X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FNetReader.pm;h=c1af03a3f8b972db9a8ff38f0b081652dbb90a53;hb=961690bae47c90a4a6960952587c6f4463fb4b19;hp=f0f56431282312c37840809be755cac0007ba51e;hpb=9d11ed460ce113dd10cd098e2dfa814fcfbddde9;p=public-inbox.git diff --git a/lib/PublicInbox/NetReader.pm b/lib/PublicInbox/NetReader.pm index f0f56431..c1af03a3 100644 --- a/lib/PublicInbox/NetReader.pm +++ b/lib/PublicInbox/NetReader.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # common reader code for IMAP and NNTP (and maybe JMAP) @@ -35,6 +35,7 @@ sub socks_args ($) { eval { require IO::Socket::Socks } or die < $h, ProxyPort => $p }; } die "$val not understood (only socks5h:// is supported)\n"; @@ -42,20 +43,64 @@ EOM sub mic_new ($$$$) { my ($self, $mic_arg, $sec, $uri) = @_; - my %mic_arg = %$mic_arg; + my %mic_arg = (%$mic_arg, Keepalive => 1); my $sa = $self->{cfg_opt}->{$sec}->{-proxy_cfg} || $self->{-proxy_cli}; if ($sa) { - my %opt = %$sa; + # this `require' needed for worker[1..Inf], since socks_args + # only got called in worker[0] + require IO::Socket::Socks; + my %opt = (%$sa, Keepalive => 1); + $opt{SocksDebug} = 1 if $mic_arg{Debug}; $opt{ConnectAddr} = delete $mic_arg{Server}; $opt{ConnectPort} = delete $mic_arg{Port}; - $mic_arg{Socket} = IO::Socket::Socks->new(%opt) or die - "E: <$$uri> ".eval('$IO::Socket::Socks::SOCKS_ERROR'); + my $s = IO::Socket::Socks->new(%opt) or die + "E: <$uri> ".eval('$IO::Socket::Socks::SOCKS_ERROR'); + if ($mic_arg->{Ssl}) { # for imaps:// + require IO::Socket::SSL; + $s = IO::Socket::SSL->start_SSL($s) or die + "E: <$uri> ".(IO::Socket::SSL->errstr // ''); + } + $mic_arg{Socket} = $s; } - PublicInbox::IMAPClient->new(%mic_arg, Keepalive => 1); + PublicInbox::IMAPClient->new(%mic_arg); } sub auth_anon_cb { '' }; # for Mail::IMAPClient::Authcallback +sub onion_hint ($$) { + my ($lei, $uri) = @_; + $uri->host =~ /\.onion\z/i or return "\n"; + my $t = $uri->isa('PublicInbox::URIimap') ? 'imap' : 'nntp'; + my $url = PublicInbox::Config::squote_maybe(uri_section($uri)); + my $set_cfg = 'lei config'; + if (!$lei) { # public-inbox-watch + my $f = PublicInbox::Config::squote_maybe( + $ENV{PI_CONFIG} || '~/.public-inbox/config'); + $set_cfg = "git config -f $f"; + } + my $dq = substr($url, 0, 1) eq "'" ? '"' : ''; + < $uri->port, Server => $host, - Ssl => $uri->scheme eq 'imaps', %$common, # may set Starttls, Compress, Debug .... }; $mic_arg->{Ssl} = 1 if $uri->scheme eq 'imaps'; require PublicInbox::IMAPClient; - my $mic = mic_new($self, $mic_arg, $sec, $uri) or - die "E: <$uri> new: $@\n"; + my $mic = mic_new($self, $mic_arg, $sec, $uri); + ($mic && $mic->IsConnected) or + die "E: <$uri> new: $@".onion_hint($lei, $uri); + # default to using STARTTLS if it's available, but allow # it to be disabled since I usually connect to localhost if (!$mic_arg->{Ssl} && !defined($mic_arg->{Starttls}) && $mic->has_capability('STARTTLS') && + try_starttls($host) && $mic->can('starttls')) { $mic->starttls or die "E: <$uri> STARTTLS: $@\n"; } @@ -128,25 +175,18 @@ sub mic_for ($$$$) { # mic = Mail::IMAPClient $mic; } -# Net::NNTP doesn't support CAPABILITIES, yet -sub try_starttls ($) { - my ($host) = @_; - return if $host =~ /\.onion\z/s; - return if $host =~ /\A127\.[0-9]+\.[0-9]+\.