam'
# "publicinboxwatch" is the documented namespace
# "publicinboxlearn" is legacy but may be supported
foreach my $pfx (qw(publicinboxwatch publicinboxlearn)) {
my $k = "$pfx.watchspam";
defined(my $dirs = $config->{$k}) or next;
- $dirs = [ $dirs ] if !ref($dirs);
+ $dirs = PublicInbox::Config::_array($dirs);
for my $dir (@$dirs) {
+ my $url;
if (is_maildir($dir)) {
# skip "new", no MUA has seen it, yet.
- my $cur = "$dir/cur";
- push @mdir, $cur;
- $uniq{$cur}++;
- $mdmap{$cur} = 'watchspam';
- } elsif (my $url = imap_url($dir)) {
+ $mdmap{"$dir/cur"} = 'watchspam';
+ } elsif ($url = imap_url($dir)) {
$imap{$url} = 'watchspam';
+ } elsif ($url = nntp_url($dir)) {
+ $nntp{$url} = 'watchspam';
} else {
warn "unsupported $k=$dir\n";
}
# need to make all inboxes writable for spam removal:
my $ibx = $_[0] = PublicInbox::InboxWritable->new($_[0]);
- my $watch = $ibx->{watch} or return;
- if (is_maildir($watch)) {
- compile_watchheaders($ibx);
- my ($new, $cur) = ("$watch/new", "$watch/cur");
- return if is_watchspam($cur, $mdmap{$cur}, $ibx);
- push @mdir, $new unless $uniq{$new}++;
- push @mdir, $cur unless $uniq{$cur}++;
- push @{$mdmap{$new} ||= []}, $ibx;
- push @{$mdmap{$cur} ||= []}, $ibx;
- } elsif (my $url = imap_url($watch)) {
- return if is_watchspam($url, $imap{$url}, $ibx);
- compile_watchheaders($ibx);
- push @{$imap{$url} ||= []}, $ibx;
- } else {
- warn "watch unsupported: $k=$watch\n";
+ my $watches = $ibx->{watch} or return;
+ $watches = PublicInbox::Config::_array($watches);
+ for my $watch (@$watches) {
+ my $url;
+ if (is_maildir($watch)) {
+ compile_watchheaders($ibx);
+ my ($new, $cur) = ("$watch/new", "$watch/cur");
+ my $cur_dst = $mdmap{$cur} //= [];
+ return if is_watchspam($cur, $cur_dst, $ibx);
+ push @{$mdmap{$new} //= []}, $ibx;
+ push @$cur_dst, $ibx;
+ } elsif ($url = imap_url($watch)) {
+ return if is_watchspam($url, $imap{$url}, $ibx);
+ compile_watchheaders($ibx);
+ push @{$imap{$url} ||= []}, $ibx;
+ } elsif ($url = nntp_url($watch)) {
+ return if is_watchspam($url, $nntp{$url}, $ibx);
+ compile_watchheaders($ibx);
+ push @{$nntp{$url} ||= []}, $ibx;
+ } else {
+ warn "watch unsupported: $k=$watch\n";
+ }
}
});
- return unless scalar(@mdir) || scalar(keys %imap);
my $mdre;
- if (@mdir) {
- $mdre = join('|', map { quotemeta($_) } @mdir);
+ if (scalar keys %mdmap) {
+ $mdre = join('|', map { quotemeta($_) } keys %mdmap);
$mdre = qr!\A($mdre)/!;
}
+ return unless $mdre || scalar(keys %imap) || scalar(keys %nntp);
+
bless {
spamcheck => $spamcheck,
mdmap => \%mdmap,
- mdir => \@mdir,
mdre => $mdre,
config => $config,
imap => scalar keys %imap ? \%imap : undef,
+ nntp => scalar keys %nntp? \%nntp : undef,
importers => {},
opendirs => {}, # dirname => dirhandle (in progress scans)
ops => [], # 'quit', 'full'
if (my $imap_pid = $self->{-imap_pid}) {
kill('QUIT', $imap_pid);
