X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FNNTP.pm;h=54207500dd8db5576658ae993169efd10318fdc5;hb=3b1b7abf814dbc7f2a737b2ca0e12b0fa518ff44;hp=b80ab4a81c01da7f9f8e3f77f282a236dee6f8d1;hpb=207b89615a1a0c06dd9afc94ca2200b889dc35e1;p=public-inbox.git diff --git a/lib/PublicInbox/NNTP.pm b/lib/PublicInbox/NNTP.pm index b80ab4a8..54207500 100644 --- a/lib/PublicInbox/NNTP.pm +++ b/lib/PublicInbox/NNTP.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2019 all contributors +# Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ # # Each instance of this represents a NNTP client socket @@ -7,8 +7,8 @@ use strict; use warnings; use base qw(PublicInbox::DS); use fields qw(nntpd article ng long_cb); -use PublicInbox::MID qw(mid_escape); -use Email::Simple; +use PublicInbox::MID qw(mid_escape $MID_EXTRACT); +use PublicInbox::Eml; use POSIX qw(strftime); use PublicInbox::DS qw(now); use Digest::SHA qw(sha1_hex); @@ -24,7 +24,7 @@ use constant { }; use PublicInbox::Syscall qw(EPOLLIN EPOLLONESHOT); use Errno qw(EAGAIN); - +my $ONE_MSGID = qr/\A$MID_EXTRACT\z/; my @OVERVIEW = qw(Subject From Date Message-ID References); my $OVERVIEW_FMT = join(":\r\n", @OVERVIEW, qw(Bytes Lines), '') . "Xref:full\r\n"; @@ -38,8 +38,7 @@ NEWNEWS\r LIST ACTIVE ACTIVE.TIMES NEWSGROUPS OVERVIEW.FMT\r HDR\r OVER\r - -my $have_deflate; +COMPRESS DEFLATE\r sub greet ($) { $_[0]->write($_[0]->{nntpd}->{greet}) }; @@ -76,7 +75,7 @@ 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(/[ \t]/, $l); + my ($req, @args) = split(/[ \t]+/, $l); return 1 unless defined($req); # skip blank line $req = $self->can('cmd_'.lc($req)); return res($self, '500 command not recognized') unless $req; @@ -180,6 +179,22 @@ sub cmd_list ($;$$) { '.' } +sub listgroup_range_i { + my ($self, $beg, $end) = @_; + my $r = $self->{ng}->mm->msg_range($beg, $end, 'num'); + scalar(@$r) or return; + more($self, join("\r\n", map { $_->[0] } @$r)); + 1; +} + +sub listgroup_all_i { + my ($self, $num) = @_; + my $ary = $self->{ng}->mm->ids_after($num); + scalar(@$ary) or return; + more($self, join("\r\n", @$ary)); + 1; +} + sub cmd_listgroup ($;$$) { my ($self, $group, $range) = @_; if (defined $group) { @@ -187,26 +202,13 @@ sub cmd_listgroup ($;$$) { return $res if ($res !~ /\A211 /); more($self, $res); } - my $ng = $self->{ng} or return '412 no newsgroup selected'; - my $mm = $ng->mm; + $self->{ng} or return '412 no newsgroup selected'; if (defined $range) { my $r = get_range($self, $range); return $r unless ref $r; - my ($beg, $end) = @$r; - long_response($self, sub { - $r = $mm->msg_range($beg, $end, 'num'); - scalar(@$r) or return; - more($self, join("\r\n", map { $_->[0] } @$r)); - 1; - }); + long_response($self, \&listgroup_range_i, @$r); } else { # grab every article number - my $n = 0; - long_response($self, sub { - my $ary = $mm->ids_after(\$n); - scalar(@$ary) or return; - more($self, join("\r\n", @$ary)); - 1; - }); + long_response($self, \&listgroup_all_i, \(my $num = 0)); } } @@ -217,16 +219,17 @@ sub parse_time ($$;$) { $gmt =~ /\A(?:UTC|GMT)\z/i or die "GM invalid: $gmt"; $gmt = 1; } - my @now = $gmt ? gmtime : localtime; my ($YYYY, $MM, $DD); if (bytes::length($date) == 