-# Copyright (C) 2016-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) 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
-# http://wiki2.dovecot.org/MailboxFormat/Maildir
+# https://wiki2.dovecot.org/MailboxFormat/Maildir
package PublicInbox::Watch;
use strict;
use v5.10.1;
use PublicInbox::Eml;
-use PublicInbox::InboxWritable qw(eml_from_path warn_ignore_cb);
+use PublicInbox::InboxWritable qw(eml_from_path);
+use PublicInbox::MdirReader;
+use PublicInbox::NetReader;
use PublicInbox::Filter::Base qw(REJECT);
use PublicInbox::Spamcheck;
-use PublicInbox::Sigfd;
-use PublicInbox::DS qw(now);
+use PublicInbox::DS qw(now add_timer awaitpid);
use PublicInbox::MID qw(mids);
use PublicInbox::ContentHash qw(content_hash);
-use PublicInbox::EOFpipe;
use POSIX qw(_exit WNOHANG);
sub compile_watchheaders ($) {
my ($class, $cfg) = @_;
my (%mdmap, $spamc);
my (%imap, %nntp); # url => [inbox objects] or 'watchspam'
+ my (@imap, @nntp);
# "publicinboxwatch" is the documented namespace
# "publicinboxlearn" is legacy but may be supported
# indefinitely...
foreach my $pfx (qw(publicinboxwatch publicinboxlearn)) {
my $k = "$pfx.watchspam";
- defined(my $dirs = $cfg->{$k}) or next;
- $dirs = PublicInbox::Config::_array($dirs);
+ my $dirs = $cfg->get_all($k) // next;
for my $dir (@$dirs) {
- my $url;
+ my $uri;
if (is_maildir($dir)) {
# skip "new", no MUA has seen it, yet.
$mdmap{"$dir/cur"} = 'watchspam';
- } elsif ($url = imap_url($dir)) {
- $imap{$url} = 'watchspam';
- } elsif ($url = nntp_url($dir)) {
- $nntp{$url} = 'watchspam';
+ } elsif ($uri = imap_uri($dir)) {
+ $imap{$$uri} = 'watchspam';
+ push @imap, $uri;
+ } elsif ($uri = nntp_uri($dir)) {
+ $nntp{$$uri} = 'watchspam';
+ push @nntp, $uri;
} else {
warn "unsupported $k=$dir\n";
}
my $watches = $ibx->{watch} or return;
$watches = PublicInbox::Config::_array($watches);
for my $watch (@$watches) {
- my $url;
+ my $uri;
if (is_maildir($watch)) {
compile_watchheaders($ibx);
my ($new, $cur) = ("$watch/new", "$watch/cur");
return if is_watchspam($cur, $cur_dst, $ibx);
push @{$mdmap{$new} //= []}, $ibx;
push @$cur_dst, $ibx;
- } elsif ($url = imap_url($watch)) {
- return if is_watchspam($url, $imap{$url}, $ibx);
+ } elsif ($uri = imap_uri($watch)) {
+ my $cur_dst = $imap{$$uri} //= [];
+ return if is_watchspam($uri, $cur_dst, $ibx);
compile_watchheaders($ibx);
- push @{$imap{$url} ||= []}, $ibx;
- } elsif ($url = nntp_url($watch)) {
- return if is_watchspam($url, $nntp{$url}, $ibx);
+ push(@imap, $uri) if 1 == push(@$cur_dst, $ibx);
+ } elsif ($uri = nntp_uri($watch)) {
+ my $cur_dst = $nntp{$$uri} //= [];
+ return if is_watchspam($uri, $cur_dst, $ibx);
compile_watchheaders($ibx);
- push @{$nntp{$url} ||= []}, $ibx;
+ push(@nntp, $uri) if 1 == push(@$cur_dst, $ibx);
} else {
warn "watch unsupported: $k=$watch\n";
}
pi_cfg => $cfg,
imap => scalar keys %imap ? \%imap : undef,
nntp => scalar keys %nntp? \%nntp : undef,
+ imap_order => scalar(@imap) ? \@imap : undef,
+ nntp_order => scalar(@nntp) ? \@nntp: undef,
importers => {},
opendirs => {}, # dirname => dirhandle (in progress scans)
ops => [], # 'quit', 'full'
# path must be marked as (S)een
$path =~ /:2,[A-R]*S[T-Za-z]*\z/ or return;
my $eml = eml_from_path($path) or return;
- local $SIG{__WARN__} = warn_ignore_cb();
+ local $SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb();
$self->{pi_cfg}->each_inbox(\&remove_eml_i, $self, $eml, $path);
}
sub _try_path {
my ($self, $path) = @_;
- return unless PublicInbox::InboxWritable::is_maildir_path($path);
+ my $fl = PublicInbox::MdirReader::maildir_path_flags($path) // return;
+ return if $fl =~ /[DT]/; # no Drafts or Trash
if ($path !~ $self->{mdre}) {
warn "unrecognized path: $path\n";
return;
return unless $self->{quit};
# don't have reliable wakeups, keep signalling
- my $done = 1;
- for (qw(idle_pids poll_pids)) {
- my $pids = $self->{$_} or next;
- for (keys %$pids) {
- $done = undef if kill('QUIT', $_);
- }
- }
- $done;
+ my $live = grep { kill('QUIT', $_) } keys %{$self->{pids}};
+ add_timer(0.01, \&quit_done, $self) if $live;
+ $live == 0;
}
sub quit {
};
require PublicInbox::DirIdle;
# inotify_create + EPOLL_CTL_ADD
- PublicInbox::DirIdle->new([keys %{$self->{mdmap}}], $cb);
-}
-
-# avoid exposing deprecated "snews" to users.