}
- if (my $idle_pids = $self->{idle_pids}) {
- kill('QUIT', $_) for (keys %$idle_pids);
+ for (qw(idle_pids poll_pids)) {
+ my $pids = $self->{$_} or next;
+ kill('QUIT', $_) for (keys %$pids);
}
if (my $idle_mic = $self->{idle_mic}) {
eval { $idle_mic->done };
- warn "IDLE DONE error: $@\n" if $@;
- eval { $idle_mic->disconnect };
- warn "IDLE LOGOUT error: $@\n" if $@;
+ if ($@) {
+ warn "IDLE DONE error: $@\n";
+ eval { $idle_mic->disconnect };
+ warn "IDLE LOGOUT error: $@\n" if $@;
+ }
}
}
$self->{done_timer} //= PublicInbox::DS::requeue($done);
};
require PublicInbox::DirIdle;
- PublicInbox::DirIdle->new($self->{mdir}, $cb); # EPOLL_CTL_ADD
+ # inotify_create + EPOLL_CTL_ADD
+ PublicInbox::DirIdle->new([keys %{$self->{mdmap}}], $cb);
}
# returns the git config section name, e.g [imap "imaps://user@example.com"]
# without the mailbox, so we can share connections between different inboxes
-sub imap_section ($) {
+sub uri_section ($) {
my ($uri) = @_;
$uri->scheme . '://' . $uri->authority;
}
-sub cfg_intvl ($$) {
- my ($cfg, $key) = @_;
- defined(my $v = $cfg->{lc($key)}) or return;
- $v =~ /\A[0-9]+\z/s and return $v + 0;
+sub cfg_intvl ($$$) {
+ my ($cfg, $key, $url) = @_;
+ my $v = $cfg->urlmatch($key, $url) // return;
+ $v =~ /\A[0-9]+(?:\.[0-9]+)?\z/s and return $v + 0;
if (ref($v) eq 'ARRAY') {
$v = join(', ', @$v);
warn "W: $key has multiple values: $v\nW: $key ignored\n";
} else {
- warn "W: $key=$v is not an integer value in seconds\n";
+ warn "W: $key=$v is not a numeric value in seconds\n";
}
}
+sub cfg_bool ($$$) {
+ my ($cfg, $key, $url) = @_;
+ my $orig = $cfg->urlmatch($key, $url) // return;
+ my $bool = PublicInbox::Config::_git_config_bool($orig);
+ warn "W: $key=$orig for $url is not boolean\n" unless defined($bool);
+ $bool;
+}
+
# flesh out common IMAP-specific data structures
sub imap_common_init ($) {
my ($self) = @_;
my $mic_args = {}; # scheme://authority => Mail:IMAPClient arg
for my $url (sort keys %{$self->{imap}}) {
my $uri = PublicInbox::URIimap->new($url);
- my $sec = imap_section($uri);
+ my $sec = uri_section($uri);
for my $k (qw(Starttls Debug Compress)) {
- my $key = lc("imap.$sec.$k");
- defined(my $orig = $cfg->{$key}) or next;
- my $v = PublicInbox::Config::_git_config_bool($orig);
- if (defined($v)) {
- $mic_args->{$sec}->{$k} = $v;
- } else {
- warn "W: $key=$orig is not boolean\n";
- }
+ my $bool = cfg_bool($cfg, "imap.$k", $url) // next;
+ $mic_args->{$sec}->{$k} = $bool;
}
- my $to = cfg_intvl($cfg, "imap.$sec.Timeout");
+ my $to = cfg_intvl($cfg, 'imap.timeout', $url);
$mic_args->{$sec}->{Timeout} = $to if $to;
- $to = cfg_intvl($cfg, "imap.$sec.PollInterval");
- $self->{imap_opt}->{$sec}->{poll_intvl} = $to if $to;
- $to = cfg_intvl($cfg, "imap.$sec.IdleInterval");
- $self->{imap_opt}->{$sec}->{idle_intvl} = $to if $to;