[0-9]+\z/s; - return if $host eq '::1'; - 1; -} - sub nn_new ($$$) { my ($nn_arg, $nntp_cfg, $uri) = @_; my $nn; if (defined $nn_arg->{ProxyAddr}) { require PublicInbox::NetNNTPSocks; + $nn_arg->{SocksDebug} = 1 if $nn_arg->{Debug}; eval { $nn = PublicInbox::NetNNTPSocks->new_socks(%$nn_arg) }; die "E: <$uri> $@\n" if $@; } else { - $nn = Net::NNTP->new(%$nn_arg) or die "E: <$uri> new: $!\n"; + $nn = Net::NNTP->new(%$nn_arg) or return; } + setsockopt($nn, Socket::SOL_SOCKET(), Socket::SO_KEEPALIVE(), 1); # default to using STARTTLS if it's available, but allow # it to be disabled for localhost/VPN users @@ -202,7 +242,8 @@ sub nn_for ($$$$) { # nn = Net::NNTP $nn_arg->{SSL} = 1 if $uri->secure; # snews == nntps my $sa = $self->{-proxy_cli}; %$nn_arg = (%$nn_arg, %$sa) if $sa; - my $nn = nn_new($nn_arg, $nntp_cfg, $uri); + my $nn = nn_new($nn_arg, $nntp_cfg, $uri) or + die "E: <$uri> new: $@".onion_hint($lei, $uri); if ($cred) { $cred->fill($lei) unless defined($p); # may prompt user here if ($nn->authinfo($u, $p)) { @@ -287,7 +328,7 @@ sub imap_common_init ($;$) { my $sec = uri_section($uri); # knobs directly for Mail::IMAPClient->new - for my $k (qw(Starttls Debug Compress Ignoresizeerrors)) { + for my $k (qw(Starttls Debug Compress)) { my $bool = cfg_bool($cfg, "imap.$k", $$uri) // next; $mic_common->{$sec}->{$k} = $bool; } @@ -303,10 +344,10 @@ sub imap_common_init ($;$) { } my $k = 'imap.fetchBatchSize'; my $bs = $cfg->urlmatch($k, $$uri) // next; - if ($bs =~ /\A([0-9]+)\z/) { + if ($bs =~ /\A([0-9]+)\z/ && $bs > 0) { $self->{cfg_opt}->{$sec}->{batch_size} = $bs; } else { - warn "$k=$bs is not an integer\n"; + warn "$k=$bs is not a positive integer\n"; } } # make sure we can connect and cache the credentials in memory @@ -318,6 +359,7 @@ sub imap_common_init ($;$) { mic_for($self, $uri, $mic_common, $lei) // die "Unable to continue\n"; next unless $self->isa('PublicInbox::NetWriter'); + next if $self->{-skip_creat}; my $dst = $orig_uri->mailbox // next; next if $mic->exists($dst); # already exists $mic->create($dst) or die "CREATE $dst failed <$orig_uri>: $@"; @@ -439,7 +481,7 @@ sub itrk_last ($$;$$) { my ($self, $uri, $r_uidval, $mic) = @_; return (undef, undef, $r_uidval) unless $self->{incremental}; my ($itrk, $l_uid, $l_uidval); - if (defined(my $lms = $self->{-lms_ro})) { # LeiMailSync or 0 + if (defined(my $lms = $self->{-lms_rw})) { # LeiMailSync or 0 $uri->uidvalidity($r_uidval) if defined $r_uidval; if ($mic) { my $auth = $mic->Authmechanism // ''; @@ -498,6 +540,41 @@ sub perm_fl_ok ($) { # may be overridden in NetWriter or Watch sub folder_select { $_[0]->{each_old} ? 'select' : 'examine' } +sub _imap_fetch_bodies ($$$$) { + my ($self, $mic, $uri, $uids) = @_; + my $req = $mic->imap4rev1 ? 'BODY.PEEK[]' : 'RFC822.PEEK'; + my $key = $req; + $key =~ s/\.PEEK//; + my $sec = uri_section($uri); + my $mbx = $uri->mailbox; + my $bs = $self->{cfg_opt}->{$sec}->{batch_size} // 1; + my ($last_uid, $err); + my $use_fl = $self->{-use_fl}; + + while (scalar @$uids) { + my @batch = splice(@$uids, 0, $bs); + my $batch = join(',', @batch); + local $0 = "UID:$batch $mbx $sec"; + my $r = $mic->fetch_hash($batch, $req, 'FLAGS'); + unless ($r) { # network error? + last if $!