-my %SCHEME_MAP = ('snews' => 'nntps');
-
-sub uri_scheme ($) {
- my ($uri) = @_;
- my $scheme = $uri->scheme;
- $SCHEME_MAP{$scheme} // $scheme;
-}
-
-# returns the git config section name, e.g [imap "imaps://user@example.com"]
-# without the mailbox, so we can share connections between different inboxes
-sub uri_section ($) {
- my ($uri) = @_;
- uri_scheme($uri) . '://' . $uri->authority;
-}
-
-sub cfg_intvl ($$$) {
- my ($cfg, $key, $url) = @_;
- my $v = $cfg->urlmatch($key, $url) // return;
- $v =~ /\A[0-9]+(?:\.[0-9]+)?\z/s and return $v + 0;
- if (ref($v) eq 'ARRAY') {
- $v = join(', ', @$v);
- warn "W: $key has multiple values: $v\nW: $key ignored\n";
- } else {
- warn "W: $key=$v is not a numeric value in seconds\n";
- }
-}
-
-sub cfg_bool ($$$) {
- my ($cfg, $key, $url) = @_;
- my $orig = $cfg->urlmatch($key, $url) // return;
- my $bool = $cfg->git_bool($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 $cfg = $self->{pi_cfg};
- my $mic_args = {}; # scheme://authority => Mail:IMAPClient arg
- for my $url (sort keys %{$self->{imap}}) {
- my $uri = PublicInbox::URIimap->new($url);
- my $sec = uri_section($uri);
- for my $k (qw(Starttls Debug Compress)) {
- my $bool = cfg_bool($cfg, "imap.$k", $url) // next;
- $mic_args->{$sec}->{$k} = $bool;
- }
- my $to = cfg_intvl($cfg, 'imap.timeout', $url);
- $mic_args->{$sec}->{Timeout} = $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;
-}
-
-sub auth_anon_cb { '' }; # for Mail::IMAPClient::Authcallback
-
-sub mic_for ($$$) { # mic = Mail::IMAPClient
- my ($self, $url, $mic_args) = @_;
- my $uri = PublicInbox::URIimap->new($url);
- require PublicInbox::GitCredential;
- my $cred = bless {
- url => $url,
- protocol => $uri->scheme,
- host => $uri->host,
- username => $uri->user,
- password => $uri->password,
- }, 'PublicInbox::GitCredential';
- my $common = $mic_args->{uri_section($uri)} // {};
- # IMAPClient and Net::Netrc both mishandles `0', so we pass `127.0.0.1'
- my $host = $cred->{host};
- $host = '127.0.0.1' if $host eq '0';
- my $mic_arg = {
- Port => $uri->port,
- Server => $host,
- Ssl => $uri->scheme eq 'imaps',
- Keepalive => 1, # SO_KEEPALIVE
- %$common, # may set Starttls, Compress, Debug ....