+ for my $k (qw(pollInterval idleInterval)) {
+ $to = cfg_intvl($cfg, "imap.$k", $url) // next;
+ $self->{imap_opt}->{$sec}->{$k} = $to;
+ }
+ my $k = 'imap.fetchBatchSize';
+ my $bs = $cfg->urlmatch($k, $url) // next;
+ if ($bs =~ /\A([0-9]+)\z/) {
+ $self->{imap_opt}->{$sec}->{batch_size} = $bs;
+ } else {
+ warn "$k=$bs is not an integer\n";
+ }
}
$mic_args;
}
username => $uri->user,
password => $uri->password,
};
- my $common = $mic_args->{imap_section($uri)} // {};
+ my $common = $mic_args->{uri_section($uri)} // {};
my $host = $cred->{host};
my $mic_arg = {
Port => $uri->port,
}
if ($mic->login && $mic->IsAuthenticated) {
# success! keep IMAPClient->new arg in case we get disconnected
- $self->{mic_arg}->{imap_section($uri)} = $mic_arg;
+ $self->{mic_arg}->{uri_section($uri)} = $mic_arg;
} else {
warn "E: <$url> LOGIN: $@\n";
$mic = undef;
$mic;
}
+sub imap_import_msg ($$$$) {
+ my ($self, $url, $uid, $raw) = @_;
+ # our target audience expects LF-only, save storage
+ $$raw =~ s/\r\n/\n/sg;
+
+ my $inboxes = $self->{imap}->{$url};
+ if (ref($inboxes)) {
+ for my $ibx (@$inboxes) {
+ my $eml = PublicInbox::Eml->new($$raw);
+ my $x = import_eml($self, $ibx, $eml);
+ }
+ } elsif ($inboxes eq 'watchspam') {
+ my $eml = PublicInbox::Eml->new($raw);
+ my $arg = [ $self, $eml, "$url UID:$uid" ];
+ $self->{config}->each_inbox(\&remove_eml_i, $arg);
+ } else {
+ die "BUG: destination unknown $inboxes";
+ }
+}
+
sub imap_fetch_all ($$$) {
my ($self, $mic, $uri) = @_;
- my $sec = imap_section($uri);
+ my $sec = uri_section($uri);
my $mbx = $uri->mailbox;
my $url = $uri->as_string;
$mic->Clear(1); # trim results history
return "E: $url cannot get UIDVALIDITY";
$r_uidnext //= $mic->uidnext($mbx) //
return "E: $url cannot get UIDNEXT";
- my $itrk = PublicInbox::IMAPTracker->new;
- my ($l_uidval, $l_uid) = $itrk->get_last($url);
+ my $itrk = PublicInbox::IMAPTracker->new($url);
+ my ($l_uidval, $l_uid) = $itrk->get_last;
$l_uidval //= $r_uidval; # first time
$l_uid //= 1;
if ($l_uidval != $r_uidval) {
}
return if $l_uid >= $r_uid; # nothing to do
+ warn "I: $url fetching UID $l_uid:$r_uid\n";
$mic->Uid(1); # the default, we hope
+ my $bs = $self->{imap_opt}->{$sec}->{batch_size} // 1;
my $req = $mic->imap4rev1 ? 'BODY.PEEK[]' : 'RFC822.PEEK';
+
+ # TODO: FLAGS may be useful for personal use
my $key = $req;
$key =~ s/\.PEEK//;
- my $inboxes = $self->{imap}->{$url};
- warn "I: $url fetching $l_uid..$r_uid\n";
- my $uid = -1;
+ my ($uids, $batch);
my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
local $SIG{__WARN__} = sub {
- $warn_cb->("$url UID:$uid\n");
+ $batch //= '?';
+ $warn_cb->("$url UID:$batch\n");
$warn_cb->(@_);
};
my $err;
- $itrk->{dbh}->begin_work;
- for my $u ($l_uid..$r_uid) {
- $uid = $u;
- local $0 = "UID:$uid $mbx $sec";
- my $r = $mic->fetch_hash($uid, $req);
- unless ($r) { # network error?
