X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FNNTP.pm;h=8a31b910be76a317df6838879a5918a32d0c46b2;hb=3c30532aed6256a984c535530c6667552c2e6a84;hp=56d08385da0f6a4b924e07ffb01662ad288f0715;hpb=6e238ee3396719e578d6a90e177a71ce9f8c1ca0;p=public-inbox.git diff --git a/lib/PublicInbox/NNTP.pm b/lib/PublicInbox/NNTP.pm index 56d08385..8a31b910 100644 --- a/lib/PublicInbox/NNTP.pm +++ b/lib/PublicInbox/NNTP.pm @@ -1,45 +1,43 @@ -# Copyright (C) 2015 all contributors -# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt) +# Copyright (C) 2015-2018 all contributors +# License: AGPL-3.0+ # # Each instance of this represents a NNTP client socket package PublicInbox::NNTP; use strict; use warnings; -use base qw(Danga::Socket); +use base qw(PublicInbox::DS); use fields qw(nntpd article rbuf ng long_res); use PublicInbox::Search; use PublicInbox::Msgmap; +use PublicInbox::MID qw(mid_escape); use PublicInbox::Git; require PublicInbox::EvCleanup; use Email::Simple; use POSIX qw(strftime); use Time::HiRes qw(clock_gettime CLOCK_MONOTONIC); -use URI::Escape qw(uri_escape_utf8); +use Digest::SHA qw(sha1_hex); +use Time::Local qw(timegm timelocal); use constant { r501 => '501 command syntax error', r221 => '221 Header follows', r224 => '224 Overview information follows (multi-line)', r225 => '225 Headers follow (multi-line)', r430 => '430 No article with that message-id', - long_response_limit => 0xffffffff, }; sub now () { clock_gettime(CLOCK_MONOTONIC) }; -my @OVERVIEW = qw(Subject From Date Message-ID References); +my @OVERVIEW = qw(Subject From Date Message-ID References Xref); my $OVERVIEW_FMT = join(":\r\n", @OVERVIEW, qw(Bytes Lines)) . ":\r\n"; my $LIST_HEADERS = join("\r\n", @OVERVIEW, qw(:bytes :lines Xref To Cc)) . "\r\n"; # disable commands with easy DoS potential: -# LISTGROUP could get pretty bad, too... my %DISABLED; # = map { $_ => 1 } qw(xover list_overview_fmt newnews xhdr); my $EXPMAP; # fd -> [ idle_time, $self ] my $expt; our $EXPTIME = 180; # 3 minutes -my $WEAKEN = {}; # string(nntpd) -> nntpd -my $weakt; my $nextt; my $nextq = []; @@ -52,8 +50,16 @@ sub next_tick () { # before finishing reading: if (my $long_cb = $nntp->{long_res}) { $nntp->write($long_cb); - } elsif (&Danga::Socket::POLLIN & $nntp->{event_watch}) { + } else { + # pipelined request, we bypassed socket-readiness + # checks to get here: event_read($nntp); + + # maybe there's more pipelined data, or we'll have + # to register it for socket-readiness notifications + if (!$nntp->{long_res} && !$nntp->{closed}) { + check_read($nntp); + } } } } @@ -64,16 +70,6 @@ sub update_idle_time ($) { defined $fd and $EXPMAP->{$fd} = [ now(), $self ]; } -# reduce FD pressure by closing some "git cat-file --batch" processes -# and unused FDs for msgmap and Xapian indices -sub weaken_groups () { - $weakt = undef; - foreach my $nntpd (values %$WEAKEN) { - $_->weaken_all foreach (@{$nntpd->{grouplist}}); - } - $WEAKEN = {}; -} - sub expire_old () { my $now = now(); my $exp = $EXPTIME; @@ -92,15 +88,11 @@ sub expire_old () { $EXPMAP = \%new; if ($nr) { $expt = PublicInbox::EvCleanup::later(*expire_old); - weaken_groups(); } else { $expt = undef; # noop to kick outselves out of the loop ASAP so descriptors # really get closed PublicInbox::EvCleanup::asap(sub {}); - - # grace