- };
- my $mic = PublicInbox::IMAPClient->new(%$mic_arg) or
- die "E: <$url> new: $@\n";
-
- # default to using STARTTLS if it's available, but allow
- # it to be disabled since I usually connect to localhost
- if (!$mic_arg->{Ssl} && !defined($mic_arg->{Starttls}) &&
- $mic->has_capability('STARTTLS') &&
- $mic->can('starttls')) {
- $mic->starttls or die "E: <$url> STARTTLS: $@\n";
- }
-
- # do we even need credentials?
- if (!defined($cred->{username}) &&
- $mic->has_capability('AUTH=ANONYMOUS')) {
- $cred = undef;
- }
- if ($cred) {
- $cred->check_netrc unless defined $cred->{password};
- $cred->fill; # may prompt user here
- $mic->User($mic_arg->{User} = $cred->{username});
- $mic->Password($mic_arg->{Password} = $cred->{password});
- } else { # AUTH=ANONYMOUS
- $mic->Authmechanism($mic_arg->{Authmechanism} = 'ANONYMOUS');
- $mic->Authcallback($mic_arg->{Authcallback} = \&auth_anon_cb);
- }
- if ($mic->login && $mic->IsAuthenticated) {
- # success! keep IMAPClient->new arg in case we get disconnected
- $self->{mic_arg}->{uri_section($uri)} = $mic_arg;
- } else {
- warn "E: <$url> LOGIN: $@\n";
- $mic = undef;
- }
- $cred->run($mic ? 'approve' : 'reject') if $cred;
- $mic;
+ my $dir_idle = PublicInbox::DirIdle->new($cb);
+ $dir_idle->add_watches([keys %{$self->{mdmap}}]);
}
-sub imap_import_msg ($$$$$) {
- my ($self, $url, $uid, $raw, $flags) = @_;
- # our target audience expects LF-only, save storage
- $$raw =~ s/\r\n/\n/sg;
-
- my $inboxes = $self->{imap}->{$url};
+sub net_cb { # NetReader::(nntp|imap)_each callback
+ my ($uri, $art, $kw, $eml, $self, $inboxes) = @_;
+ return if grep(/\Adraft\z/, @$kw);
+ local $self->{cur_uid} = $art; # IMAP UID or NNTP article
if (ref($inboxes)) {
- for my $ibx (@$inboxes) {
- my $eml = PublicInbox::Eml->new($$raw);
- import_eml($self, $ibx, $eml);
+ my @ibx = @$inboxes;
+ my $last = pop @ibx;
+ for my $ibx (@ibx) {
+ my $tmp = PublicInbox::Eml->new(\($eml->as_string));
+ import_eml($self, $ibx, $tmp);
}
+ import_eml($self, $last, $eml);
} elsif ($inboxes eq 'watchspam') {
- # we don't remove unseen messages
- if ($flags =~ /\\Seen\b/) {
- local $SIG{__WARN__} = warn_ignore_cb();
- my $eml = PublicInbox::Eml->new($raw);
- $self->{pi_cfg}->each_inbox(\&remove_eml_i,
- $self, $eml, "$url UID:$uid");
+ if ($uri->scheme =~ /\Aimaps?\z/ && !grep(/\Aseen\z/, @$kw)) {
+ return;
}
+ $self->{pi_cfg}->each_inbox(\&remove_eml_i,
+ $self, $eml, "$uri #$art");
} else {
die "BUG: destination unknown $inboxes";
}
}
-sub imap_fetch_all ($$$) {
- my ($self, $mic, $url) = @_;
- my $uri = PublicInbox::URIimap->new($url);
- my $sec = uri_section($uri);
- my $mbx = $uri->mailbox;
- $mic->Clear(1); # trim results history
- $mic->examine($mbx) or return "E: EXAMINE $mbx ($sec) failed: $!";
- my ($r_uidval, $r_uidnext);
- for ($mic->Results) {
- /^\* OK \[UIDVALIDITY ([0-9]+)\].*/ and $r_uidval = $1;
- /^\* OK \[UIDNEXT ([0-9]+)\].*/ and $r_uidnext = $1;
- last if $r_uidval && $r_uidnext;
- }
- $r_uidval //= $mic->uidvalidity($mbx) //
- return "E: $url cannot get UIDVALIDITY";
- $r_uidnext //= $mic->uidnext($mbx) //
- return "E: $url cannot get UIDNEXT";
- 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 "E: $url UIDVALIDITY mismatch\n".
- "E: local=$l_uidval != remote=$r_uidval";
- }
- my $r_uid = $r_uidnext - 1;
- if ($l_uid != 1 && $l_uid > $r_uid) {
- return "E: $url local UID exceeds remote ($l_uid > $r_uid)\n".