- $err = "E: $url UID FETCH $uid error: $!\n";
- last;
- }
+ do {
+ # I wish "UID FETCH $START:*" could work, but:
+ # 1) servers do not need to return results in any order
+ # 2) Mail::IMAPClient doesn't offer a streaming API
+ $uids = $mic->search("UID $l_uid:*") or
+ return "E: $url UID SEARCH $l_uid:* error: $!";
+ return if scalar(@$uids) == 0;
- # messages get deleted, so holes appear
- defined(my $raw = delete $r->{$uid}->{$key}) or next;
+ # RFC 3501 doesn't seem to indicate order of UID SEARCH
+ # responses, so sort it ourselves. Order matters so
+ # IMAPTracker can store the newest UID.
+ @$uids = sort { $a <=> $b } @$uids;
- # our target audience expects LF-only, save storage
- $raw =~ s/\r\n/\n/sg;
+ # Did we actually get new messages?
+ return if $uids->[0] < $l_uid;
- if (ref($inboxes)) {
- for my $ibx (@$inboxes) {
- my $eml = PublicInbox::Eml->new($raw);
- my $x = import_eml($self, $ibx, $eml);
+ $l_uid = $uids->[-1] + 1; # for next search
+ my $last_uid;
+
+ while (scalar @$uids) {
+ my @batch = splice(@$uids, 0, $bs);
+ $batch = join(',', @batch);
+ local $0 = "UID:$batch $mbx $sec";
+ my $r = $mic->fetch_hash($batch, $req);
+ unless ($r) { # network error?
+ $err = "E: $url UID FETCH $batch error: $!";
+ last;
}
- } elsif ($inboxes eq 'watchspam') {
- my $eml = PublicInbox::Eml->new($raw);
- my $arg = [ $self, $eml, "$uri UID:$uid" ];
- $self->{config}->each_inbox(\&remove_eml_i, $arg);
- } else {
- die "BUG: destination unknown $inboxes";
+ for my $uid (@batch) {
+ # messages get deleted, so holes appear
+ my $per_uid = delete $r->{$uid} // next;
+ my $raw = delete($per_uid->{$key}) // next;
+ imap_import_msg($self, $url, $uid, \$raw);
+ $last_uid = $uid;
+ last if $self->{quit};
+ }
+ last if $self->{quit};
}
- $itrk->update_last($url, $r_uidval, $uid);
- last if $self->{quit};
- }
- _done_for_now($self);
- $itrk->{dbh}->commit;
+ _done_for_now($self);
+ $itrk->update_last($r_uidval, $last_uid) if defined $last_uid;
+ } until ($err || $self->{quit});
$err;
}
# idles on a single URI
sub watch_imap_idle_1 ($$$) {
my ($self, $uri, $intvl) = @_;
- my $sec = imap_section($uri);
+ my $sec = uri_section($uri);
my $mic_arg = $self->{mic_arg}->{$sec} or
die "BUG: no Mail::IMAPClient->new arg for $sec";
my $mic;
sub watch_atfork_child ($) {
my ($self) = @_;
delete $self->{idle_pids};
+ delete $self->{poll_pids};
+ delete $self->{opendirs};
PublicInbox::DS->Reset;
PublicInbox::Sigfd::sig_setmask($self->{oldset});
%SIG = (%SIG, %{$self->{sig}});
}
+sub watch_atfork_parent ($) {
+ my ($self) = @_;
+ _done_for_now($self);
+ $self->{mics} = {}; # going to be forking, so disconnect
+}
+
sub imap_idle_reap { # PublicInbox::DS::dwaitpid callback
my ($self, $pid) = @_;
my $uri_intvl = delete $self->{idle_pids}->{$pid} or
return if $self->{quit};
my $idle_todo = $self->{idle_todo};
if ($idle_todo && @$idle_todo) {
- $self->{mics} = {}; # going to be forking, so disconnect
+ watch_atfork_parent($self);
while (my $uri_intvl = shift(@$idle_todo)) {
imap_idle_fork($self, $uri_intvl);
}