period for reaping resources - $weakt ||= PublicInbox::EvCleanup::later(*weaken_groups); } } @@ -109,11 +101,10 @@ sub new ($$$) { my $self = fields::new($class); $self->SUPER::new($sock); $self->{nntpd} = $nntpd; - res($self, '201 server ready - post via email'); + res($self, '201 ' . $nntpd->{servername} . ' ready - post via email'); $self->{rbuf} = ''; $self->watch_read(1); update_idle_time($self); - $WEAKEN->{"$nntpd"} = $nntpd; $expt ||= PublicInbox::EvCleanup::later(*expire_old); $self; } @@ -130,7 +121,8 @@ sub args_ok ($$) { # returns 1 if we can continue, 0 if not due to buffered writes or disconnect sub process_line ($$) { my ($self, $l) = @_; - my ($req, @args) = split(/\s+/, $l); + my ($req, @args) = split(/[ \t]/, $l); + return 1 unless defined($req); # skip blank line $req = lc($req); $req = eval { no strict 'refs'; @@ -142,6 +134,7 @@ sub process_line ($$) { my $res = eval { $req->($self, @args) }; my $err = $@; if ($err && !$self->{closed}) { + local $/ = "\n"; chomp($l); err($self, 'error from: %s (%s)', $l, $err); $res = '503 program fault - command not performed'; @@ -239,21 +232,17 @@ sub cmd_listgroup ($;$) { } $self->{ng} or return '412 no newsgroup selected'; - long_response($self, 0, long_response_limit, sub { - my ($i) = @_; - my $nr = $self->{ng}->mm->id_batch($$i, sub { - my ($ary) = @_; - more($self, join("\r\n", @$ary)); - }); - - # -1 to adjust for implicit increment in long_response - $$i = $nr ? $$i + $nr - 1 : long_response_limit; + my $n = 0; + long_response($self, sub { + my $ary = $self->{ng}->mm->ids_after(\$n); + scalar @$ary or return; + more($self, join("\r\n", @$ary)); + 1; }); } sub parse_time ($$;$) { my ($date, $time, $gmt) = @_; - use Time::Local qw(); my ($hh, $mm, $ss) = unpack('A2A2A2', $time); if (defined $gmt) { $gmt =~ /\A(?:UTC|GMT)\z/i or die "GM invalid: $gmt"; @@ -265,15 +254,15 @@ sub parse_time ($$;$) { ($YYYY, $MM, $DD) = unpack('A4A2A2', $date); } else { # legacy clients send YYMMDD ($YYYY, $MM, $DD) = unpack('A2A2A2', $date); - if ($YYYY > strftime('%y', @now)) { - my $cur_year = $now[5] + 1900; + my $cur_year = $now[5] + 1900; + if ($YYYY > $cur_year) { $YYYY += int($cur_year / 1000) * 1000 - 100; } } if ($gmt) { - Time::Local::timegm($ss, $mm, $hh, $DD, $MM - 1, $YYYY); + timegm($ss, $mm, $hh, $DD, $MM - 1, $YYYY); } else { - Time::Local::timelocal($ss, $mm, $hh, $DD, $MM - 1, $YYYY); + timelocal($ss, $mm, $hh, $DD, $MM - 1, $YYYY); } } @@ -302,7 +291,6 @@ sub wildmat2re (;$) { return $_[0] = qr/.*/ if (!defined $_[0] || $_[0] eq '*'); my %keep; my $salt = rand; - use Digest::SHA qw(sha1_hex); my $tmp = $_[0]; $tmp =~ s#(?{nntpd}->{grouplist}}) { $ng->{newsgroup} =~ $keep or next; $ng->{newsgroup} =~ $skip and next; - my $srch = $ng->search or next; - push @srch, $srch; + my $over = $ng->over or next; + push @over, $over; }; - return '.' unless @srch; - - $ts .