- "E: $url strangely, UIDVALIDLITY matches ($l_uidval)\n";
- }
- 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;
- $key =~ s/\.PEEK//;
- my ($uids, $batch);
+sub imap_fetch_all ($$) {
+ my ($self, $uri) = @_;
my $warn_cb = $SIG{__WARN__} || \&CORE::warn;
+ $self->{incremental} = 1;
+ $self->{on_commit} = [ \&_done_for_now, $self ];
+ local $self->{cur_uid};
local $SIG{__WARN__} = sub {
- my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
- $batch //= '?';
- $warn_cb->("$pfx$url UID:$batch\n", @_);
+ my $pfx = ($_[0] // '') =~ /^([A-Z]: |# )/g ? $1 : '';
+ my $uid = $self->{cur_uid};
+ $warn_cb->("$pfx$uri", $uid ? ("UID:$uid") : (), "\n", @_);
};
- my $err;
- 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;
-
- # 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;
-
- # Did we actually get new messages?
- return if $uids->[0] < $l_uid;
-
- $l_uid = $uids->[-1] + 1; # for next search
- my $last_uid;
- my $n = $self->{max_batch};
-
- while (scalar @$uids) {
- if (--$n < 0) {
- _done_for_now($self);
- $itrk->update_last($r_uidval, $last_uid);
- $n = $self->{max_batch};
- }
- my @batch = splice(@$uids, 0, $bs);
- $batch = join(',', @batch);
- local $0 = "UID:$batch $mbx $sec";
- my $r = $mic->fetch_hash($batch, $req, 'FLAGS');
- unless ($r) { # network error?
- $err = "E: $url UID FETCH $batch error: $!";
- last;
- }
- for my $uid (@batch) {
- # messages get deleted, so holes appear
- my $per_uid = delete $r->{$uid} // next;
- my $raw = delete($per_uid->{$key}) // next;
- my $fl = $per_uid->{FLAGS} // '';
- imap_import_msg($self, $url, $uid, \$raw, $fl);
- $last_uid = $uid;
- last if $self->{quit};
- }
- last if $self->{quit};
- }
- _done_for_now($self);
- $itrk->update_last($r_uidval, $last_uid);
- } until ($err || $self->{quit});
- $err;
+ PublicInbox::NetReader::imap_each($self, $uri, \&net_cb, $self,
+ $self->{imap}->{$$uri});
}
sub imap_idle_once ($$$$) {
- my ($self, $mic, $intvl, $url) = @_;
+ my ($self, $mic, $intvl, $uri) = @_;
my $i = $intvl //= (29 * 60);
my $end = now() + $intvl;
- warn "I: $url idling for ${intvl}s\n";
+ warn "# $uri idling for ${intvl}s\n";
local $0 = "IDLE $0";
+ return if $self->{quit};
unless ($mic->idle) {
return if $self->{quit};
- return "E: IDLE failed on $url: $!";
+ return "E: IDLE failed on $uri: $!";
}
$self->{idle_mic} = $mic; # for ->quit
my @res;
}
delete $self->{idle_mic};
unless ($self->{quit}) {
- $mic->IsConnected or return "E: IDLE disconnected on $url";
- $mic->done or return "E: IDLE DONE failed on $url: $!";
+ $mic->IsConnected or return "E: IDLE disconnected on $uri";
+ $mic->done or return "E: IDLE DONE failed on $uri: $!";
}
undef;
}
# idles on a single URI
sub watch_imap_idle_1 ($$$) {
- my ($self, $url, $intvl) = @_;
- my $uri = PublicInbox::URIimap->new($url);
+ my ($self, $uri, $intvl) = @_;
my $sec = uri_section($uri);
- my $mic_arg = $self->{mic_arg}->{$sec} or
+ my $mic_arg = $self->{net_arg}->{$sec} or
die "BUG: no Mail::IMAPClient->new arg for $sec";
my $mic;
local $0 = $uri->mailbox." $sec";
until ($self->{quit}) {
- $mic //= PublicInbox::IMAPClient->new(%$mic_arg);