goto(&fs_scan_step) if $self->{mdre};
}
+sub watch_imap_fetch_all ($$) {
+ my ($self, $uris) = @_;
+ for my $uri (@$uris) {
+ my $sec = uri_section($uri);
+ my $mic_arg = $self->{mic_arg}->{$sec} or
+ die "BUG: no Mail::IMAPClient->new arg for $sec";
+ my $mic = PublicInbox::IMAPClient->new(%$mic_arg) or next;
+ my $err = imap_fetch_all($self, $mic, $uri);
+ last if $self->{quit};
+ warn $err, "\n" if $err;
+ }
+}
+
+sub watch_nntp_fetch_all ($$) {
+ my ($self, $uris) = @_;
+ for my $uri (@$uris) {
+ my $sec = uri_section($uri);
+ my $nn_arg = $self->{nn_arg}->{$sec} or
+ die "BUG: no Net::NNTP->new arg for $sec";
+ my $nntp_opt = $self->{nntp_opt}->{$sec};
+ my $url = $uri->as_string;
+ my $nn = nn_new($nn_arg, $nntp_opt, $url);
+ unless ($nn) {
+ warn "E: $url: \$!=$!\n";
+ next;
+ }
+ last if $self->{quit};
+ if (my $postconn = $nntp_opt->{-postconn}) {
+ for my $m_arg (@$postconn) {
+ my ($method, @args) = @$m_arg;
+ $nn->$method(@args) and next;
+ warn "E: <$url> $method failed\n";
+ $nn = undef;
+ last;
+ }
+ }
+ last if $self->{quit};
+ if ($nn) {
+ my $err = nntp_fetch_all($self, $nn, $uri);
+ warn $err, "\n" if $err;
+ }
+ }
+}
+
+sub poll_fetch_fork ($) { # DS::add_timer callback
+ my ($self, $intvl, $uris) = @{$_[0]};
+ return if $self->{quit};
+ watch_atfork_parent($self);
+ defined(my $pid = fork) or die "fork: $!";
+ if ($pid == 0) {
+ watch_atfork_child($self);
+ if ($uris->[0]->scheme =~ /\Aimaps?\z/) {
+ watch_imap_fetch_all($self, $uris);
+ } else {
+ watch_nntp_fetch_all($self, $uris);
+ }
+ _exit(0);
+ }
+ $self->{poll_pids}->{$pid} = [ $intvl, $uris ];
+ PublicInbox::DS::dwaitpid($pid, \&poll_fetch_reap, $self);
+}
+
+sub poll_fetch_reap { # PublicInbox::DS::dwaitpid callback
+ my ($self, $pid) = @_;
+ my $intvl_uris = delete $self->{poll_pids}->{$pid} or
+ die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
+ return if $self->{quit};
+ my ($intvl, $uris) = @$intvl_uris;
+ if ($?) {
+ warn "W: PID=$pid died: \$?=$?\n",
+ map { $_->as_string."\n" } @$uris;
+ }
+ warn('I: will check ', $_->as_string, " in ${intvl}s\n") for @$uris;
+ PublicInbox::DS::add_timer($intvl, \&poll_fetch_fork,
+ [$self, $intvl, $uris]);
+}
+
sub watch_imap_init ($) {
my ($self) = @_;
eval { require PublicInbox::IMAPClient } or
my $mics = $self->{mics} = {}; # schema://authority => IMAPClient obj
for my $url (sort keys %{$self->{imap}}) {
my $uri = PublicInbox::URIimap->new($url);
- $mics->{imap_section($uri)} //= mic_for($self, $uri, $mic_args);
+ $mics->{uri_section($uri)} //= mic_for($self, $uri, $mic_args);
}
my $idle = []; # [ [ uri1, intvl1 ], [uri2, intvl2] ]
my $poll = {}; # intvl_seconds => [ uri1, uri2 ]
for my $url (keys %{$self->{imap}}) {
my $uri = PublicInbox::URIimap->new($url);
- my $sec = imap_section($uri);
+ my $sec = uri_section($uri);
my $mic = $mics->{$sec};
- my $intvl = $self->{imap_opt}->{$sec}->{poll_intvl};
+ my $intvl = $self->{imap_opt}->{$sec}->{pollInterval};
if ($mic->has_capability('IDLE') && !$intvl) {
- $intvl = $self->{imap_opt}->{$sec}->{idle_intvl};