{EINTR} && $self->{quit}; + $err = "E: $uri UID FETCH $batch error: $!"; + last; + } + for my $uid (@batch) { + # messages get deleted, so holes appear + my $per_uid = delete $r->{$uid} // next; + my $raw = delete($per_uid->{$key}) // next; + my $fl = $use_fl ? $per_uid->{FLAGS} : undef; + _imap_do_msg($self, $uri, $uid, \$raw, $fl); + $last_uid = $uid; + last if $self->{quit}; + } + last if $self->{quit}; + } + ($last_uid, $err); +} + sub _imap_fetch_all ($$$) { my ($self, $mic, $orig_uri) = @_; my $sec = uri_section($orig_uri); @@ -545,6 +622,7 @@ EOF $mic->Uid(1); # the default, we hope my $err; my $use_fl = perm_fl_ok($perm_fl); + local $self->{-use_fl} = $use_fl; if (!defined($single_uid) && $self->{each_old} && $use_fl) { $err = each_old_flags($self, $mic, $uri, $l_uid); return $err if $err; @@ -556,15 +634,12 @@ EOF my $m = $mod ? " [(UID % $mod) == $shard]" : ''; warn "# $uri fetching UID $l_uid:$r_uid$m\n"; } - my $bs = $self->{cfg_opt}->{$sec}->{batch_size} // 1; - my $req = $mic->imap4rev1 ? 'BODY.PEEK[]' : 'RFC822.PEEK'; - my $key = $req; - $key =~ s/\.PEEK//; - my ($uids, $batch); + my $fetch_cb = \&_imap_fetch_bodies; 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 + my $uids; if (defined $single_uid) { $uids = [ $single_uid ]; } elsif (!($uids = $mic->search("UID $l_uid:*"))) { @@ -582,31 +657,8 @@ EOF return if $uids->[0] < $l_uid; $l_uid = $uids->[-1] + 1; # for next search - my $last_uid; - my $n = $self->{max_batch}; - @$uids = grep { ($_ % $mod) == $shard } @$uids if $mod; - while (scalar @$uids) { - my @batch = splice(@$uids, 0, $bs); - $batch = join(',', @batch); - local $0 = "UID:$batch $mbx $sec"; - my $r = $mic->fetch_hash($batch, $req, 'FLAGS'); - unless ($r) { # network error? - last if $!{EINTR} && $self->{quit}; - $err = "E: $uri 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 = $use_fl ? $per_uid->{FLAGS} : undef; - _imap_do_msg($self, $uri, $uid, \$raw, $fl); - $last_uid = $uid; - last if $self->{quit}; - } - last if $self->{quit}; - } + (my $last_uid, $err) = $fetch_cb->($self, $mic, $uri, $uids); run_commit_cb($self); $itrk->update_last($r_uidval, $last_uid) if $itrk; } until ($err || $self->{quit} || defined($single_uid)); @@ -686,21 +738,27 @@ sub _nntp_fetch_all ($$$) { my $msg = ndump($nn->message); return "E: GROUP $group <$sec> $msg"; } - + (defined($num_a) && defined($num_b) && $num_a > $num_b) and + return "E: $uri: backwards range: $num_a > $num_b"; + if (defined($num_a)) { # no article numbers in mail_sync.sqlite3 + $uri = $uri->clone; + $uri->group($group); + } # 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, $l_art) = itrk_last($self, $uri); - # allow users to specify articles to refetch - # cf. https://tools.ietf.org/id/draft-gilman-news-url-01.txt - # nntp://example.com/inbox.foo/$num_a-$num_b - $beg = $num_a if defined($num_a) && $num_a < $beg; - $end = $num_b if defined($num_b) && $num_b < $end; - if (defined $l_art) { + if (defined($l_art) && !defined($num_a)) { return if $l_art >= $end; # nothing to do $beg = $l_art + 1; } + # allow users to specify articles to refetch + # cf. https://tools.ietf.org/id/draft-gilman-news-url-01.txt + # nntp://example.com/inbox.foo/$num_a-$num_b + $beg = $num_a if defined($num_a) && $num_a > $beg && $num_a <= $end; + $end = $num_b if defined($num_b) && $num_b >= $beg && $num_b < $end; + $end = $beg if defined($num_a) && !defined($num_b); my ($err, $art, $last_art, $kw); # kw stays undef, no keywords in NNTP unless ($self->{quiet}) { warn "# $uri fetching ARTICLE $beg..$end\n";