+ $mic //= PublicInbox::NetReader::mic_new(
+ $self, $mic_arg, $sec, $uri);
my $err;
if ($mic && $mic->IsConnected) {
- $err = imap_fetch_all($self, $mic, $url);
- $err //= imap_idle_once($self, $mic, $intvl, $url);
+ local $self->{mics_cached}->{$sec} = $mic;
+ my $m = imap_fetch_all($self, $uri);
+ $m == $mic or die "BUG: wrong mic";
+ $mic->IsConnected and
+ $err = imap_idle_once($self, $mic, $intvl, $uri)
} else {
$err = "E: not connected: $!";
}
sub watch_atfork_child ($) {
my ($self) = @_;
- delete $self->{idle_pids};
- delete $self->{poll_pids};
+ delete $self->{pids};
delete $self->{opendirs};
PublicInbox::DS->Reset;
- %SIG = (%SIG, %{$self->{sig}}, CHLD => 'DEFAULT');
+ my $sig = delete $self->{sig};
+ $sig->{CHLD} = 'DEFAULT';
+ @SIG{keys %$sig} = values %$sig;
PublicInbox::DS::sig_setmask($self->{oldset});
}
-sub watch_atfork_parent ($) {
- my ($self) = @_;
- _done_for_now($self);
- PublicInbox::DS::block_signals();
-}
+sub watch_atfork_parent ($) { _done_for_now($_[0]) }
-sub imap_idle_requeue ($) { # DS::add_timer callback
- my ($self, $url_intvl) = @{$_[0]};
+sub imap_idle_requeue { # DS::add_timer callback
+ my ($self, $uri, $intvl) = @_;
return if $self->{quit};
- push @{$self->{idle_todo}}, $url_intvl;
+ push @{$self->{idle_todo}}, $uri, $intvl;
event_step($self);
}
-sub imap_idle_reap { # PublicInbox::DS::dwaitpid callback
- my ($self, $pid) = @_;
- my $url_intvl = delete $self->{idle_pids}->{$pid} or
- die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
-
- my ($url, $intvl) = @$url_intvl;
+sub imap_idle_reap { # awaitpid callback
+ my ($pid, $self, $uri, $intvl) = @_;
+ delete $self->{pids}->{$pid};
return if $self->{quit};
- warn "W: PID=$pid on $url died: \$?=$?\n" if $?;
- PublicInbox::DS::add_timer(60,
- \&imap_idle_requeue, [ $self, $url_intvl ]);
+ warn "W: PID=$pid on $uri died: \$?=$?\n" if $?;
+ add_timer(60, \&imap_idle_requeue, $self, $uri, $intvl);
}
-sub reap { # callback for EOFpipe
- my ($pid, $cb, $self) = @{$_[0]};
- my $ret = waitpid($pid, 0);
- if ($ret == $pid) {
- $cb->($self, $pid); # poll_fetch_reap || imap_idle_reap
- } else {
- warn "W: waitpid($pid) => ", $ret // "($!)", "\n";
- }
-}
-
-sub imap_idle_fork ($$) {
- my ($self, $url_intvl) = @_;
- my ($url, $intvl) = @$url_intvl;
- pipe(my ($r, $w)) or die "pipe: $!";
+sub imap_idle_fork {
+ my ($self, $uri, $intvl) = @_;
+ return if $self->{quit};
my $seed = rand(0xffffffff);
- defined(my $pid = fork) or die "fork: $!";
+ my $pid = fork // die "fork: $!";
if ($pid == 0) {
srand($seed);
eval { Net::SSLeay::randomize() };
- close $r;
watch_atfork_child($self);
- watch_imap_idle_1($self, $url, $intvl);
- close $w;
+ watch_imap_idle_1($self, $uri, $intvl);
_exit(0);
}
- $self->{idle_pids}->{$pid} = $url_intvl;
- PublicInbox::EOFpipe->new($r, \&reap, [$pid, \&imap_idle_reap, $self]);
+ $self->{pids}->{$pid} = undef;
+ awaitpid($pid, \&imap_idle_reap, $self, $uri, $intvl);
}
sub event_step {
return if $self->{quit};
my $idle_todo = $self->{idle_todo};
if ($idle_todo && @$idle_todo) {
- my $oldset = watch_atfork_parent($self);