+ $intvl = $self->{imap_opt}->{$sec}->{idleInterval};
push @$idle, [ $uri, $intvl // () ];
} else {
push @{$poll->{$intvl || 120}}, $uri;
$self->{idle_todo} = $idle;
PublicInbox::DS::requeue($self); # ->event_step to fork
}
- # TODO: polling
+ return unless scalar keys %$poll;
+ $self->{poll_pids} //= {};
+
+ # poll all URIs for a given interval sequentially
+ while (my ($intvl, $uris) = each %$poll) {
+ PublicInbox::DS::add_timer(0, \&poll_fetch_fork,
+ [$self, $intvl, $uris]);
+ }
+}
+
+# flesh out common NNTP-specific data structures
+sub nntp_common_init ($) {
+ my ($self) = @_;
+ my $cfg = $self->{config};
+ my $nn_args = {}; # scheme://authority => Net::NNTP->new arg
+ for my $url (sort keys %{$self->{nntp}}) {
+ my $sec = uri_section(URI->new($url));
+
+ # Debug and Timeout are passed to Net::NNTP->new
+ my $v = cfg_bool($cfg, 'nntp.Debug', $url);
+ $nn_args->{$sec}->{Debug} = $v if defined $v;
+ my $to = cfg_intvl($cfg, 'nntp.Timeout', $url);
+ $nn_args->{$sec}->{Timeout} = $to if $to;
+
+ # Net::NNTP post-connect commands
+ for my $k (qw(starttls compress)) {
+ $v = cfg_bool($cfg, "nntp.$k", $url) // next;
+ $self->{nntp_opt}->{$sec}->{$k} = $v;
+ }
+
+ # internal option
+ for my $k (qw(pollInterval)) {
+ $to = cfg_intvl($cfg, "nntp.$k", $url) // next;
+ $self->{nntp_opt}->{$sec}->{$k} = $to;
+ }
+ }
+ $nn_args;
+}
+
+# Net::NNTP doesn't support CAPABILITIES, yet
+sub try_starttls ($) {
+ my ($host) = @_;
+ return if $host =~ /\.onion\z/s;
+ return if $host =~ /\A127\.[0-9]+\.[0-9]+\.[0-9]+\z/s;
+ return if $host eq '::1';
+ 1;
+}
+
+sub nn_new ($$$) {
+ my ($nn_arg, $nntp_opt, $url) = @_;
+ my $nn = Net::NNTP->new(%$nn_arg) or die "E: <$url> new: $!\n";
+
+ # default to using STARTTLS if it's available, but allow
+ # it to be disabled for localhost/VPN users
+ if (!$nn_arg->{SSL} && $nn->can('starttls')) {
+ if (!defined($nntp_opt->{starttls}) &&
+ try_starttls($nn_arg->{Host})) {
+ # soft fail by default
+ $nn->starttls or warn <<"";
+W: <$url> STARTTLS tried and failed (not requested)
+
+ } elsif ($nntp_opt->{starttls}) {
+ # hard fail if explicitly configured
+ $nn->starttls or die <<"";
+E: <$url> STARTTLS requested and failed
+
+ }
+ } elsif ($nntp_opt->{starttls}) {
+ $nn->can('starttls') or
+ die "E: <$url> Net::NNTP too old for STARTTLS\n";
+ $nn->starttls or die <<"";
+E: <$url> STARTTLS requested and failed
+
+ }
+ $nn;
+}
+
+sub nn_for ($$$) { # nn = Net::NNTP
+ my ($self, $uri, $nn_args) = @_;
+ my $url = $uri->as_string;
+ my $sec = uri_section($uri);
+ my $nntp_opt = $self->{nntp_opt}->{$sec} //= {};
+ my $cred;
+ my ($u, $p);
+ if (defined(my $ui = $uri->userinfo)) {
+ $cred = {
+ url => $sec,
+ protocol => $uri->scheme,
+ host => $uri->host,
+ };
+ ($u, $p) = split(/:/, $ui, 2);
+ ($cred->{username}, $cred->{password}) = ($u, $p);
+ }
+ my $common = $nn_args->{$sec} // {};
+ my $nn_arg = {
+ Port => $uri->port,
+ # Net::NNTP mishandles `0', so we pass `127.0.0.1'
+ Host => $uri->host eq '0' ? '127.0.0.1' : $uri->host,
+ SSL => $uri->secure, # snews == nntps
+ %$common, # may Debug ....