= '..'; - my $opts = { asc => 1, limit => 1000, offset => 0 }; - long_response($self, 0, long_response_limit, sub { - my ($i) = @_; - my $srch = $srch[0]; - my $res = $srch->query($ts, $opts); - my $msgs = $res->{msgs}; - if (my $nr = scalar @$msgs) { + return '.' unless @over; + + my $prev = 0; + long_response($self, sub { + my $over = $over[0]; + my $msgs = $over->query_ts($ts, $prev); + if (scalar @$msgs) { more($self, '<' . join(">\r\n<", map { $_->mid } @$msgs ). '>'); - $opts->{offset} += $nr; + $prev = $msgs->[-1]->{num}; } else { - shift @srch; - if (@srch) { # continue onto next newsgroup - $opts->{offset} = 0; + shift @over; + if (@over) { # continue onto next newsgroup + $prev = 0; + return 1; } else { # break out of the long response. - $$i = long_response_limit; + return; } } }); @@ -429,15 +415,53 @@ sub header_append ($$$) { $hdr->header_set($k, @v, $v); } -sub set_nntp_headers { - my ($hdr, $ng, $n, $mid) = @_; +sub xref ($$$$) { + my ($self, $ng, $n, $mid) = @_; + my $ret = $self->{nntpd}->{servername} . " $ng->{newsgroup}:$n"; + + # num_for is pretty cheap and sometimes we'll lookup the existence + # of an article without getting even the OVER info. In other words, + # I'm not sure if its worth optimizing by scanning To:/Cc: and + # PublicInbox::ExtMsg on the PSGI end is just as expensive + foreach my $other (@{$self->{nntpd}->{grouplist}}) { + next if $ng eq $other; + my $num = eval { $other->mm->num_for($mid) } or next; + $ret .= " $other->{newsgroup}:$num"; + } + $ret; +} + +sub set_nntp_headers ($$$$$) { + my ($self, $hdr, $ng, $n, $mid) = @_; + + # why? leafnode requires a Path: header for some inexplicable + # reason. We'll fake the shortest one possible. + $hdr->header_set('Path', 'y'); + + # leafnode (and maybe other NNTP clients) have trouble dealing + # with v2 messages which have multiple Message-IDs (either due + # to our own content-based dedupe or buggy git-send-email versions). + my @mids = $hdr->header('Message-ID'); + if (scalar(@mids) > 1) { + my $mid0 = "<$mid>"; + $hdr->header_set('Message-ID', $mid0); + my @alt = $hdr->header('X-Alt-Message-ID'); + my %seen = map { $_ => 1 } (@alt, $mid0); + foreach my $m (@mids) { + next if $seen{$m}++; + push @alt, $m; + } + $hdr->header_set('X-Alt-Message-ID', @alt); + } # clobber some - $hdr->header_set('Newsgroups', $ng->{newsgroup}); - $hdr->header_set('Xref', xref($ng, $n)); + my $xref = xref($self, $ng, $n, $mid); + $hdr->header_set('Xref', $xref); + $xref =~ s/:[0-9]+//g; + $hdr->header_set('Newsgroups', (split(/ /, $xref, 2))[1]); header_append($hdr, 'List-Post', "{-primary_address}>"); if (my $url = $ng->base_url) { - $mid = uri_escape_utf8($mid); + $mid = mid_escape($mid); header_append($hdr, 'Archived-At', "<$url$mid/>"); header_append($hdr, 'List-Archive', "<$url>"); } @@ -449,7 +473,7 @@ sub art_lookup ($$$) { my ($n, $mid); my $err; if (defined $art) { - if ($art =~ /\A\d+\z/o) { + if ($art =~ /\A[0-9]+\z/) { $err = '423 no such article number in this group'; $n = int($art); goto find_mid; @@ -479,18 +503,16 @@ find_mid: defined $mid or return $err; } found: - my $bytes; - my $s = eval { $ng->msg_by_mid($mid, \$bytes) } or return $err; - $s = Email::Simple->new($s); - my $lines; + my $smsg = $ng->over->get_art($n) or return $err; + my $msg = $ng->msg_by_smsg($smsg) or return $err; + my $s = Email::Simple->new($msg); if ($set_headers) { - set_nntp_headers($s->header_obj, $ng, $n, $mid); - $lines = $s->body =~ tr!\n!