8) { # RFC 3977 allows YYYYMMDD ($YYYY, $MM, $DD) = unpack('A4A2A2', $date); } else { # legacy clients send YYMMDD - ($YYYY, $MM, $DD) = unpack('A2A2A2', $date); + my $YY; + ($YY, $MM, $DD) = unpack('A2A2A2', $date); + my @now = $gmt ? gmtime : localtime; my $cur_year = $now[5] + 1900; - if ($YYYY > $cur_year) { - $YYYY += int($cur_year / 1000) * 1000 - 100; - } + my $cur_cent = int($cur_year / 100) * 100; + $YYYY = (($YY + $cur_cent) > $cur_year) ? + ($YY + 1900) : ($YY + $cur_cent); } if ($gmt) { timegm($ss, $mm, $hh, $DD, $MM - 1, $YYYY); @@ -287,6 +290,26 @@ sub ngpat2re (;$) { $_[0] = qr/\A(?:$_[0])\z/; } +sub newnews_i { + my ($self, $overs, $ts, $prev) = @_; + my $over = $overs->[0]; + my $msgs = $over->query_ts($ts, $$prev); + if (scalar @$msgs) { + more($self, '<' . + join(">\r\n<", map { $_->mid } @$msgs ). + '>'); + $$prev = $msgs->[-1]->{num}; + } else { + shift @$overs; + if (@$overs) { # continue onto next newsgroup + $$prev = 0; + return 1; + } else { # break out of the long response. + return; + } + } +} + sub cmd_newnews ($$$$;$$) { my ($self, $newsgroups, $date, $time, $gmt, $dists) = @_; my $ts = eval { parse_time($date, $time, $gmt) }; @@ -295,34 +318,17 @@ sub cmd_newnews ($$$$;$$) { my ($keep, $skip) = split('!', $newsgroups, 2); ngpat2re($keep); ngpat2re($skip); - my @over; + my @overs; foreach my $ng (@{$self->{nntpd}->{grouplist}}) { $ng->{newsgroup} =~ $keep or next; $ng->{newsgroup} =~ $skip and next; my $over = $ng->over or next; - push @over, $over; + push @overs, $over; }; - return '.' unless @over; + return '.' unless @overs; 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 ). - '>'); - $prev = $msgs->[-1]->{num}; - } else { - shift @over; - if (@over) { # continue onto next newsgroup - $prev = 0; - return 1; - } else { # break out of the long response. - return; - } - } - }); + long_response($self, \&newnews_i, \@overs, $ts, \$prev); } sub cmd_group ($$) { @@ -377,7 +383,7 @@ sub cmd_quit ($) { sub header_append ($$$) { my ($hdr, $k, $v) = @_; - my @v = $hdr->header($k); + my @v = $hdr->header_raw($k); foreach (@v) { return if $v eq $_; } @@ -410,16 +416,13 @@ sub set_nntp_headers ($$$$$) { # leafnode (and maybe other NNTP clients) have trouble dealing # with v2 messages which have multiple Message-IDs (either due # to our own content-based dedupe or buggy git-send-email versions). - my @mids = $hdr->header('Message-ID'); + my @mids = $hdr->header_raw('Message-ID'); if (scalar(@mids) > 1) { my $mid0 = "<$mid>"; $hdr->header_set('Message-ID', $mid0); - my @alt = $hdr->header('X-Alt-Message-ID'); + my @alt = $hdr->header_raw('X-Alt-Message-ID'); my %seen = map { $_ => 1 } (@alt, $mid0); - foreach my $m (@mids) { - next if $seen{$m}++; - push @alt, $m; - } + push(@alt, grep { !