+ };
+ my $nn = nn_new($nn_arg, $nntp_opt, $url);
+
+ if ($cred) {
+ Git::credential($cred, 'fill'); # may prompt user here
+ if ($nn->authinfo($u, $p)) {
+ push @{$nntp_opt->{-postconn}}, [ 'authinfo', $u, $p ];
+ } else {
+ warn "E: <$url> AUTHINFO $u XXXX failed\n";
+ $nn = undef;
+ }
+ }
+
+ if ($nntp_opt->{compress}) {
+ # https://rt.cpan.org/Ticket/Display.html?id=129967
+ if ($nn->can('compress')) {
+ if ($nn->compress) {
+ push @{$nntp_opt->{-postconn}}, [ 'compress' ];
+ } else {
+ warn "W: <$url> COMPRESS failed\n";
+ }
+ } else {
+ delete $nntp_opt->{compress};
+ warn <<"";
+W: <$url> COMPRESS not supported by Net::NNTP
+W: see https://rt.cpan.org/Ticket/Display.html?id=129967 for updates
+
+ }
+ }
+
+ $self->{nn_arg}->{$sec} = $nn_arg;
+ Git::credential($cred, $nn ? 'approve' : 'reject') if $cred;
+ $nn;
+}
+
+sub nntp_fetch_all ($$$) {
+ my ($self, $nn, $uri) = @_;
+ my ($group, $num_a, $num_b) = $uri->group;
+ my $sec = uri_section($uri);
+ my $url = $uri->as_string;
+ my ($nr, $beg, $end) = $nn->group($group);
+ unless (defined($nr)) {
+ chomp(my $msg = $nn->message);
+ return "E: GROUP $group <$sec> $msg";
+ }
+
+ # IMAPTracker is also used for tracking NNTP, UID == article number
+ # LIST.ACTIVE can get the equivalent of UIDVALIDITY, but that's
+ # expensive. So we assume newsgroups don't change:
+ my $itrk = PublicInbox::IMAPTracker->new($url);
+ my (undef, $l_art) = $itrk->get_last;
+ $l_art //= $beg; # initial import
+
+ # allow users to specify articles to refetch
+ # cf. https://tools.ietf.org/id/draft-gilman-news-url-01.txt
+ # nntp://example.com/inbox.foo/$num_a-$num_b
+ $l_art = $num_a if defined($num_a) && $num_a < $l_art;
+ $end = $num_b if defined($num_b) && $num_b < $end;
+
+ return if $l_art >= $end; # nothing to do
+ $beg = $l_art + 1;
+
+ warn "I: $url fetching ARTICLE $beg..$end\n";
+ my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
+ my ($err, $art);
+ local $SIG{__WARN__} = sub {
+ $warn_cb->("$url ", $art ? ("ARTICLE $art") : (), "\n", @_);
+ };
+ my $inboxes = $self->{nntp}->{$url};
+ my $last_art;
+ for ($beg..$end) {
+ last if $self->{quit};
+ $art = $_;
+ my $raw = $nn->article($art);
+ unless (defined($raw)) {
+ my $msg = $nn->message;
+ if ($nn->code == 421) { # pseudo response from Net::Cmd
+ $err = "E: $msg";
+ last;
+ } else { # probably just a deleted message (spam)
+ warn "W: $msg";
+ next;
+ }
+ }
+ s/\r\n/\n/ for @$raw;
+ $raw = join('', @$raw);