+ watch_atfork_parent($self);
eval {
- while (my $url_intvl = shift(@$idle_todo)) {
- imap_idle_fork($self, $url_intvl);
+ while (my ($uri, $intvl) = splice(@$idle_todo, 0, 2)) {
+ imap_idle_fork($self, $uri, $intvl);
}
};
- PublicInbox::DS::sig_setmask($oldset);
die $@ if $@;
}
fs_scan_step($self) if $self->{mdre};
}
sub watch_imap_fetch_all ($$) {
- my ($self, $urls) = @_;
- for my $url (@$urls) {
- my $uri = PublicInbox::URIimap->new($url);
- 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, $url);
+ my ($self, $uris) = @_;
+ for my $uri (@$uris) {
+ imap_fetch_all($self, $uri);
last if $self->{quit};
- warn $err, "\n" if $err;
}
}
sub watch_nntp_fetch_all ($$) {
- my ($self, $urls) = @_;
- for my $url (@$urls) {
- my $uri = uri_new($url);
- my $sec = uri_section($uri);
- my $nn_arg = $self->{nn_arg}->{$sec} or
- die "BUG: no Net::NNTP->new arg for $sec";
- my $nntp_opt = $self->{nntp_opt}->{$sec};
- my $nn = nn_new($nn_arg, $nntp_opt, $url);
- unless ($nn) {
- warn "E: $url: \$!=$!\n";
- next;
- }
- last if $self->{quit};
- if (my $postconn = $nntp_opt->{-postconn}) {
- for my $m_arg (@$postconn) {
- my ($method, @args) = @$m_arg;
- $nn->$method(@args) and next;
- warn "E: <$url> $method failed\n";
- $nn = undef;
- last;
- }
- }
+ my ($self, $uris) = @_;
+ $self->{incremental} = 1;
+ $self->{on_commit} = [ \&_done_for_now, $self ];
+ my $warn_cb = $SIG{__WARN__} || \&CORE::warn;
+ local $self->{cur_uid};
+ my $uri = '';
+ local $SIG{__WARN__} = sub {
+ my $pfx = ($_[0] // '') =~ /^([A-Z]: |# )/g ? $1 : '';
+ my $art = $self->{cur_uid};
+ $warn_cb->("$pfx$uri", $art ? ("ARTICLE $art") : (), "\n", @_);
+ };
+ for $uri (@$uris) {
+ PublicInbox::NetReader::nntp_each($self, $uri, \&net_cb, $self,
+ $self->{nntp}->{$$uri});
last if $self->{quit};
- if ($nn) {
- my $err = nntp_fetch_all($self, $nn, $url);
- warn $err, "\n" if $err;
- }
}
}
-sub poll_fetch_fork ($) { # DS::add_timer callback
- my ($self, $intvl, $urls) = @{$_[0]};
+sub poll_fetch_fork { # DS::add_timer callback
+ my ($self, $intvl, $uris) = @_;
return if $self->{quit};
- pipe(my ($r, $w)) or die "pipe: $!";
- my $oldset = watch_atfork_parent($self);
+ watch_atfork_parent($self);
my $seed = rand(0xffffffff);
- my $pid = fork;
- if (defined($pid) && $pid == 0) {
+ my $pid = fork // die "fork: $!";
+ if ($pid == 0) {
srand($seed);
eval { Net::SSLeay::randomize() };
- close $r;
watch_atfork_child($self);
- if ($urls->[0] =~ m!\Aimaps?://!i) {
- watch_imap_fetch_all($self, $urls);
+ if ($uris->[0]->scheme =~ m!\Aimaps?!i) {
+ watch_imap_fetch_all($self, $uris);
} else {
- watch_nntp_fetch_all($self, $urls);
+ watch_nntp_fetch_all($self, $uris);
}
- close $w;
_exit(0);
}
- PublicInbox::DS::sig_setmask($oldset);
- die "fork: $!" unless defined $pid;
- $self->{poll_pids}->{$pid} = [ $intvl, $urls ];
- PublicInbox::EOFpipe->new($r, \&reap, [$pid, \&poll_fetch_reap, $self]);
+ $self->{pids}->{$pid} = undef;
+ awaitpid($pid, \&poll_fetch_reap, $self, $intvl, $uris);
}
-sub poll_fetch_reap {
- my ($self, $pid) = @_;
- my $intvl_urls = delete $self->{poll_pids}->{$pid} or