\n!; + set_nntp_headers($self, $s->header_obj, $ng, $n, $mid); # must be last $s->body_set('') if ($set_headers == 2); } - [ $n, $mid, $s, $bytes, $lines, $ng ]; + [ $n, $mid, $s, $smsg->bytes, $smsg->lines, $ng ]; } sub simple_body_write ($$) { @@ -506,12 +528,20 @@ sub simple_body_write ($$) { sub set_art { my ($self, $art) = @_; - $self->{article} = $art if defined $art && $art =~ /\A\d+\z/; + $self->{article} = $art if defined $art && $art =~ /\A[0-9]+\z/; } sub _header ($) { my $hdr = $_[0]->header_obj->as_string; utf8::encode($hdr); + $hdr =~ s/(?mm->minmax; - if ($range =~ /\A(\d+)\z/) { + if ($range =~ /\A([0-9]+)\z/) { $beg = $end = $1; - } elsif ($range =~ /\A(\d+)-\z/) { + } elsif ($range =~ /\A([0-9]+)-\z/) { ($beg, $end) = ($1, $max); - } elsif ($range =~ /\A(\d+)-(\d+)\z/) { + } elsif ($range =~ /\A([0-9]+)-([0-9]+)\z/) { ($beg, $end) = ($1, $2); } else { return r501; @@ -588,8 +618,8 @@ sub get_range ($$) { [ $beg, $end ]; } -sub long_response ($$$$) { - my ($self, $beg, $end, $cb) = @_; +sub long_response ($$) { + my ($self, $cb) = @_; die "BUG: nested long response" if $self->{long_res}; my $fd = $self->{fd}; @@ -600,32 +630,23 @@ sub long_response ($$$$) { $self->watch_read(0); my $t0 = now(); $self->{long_res} = sub { - # limit our own running time for fairness with other - # clients and to avoid buffering too much: - my $lim = 100; - - my $err; - do { - eval { $cb->(\$beg) }; - } until (($err = $@) || $self->{closed} || - ++$beg > $end || !--$lim || $self->{write_buf_size}); - - if ($err || $self->{closed}) { + my $more = eval { $cb->() }; + if ($@ || $self->{closed}) { $self->{long_res} = undef; - if ($err) { + if ($@) { err($self, "%s during long response[$fd] - %0.6f", - $err, now() - $t0); + $@, now() - $t0); } if ($self->{closed}) { out($self, " deferred[$fd] aborted - %0.6f", now() - $t0); } else { update_idle_time($self); - $self->watch_read(1); + check_read($self); } - } elsif (!$lim || $self->{write_buf_size}) { + } elsif ($more) { # $self->{write_buf_size}: # no recursion, schedule another call ASAP # but only after all pending writes are done update_idle_time($self); @@ -634,7 +655,7 @@ sub long_response ($$$$) { $nextt ||= PublicInbox::EvCleanup::asap(*next_tick); } else { # all done! $self->{long_res} = undef; - $self->watch_read(1); + check_read($self); res($self, '.'); out($self, " deferred[$fd] done - %0.6f", now() - $t0); } @@ -657,19 +678,17 @@ sub hdr_message_id ($$$) { # optimize XHDR Message-ID [range] for slrnpull. my $mm = $self->{ng}->mm; my ($beg, $end) = @$r; more($self, $xhdr ? r221 : r225); - long_response($self, $beg, $end, sub { - my ($i) = @_; - my $mid = $mm->mid_for($$i); - more($self, "$$i <$mid>") if defined $mid; + long_response($self, sub { + my $r = $mm->msg_range(\$beg, $end); + @$r or return; + more($self, join("\r\n", map { + "$_->[0] <$_->[1]>" + } @$r)); + 1; }); } } -sub xref ($$) { - my ($ng, $n) = @_; - "$ng->{domain} $ng->{newsgroup}:$n" -} - sub mid_lookup ($$) { my ($self, $mid) = @_; my $self_ng = $self->{ng}; @@ -689,9 +708,11 @@ sub hdr_xref ($$$) { # optimize XHDR Xref [range] for rtin my ($self, $xhdr, $range) = @_; if (defined $range && $range =~ /\A<(.