+ if (ref($inboxes)) {
+ for my $ibx (@$inboxes) {
+ my $eml = PublicInbox::Eml->new($raw);
+ import_eml($self, $ibx, $eml);
+ }
+ } elsif ($inboxes eq 'watchspam') {
+ my $eml = PublicInbox::Eml->new(\$raw);
+ my $arg = [ $self, $eml, "$url ARTICLE $art" ];
+ $self->{config}->each_inbox(\&remove_eml_i, $arg);
+ } else {
+ die "BUG: destination unknown $inboxes";
+ }
+ $last_art = $art;
+ }
+ $itrk->update_last(0, $last_art) if defined $last_art;
+ _done_for_now($self);
+ $err;
+}
+
+sub watch_nntp_init ($) {
+ my ($self) = @_;
+ eval { require Net::NNTP } or
+ die "Net::NNTP is required for NNTP:\n$@\n";
+ eval { require Git } or
+ die "Git (Perl module) is required for NNTP:\n$@\n";
+ eval { require PublicInbox::IMAPTracker } or
+ die "DBD::SQLite is required for NNTP\n:$@\n";
+
+ my $nn_args = nntp_common_init($self); # read args from config
+
+ # make sure we can connect and cache the credentials in memory
+ $self->{nn_arg} = {}; # schema://authority => Net::NNTP->new args
+ for my $url (sort keys %{$self->{nntp}}) {
+ nn_for($self, URI->new($url), $nn_args);
+ }
+ my $poll = {}; # intvl_seconds => [ uri1, uri2 ]
+ for my $url (keys %{$self->{nntp}}) {
+ my $uri = URI->new($url);
+ my $sec = uri_section($uri);
+ my $intvl = $self->{nntp_opt}->{$sec}->{pollInterval};
+ push @{$poll->{$intvl || 120}}, $uri;
+ }
+ $self->{poll_pids} //= {};
+
+ # poll all URIs for a given interval sequentially
+ while (my ($intvl, $uris) = each %$poll) {
+ PublicInbox::DS::add_timer(0, \&poll_fetch_fork,
+ [$self, $intvl, $uris]);
+ }
}
sub watch {
$self->{oldset} = $oldset;
$self->{sig} = $sig;
watch_imap_init($self) if $self->{imap};
+ watch_nntp_init($self) if $self->{nntp};
watch_fs_init($self) if $self->{mdre};
PublicInbox::DS->SetPostLoopCallback(sub {});
PublicInbox::DS->EventLoop until $self->{quit};
$opendirs->{$dir} = $dh if $n < 0;
}
if ($op && $op eq 'full') {
- foreach my $dir (@{$self->{mdir}}) {
+ foreach my $dir (keys %{$self->{mdmap}}) {
next if $opendirs->{$dir}; # already in progress
my $ok = opendir(my $dh, $dir);
unless ($ok) {
$uri ? $uri->canonical->as_string : undef;
}
+my %IS_NNTP = (news => 1, snews => 1, nntp => 1);
+sub nntp_url {
+ my ($url) = @_;
+ require URI;
+ # URI::snews exists, URI::nntps does not, so use URI::snews
+ $url =~ s!\Anntps://!snews://!i;
+ my $uri = URI->new($url);
+ return unless $uri && $IS_NNTP{$uri->scheme};
+ $uri->group ? $uri->canonical->as_string : undef;
+}
+
1;