- die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
+sub poll_fetch_reap { # awaitpid callback
+ my ($pid, $self, $intvl, $uris) = @_;
+ delete $self->{pids}->{$pid};
return if $self->{quit};
- my ($intvl, $urls) = @$intvl_urls;
if ($?) {
- warn "W: PID=$pid died: \$?=$?\n", map { "$_\n" } @$urls;
+ warn "W: PID=$pid died: \$?=$?\n", map { "$_\n" } @$uris;
}
- warn("I: will check $_ in ${intvl}s\n") for @$urls;
- PublicInbox::DS::add_timer($intvl, \&poll_fetch_fork,
- [$self, $intvl, $urls]);
+ warn("# will check $_ in ${intvl}s\n") for @$uris;
+ add_timer($intvl, \&poll_fetch_fork, $self, $intvl, $uris);
}
sub watch_imap_init ($$) {
my ($self, $poll) = @_;
- eval { require PublicInbox::IMAPClient } or
- die "Mail::IMAPClient is required for IMAP:\n$@\n";
- eval { require PublicInbox::IMAPTracker } or
- die "DBD::SQLite is required for IMAP\n:$@\n";
-
- my $mic_args = imap_common_init($self); # read args from config
-
- # make sure we can connect and cache the credentials in memory
- $self->{mic_arg} = {}; # schema://authority => IMAPClient->new args
- my $mics = {}; # schema://authority => IMAPClient obj
- for my $url (sort keys %{$self->{imap}}) {
- my $uri = PublicInbox::URIimap->new($url);
- $mics->{uri_section($uri)} //= mic_for($self, $url, $mic_args);
- }
-
- my $idle = []; # [ [ url1, intvl1 ], [url2, intvl2] ]
- for my $url (keys %{$self->{imap}}) {
- my $uri = PublicInbox::URIimap->new($url);
+ my $mics = PublicInbox::NetReader::imap_common_init($self);
+ my $idle = []; # [ uri1, intvl1, uri2, intvl2 ]
+ for my $uri (@{$self->{imap_order}}) {
my $sec = uri_section($uri);
my $mic = $mics->{$sec};
- my $intvl = $self->{imap_opt}->{$sec}->{pollInterval};
+ my $intvl = $self->{cfg_opt}->{$sec}->{pollInterval};
if ($mic->has_capability('IDLE') && !$intvl) {
- $intvl = $self->{imap_opt}->{$sec}->{idleInterval};
- push @$idle, [ $url, $intvl // () ];
+ $intvl = $self->{cfg_opt}->{$sec}->{idleInterval};
+ push @$idle, $uri, $intvl;
} else {
- push @{$poll->{$intvl || 120}}, $url;
+ push @{$poll->{$intvl || 120}}, $uri;
}
}
if (scalar @$idle) {
}
}
-# flesh out common NNTP-specific data structures
-sub nntp_common_init ($) {
- my ($self) = @_;
- my $cfg = $self->{pi_cfg};
- 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 ($$$) { # nn = Net::NNTP
- my ($self, $url, $nn_args) = @_;
- my $uri = uri_new($url);
- my $sec = uri_section($uri);
- my $nntp_opt = $self->{nntp_opt}->{$sec} //= {};
- my $host = $uri->host;
- # Net::NNTP and Net::Netrc both mishandle `0', so we pass `127.0.0.1'
- $host = '127.0.0.1' if $host eq '0';
- my $cred;
- my ($u, $p);
- if (defined(my $ui = $uri->userinfo)) {
- require PublicInbox::GitCredential;
- $cred = bless {
- url => $sec,
- protocol => uri_scheme($uri),
- host => $host,
- }, 'PublicInbox::GitCredential';
- ($u, $p) = split(/:/, $ui, 2);
- ($cred->{username}, $cred->{password}) = ($u, $p);
- $cred->check_netrc unless defined $p;
- }
- my $common = $nn_args->{$sec} // {};
- my $nn_arg = {
- Port => $uri->port,
- Host => $host,
- SSL => $uri->secure, # snews == nntps
- %$common, # may Debug ....