+)>\z/) { # Message-ID - my ($ng, $n) = mid_lookup($self, $1); + my $mid = $1; + my ($ng, $n) = mid_lookup($self, $mid); return r430 unless $n; - hdr_mid_response($self, $xhdr, $ng, $n, $range, xref($ng, $n)); + hdr_mid_response($self, $xhdr, $ng, $n, $range, + xref($self, $ng, $n, $mid)); } else { # numeric range $range = $self->{article} unless defined $range; my $r = get_range($self, $range); @@ -700,50 +721,51 @@ sub hdr_xref ($$$) { # optimize XHDR Xref [range] for rtin my $mm = $ng->mm; my ($beg, $end) = @$r; more($self, $xhdr ? r221 : r225); - long_response($self, $beg, $end, sub { - my ($i) = @_; - my $mid = $mm->mid_for($$i); - more($self, "$$i ".xref($ng, $$i)) if defined $mid; + long_response($self, sub { + my $r = $mm->msg_range(\$beg, $end); + @$r or return; + more($self, join("\r\n", map { + my $num = $_->[0]; + "$num ".xref($self, $ng, $num, $_->[1]); + } @$r)); + 1; }); } } -sub search_header_for { - my ($srch, $mid, $field) = @_; - my $smsg = $srch->lookup_mail($mid) or return; - $smsg->$field; +sub over_header_for { + my ($over, $num, $field) = @_; + my $smsg = $over->get_art($num) or return; + return PublicInbox::SearchMsg::date($smsg) if $field eq 'date'; + $smsg->{$field}; } sub hdr_searchmsg ($$$$) { my ($self, $xhdr, $field, $range) = @_; if (defined $range && $range =~ /\A<(.+)>\z/) { # Message-ID my ($ng, $n) = mid_lookup($self, $1); - return r430 unless $n; - my $v = search_header_for($ng->search, $range, $field); + return r430 unless defined $n; + my $v = over_header_for($ng->over, $n, $field); hdr_mid_response($self, $xhdr, $ng, $n, $range, $v); } else { # numeric range $range = $self->{article} unless defined $range; - my $srch = $self->{ng}->search; + my $over = $self->{ng}->over; my $mm = $self->{ng}->mm; my $r = get_range($self, $range); return $r unless ref $r; my ($beg, $end) = @$r; more($self, $xhdr ? r221 : r225); - my $off = 0; - long_response($self, $beg, $end, sub { - my ($i) = @_; - my $res = $srch->query_xover($beg, $end, $off); - my $msgs = $res->{msgs}; + my $cur = $beg; + long_response($self, sub { + my $msgs = $over->query_xover($cur, $end); my $nr = scalar @$msgs or return; - $off += $nr; my $tmp = ''; foreach my $s (@$msgs) { - $tmp .= $s->num . ' ' . $s->$field . "\r\n"; + $tmp .= $s->{num} . ' ' . $s->$field . "\r\n"; } utf8::encode($tmp); do_more($self, $tmp); - # -1 to adjust for implicit increment in long_response - $$i = $nr ? $$i + $nr - 1 : long_response_limit; + $cur = $msgs->[-1]->{num} + 1; }); } } @@ -815,28 +837,29 @@ sub cmd_xrover ($;$) { return $r unless ref $r; my ($beg, $end) = @$r; my $mm = $ng->mm; - my $srch = $ng->search; + my $over = $ng->over; more($self, '224 Overview information follows'); - long_response($self, $beg, $end, sub { - my ($i) = @_; - my $mid = $mm->mid_for($$i) or return; - my $h = search_header_for($srch, $mid, 'references'); - more($self, "$$i $h"); + + long_response($self, sub { + my $h = over_header_for($over, $beg, 'references'); + more($self, "$beg $h") if defined($h); + $beg++ < $end; }); } -sub over_line ($$) { - my ($num, $smsg) = @_; +sub over_line ($$$$) { + my ($self, $ng, $num, $smsg) = @_; # n.b. field access and procedural calls can be # 10%-15% faster than OO method calls: my $s = join("\t", $num, $smsg->{subject}, $smsg->{from}, PublicInbox::SearchMsg::date($smsg), - '<'.PublicInbox::SearchMsg::mid($smsg).'>', + "<$smsg->{mid}>", $smsg->{references}, - PublicInbox::SearchMsg::bytes($smsg), - PublicInbox::SearchMsg::lines($smsg)); + $smsg->{bytes}, + $smsg->{lines}, + "Xref: " . xref($self, $ng, $num, $smsg->{mid})); utf8::encode($s); $s } @@ -845,14 +868,14 @@ sub cmd_over ($;$) { my ($self, $range) = @_; if ($range && $range =~ /\A<(.+)>\z/) { my ($ng, $n) = mid_lookup($self, $1); - my $smsg = $ng->search->lookup_mail($range) or - return '430 No article with that message-id'; + defined $n or return r430; + my $smsg = $ng->over->get_art($n) or return r430; more($self, '224 Overview information follows (multi-line)'); # Only set article number column if it's the current group my $self_ng = $self->{ng}; $n = 0 if (!$self_ng || $self_ng ne $ng); - more($self, over_line($n, $smsg)); + more($self, over_line($self, $ng, $n, $smsg)); '.'; } else { cmd_xover($self, $range); @@ -866,22 +889,17 @@ sub cmd_xover ($;$) { return $r unless ref $r; my ($beg, $end) = @$r; more($self, "224 Overview information follows for $beg to $end"); - my $srch = $self->{ng}->search; - my $off = 0; - long_response($self, $beg, $end, sub { - my ($i) = @_; - my $res = $srch->query_xover($beg, $end, $off); - my $msgs = $res->{msgs}; + my $over = $self->{ng}->over; + my $cur = $beg; + long_response($self, sub { + my $msgs = $over->query_xover($cur, $end); my $nr = scalar @$msgs or return; - $off += $nr; # OVERVIEW.FMT more($self, join("\r\n", map { - over_line(PublicInbox::SearchMsg::num($_), $_); + over_line($self, $self->{ng}, $_->{num}, $_); } @$msgs)); - - # -1 to adjust for implicit increment in long_response - $$i = $nr ? $$i + $nr - 1 : long_response_limit; + $cur = $msgs->[-1]->{num} + 1; }); } @@ -911,7 +929,7 @@ sub more ($$) { sub do_write ($$) { my ($self, $data) = @_; my $done = $self->write($data); - die if $self->{closed}; + return 0 if $self->{closed}; # Do not watch for readability if we have data in the queue, # instead re-enable watching for readability when we can @@ -945,7 +963,7 @@ sub do_more ($$) { do_write($self, $data); } -# callbacks for Danga::Socket +# callbacks for PublicInbox::DS sub event_hup { $_[0]->close } sub event_err { $_[0]->close } @@ -962,11 +980,13 @@ sub event_write { sub event_read { my ($self) = @_; use constant LINE_MAX => 512; # RFC 977 section 2.3 - my $r = 1; - my $buf = $self->read(LINE_MAX) or return $self->close; - $self->{rbuf} .= $$buf; - while ($r > 0 && $self->{rbuf} =~ s/\A\s*([^\r\n]+)\r?\n//) { + if (index($self->{rbuf}, "\n") < 0) { + my $buf = $self->read(LINE_MAX) or return $self->close; + $self->{rbuf} .= $$buf; + } + my $r = 1; + while ($r > 0 && $self->{rbuf} =~ s/\A[ \t\r\n]*([^\r\n]*)\r?\n//) { my $line = $1; return $self->close if $line =~ /[[:cntrl:]]/s; my $t0 = now(); @@ -983,10 +1003,9 @@ sub event_read { update_idle_time($self); } -sub watch_read { - my ($self, $bool) = @_; - my $rv = $self->SUPER::watch_read($bool); - if ($bool && $self->{rbuf} ne '') { +sub check_read { + my ($self) = @_; + if (index($self->{rbuf}, "\n") >= 0) { # Force another read if there is a pipelined request. # We don't know if the socket has anything for us to read, # and we must double-check again by the time the timer fires @@ -994,8 +1013,11 @@ sub watch_read { # another long response. push @$nextq, $self; $nextt ||= PublicInbox::EvCleanup::asap(*next_tick); + } else { + # no pipelined requests available, let the kernel know + # to wake us up if there's more + $self->watch_read(1); # PublicInbox::DS::watch_read } - $rv; } sub not_idle_long ($$) {