- };
- my $nn = nn_new($nn_arg, $nntp_opt, $url);
-
- if ($cred) {
- $cred->fill; # may prompt user here
- if ($nn->authinfo($u, $p)) {
- push @{$nntp_opt->{-postconn}}, [ 'authinfo', $u, $p ];
- } else {
- warn "E: <$url> AUTHINFO $u XXXX failed\n";
- $nn = undef;
- }
- }
-
- if ($nntp_opt->{compress}) {
- # https://rt.cpan.org/Ticket/Display.html?id=129967
- if ($nn->can('compress')) {
- if ($nn->compress) {
- push @{$nntp_opt->{-postconn}}, [ 'compress' ];
- } else {
- warn "W: <$url> COMPRESS failed\n";
- }
- } else {
- delete $nntp_opt->{compress};
- warn <<"";
-W: <$url> COMPRESS not supported by Net::NNTP
-W: see https://rt.cpan.org/Ticket/Display.html?id=129967 for updates
-
- }
- }
-
- $self->{nn_arg}->{$sec} = $nn_arg;
- $cred->run($nn ? 'approve' : 'reject') if $cred;
- $nn;
-}
-
-sub nntp_fetch_all ($$$) {
- my ($self, $nn, $url) = @_;
- my $uri = uri_new($url);
- my ($group, $num_a, $num_b) = $uri->group;
- my $sec = uri_section($uri);
- 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 = $SIG{__WARN__} || \&CORE::warn;
- my ($err, $art);
- local $SIG{__WARN__} = sub {
- my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
- $warn_cb->("$pfx$url ", $art ? ("ARTICLE $art") : (), "\n", @_);
- };
- my $inboxes = $self->{nntp}->{$url};
- my $last_art;
- my $n = $self->{max_batch};
- for ($beg..$end) {
- last if $self->{quit};
- $art = $_;
- if (--$n < 0) {
- _done_for_now($self);
- $itrk->update_last(0, $last_art);
- $n = $self->{max_batch};
- }
- 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);
- $self->{pi_cfg}->each_inbox(\&remove_eml_i,
- $self, $eml, "$url ARTICLE $art");
- } else {
- die "BUG: destination unknown $inboxes";
- }
- $last_art = $art;
- }
- _done_for_now($self);
- $itrk->update_last(0, $last_art);
- $err;
-}
-
sub watch_nntp_init ($$) {
my ($self, $poll) = @_;
- eval { require Net::NNTP } or
- die "Net::NNTP is required for NNTP:\n$@\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, $url, $nn_args);
- }
- for my $url (keys %{$self->{nntp}}) {
- my $uri = uri_new($url);
+ PublicInbox::NetReader::nntp_common_init($self);
+ for my $uri (@{$self->{nntp_order}}) {
my $sec = uri_section($uri);
- my $intvl = $self->{nntp_opt}->{$sec}->{pollInterval};
- push @{$poll->{$intvl || 120}}, $url;
+ my $intvl = $self->{cfg_opt}->{$sec}->{pollInterval};
+ push @{$poll->{$intvl || 120}}, $uri;
}
}
my ($self, $sig, $oldset) = @_;
$self->{oldset} = $oldset;
$self->{sig} = $sig;
- my $poll = {}; # intvl_seconds => [ url1, url2 ]
+ my $poll = {}; # intvl_seconds => [ uri1, uri2 ]
watch_imap_init($self, $poll) if $self->{imap};
watch_nntp_init($self, $poll) if $self->{nntp};
- while (my ($intvl, $urls) = each %$poll) {
- # poll all URLs for a given interval sequentially
- PublicInbox::DS::add_timer(0, \&poll_fetch_fork,
- [$self, $intvl, $urls]);
+ while (my ($intvl, $uris) = each %$poll) {
+ # poll all URIs for a given interval sequentially
+ add_timer(0, \&poll_fetch_fork, $self, $intvl, $uris);
}
watch_fs_init($self) if $self->{mdre};
PublicInbox::DS->SetPostLoopCallback(sub { !$self->quit_done });
- PublicInbox::DS->EventLoop; # calls ->event_step
+ PublicInbox::DS::event_loop($sig, $oldset); # calls ->event_step
_done_for_now($self);
}
undef;
}
-sub uri_new {
- my ($url) = @_;
-
- # URI::snews exists, URI::nntps does not, so use URI::snews
- $url =~ s!\Anntps://!snews://!i;
- URI->new($url);
-}
-
-sub imap_url {
- my ($url) = @_;
- require PublicInbox::URIimap;
- my $uri = PublicInbox::URIimap->new($url);
- $uri ? $uri->canonical->as_string : undef;
-}
-
-my %IS_NNTP = (news => 1, snews => 1, nntp => 1);
-sub nntp_url {
- my ($url) = @_;
- require URI;
- my $uri = uri_new($url);
- return unless $uri && $IS_NNTP{$uri->scheme} && $uri->group;
- $url = $uri->canonical->as_string;
- # nntps is IANA registered, snews is deprecated
- $url =~ s!\Asnews://!nntps://!;
- $url;
-}
+sub folder_select { 'select' } # for PublicInbox::NetReader
1;