$seen{$_}++ } @mids); $hdr->header_set('X-Alt-Message-ID', @alt); } @@ -446,7 +449,7 @@ sub art_lookup ($$$) { $err = '423 no such article number in this group'; $n = int($art); goto find_mid; - } elsif ($art =~ /\A<([^>]+)>\z/) { + } elsif ($art =~ $ONE_MSGID) { $mid = $1; $err = r430; $n = $ng->mm->num_for($mid) if $ng; @@ -475,10 +478,9 @@ found: my $smsg = $ng->over->get_art($n) or return $err; my $msg = $ng->msg_by_smsg($smsg) or return $err; - # Email::Simple->new will modify $msg in-place as documented - # in its manpage, so what's left is the body and we won't need - # to call Email::Simple::body(), later - my $hdr = Email::Simple->new($msg)->header_obj; + # PublicInbox::Eml->new will modify $msg in-place, so what's + # left is the body and we won't need to call ->body(), later + my $hdr = PublicInbox::Eml->new($msg)->header_obj; set_nntp_headers($self, $hdr, $ng, $n, $mid) if $set_headers; [ $n, $mid, $msg, $hdr ]; } @@ -502,13 +504,13 @@ sub set_art { sub msg_hdr_write ($$$) { my ($self, $hdr, $body_follows) = @_; $hdr = $hdr->as_string; + # fixup old bug from import (pre-a0c07cba0e5d8b6a) + $hdr =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; utf8::encode($hdr); $hdr =~ s/(?msg_more($hdr); @@ -589,12 +591,11 @@ sub get_range ($$) { sub long_step { my ($self) = @_; # wbuf is unset or empty, here; {long} may add to it - my ($cb, $t0, @args) = @{$self->{long_cb}}; + my ($fd, $cb, $t0, @args) = @{$self->{long_cb}}; my $more = eval { $cb->($self, @args) }; if ($@ || !$self->{sock}) { # something bad happened... delete $self->{long_cb}; my $elapsed = now() - $t0; - my $fd = fileno($self->{sock}); if ($@) { err($self, "%s during long response[$fd] - %0.6f", @@ -610,20 +611,19 @@ sub long_step { # each other's data $self->zflush; - # no recursion, schedule another call ASAP - # but only after all pending writes are done - my $wbuf = $self->{wbuf} ||= []; - push @$wbuf, \&long_step; + # no recursion, schedule another call ASAP, but only after + # all pending writes are done. autovivify wbuf: + my $new_size = push(@{$self->{wbuf}}, \&long_step); # wbuf may be populated by $cb, no need to rearm if so: - $self->requeue if scalar(@$wbuf) == 1; + $self->requeue if $new_size == 1; } else { # all done! delete $self->{long_cb}; res($self, '.'); my $elapsed = now() - $t0; my $fd = fileno($self->{sock}); out($self, " deferred[$fd] done - %0.6f", $elapsed); - my $wbuf = $self->{wbuf}; + my $wbuf = $self->{wbuf}; # do NOT autovivify $self->requeue unless $wbuf && @$wbuf; } } @@ -631,19 +631,27 @@ sub long_step { sub long_response ($$;@) { my ($self, $cb, @args) = @_; # cb returns true if more, false if done - $self->{sock} or return; + my $sock = $self->{sock} or return; # make sure we disable reading during a long response, # clients should not be sending us stuff and making us do more # work while we are stream a response to them - $self->{long_cb} = [ $cb, now(), @args ]; + $self->{long_cb} = [ fileno($sock), $cb, now(), @args ]; long_step($self); # kick off! undef; } +sub hdr_msgid_range_i { + my ($self, $beg, $end) = @_; + my $r = $self->{ng}->mm->msg_range($beg, $end); + @$r or return; + more($self, join("\r\n", map { "$_->[0] <$_->[1]>" } @$r)); + 1; +} + sub hdr_message_id ($$$) { # optimize XHDR Message-ID [range] for slrnpull. my ($self, $xhdr, $range) = @_; - if (defined $range && $range =~ /\A<(.+)>\z/) { # Message-ID + if (defined $range && $range =~ $ONE_MSGID) { my ($ng, $n) = mid_lookup($self, $1); return r430 unless $n; hdr_mid_response($self, $xhdr, $ng, $n, $range, $range); @@ -651,17 +659,8 @@ sub hdr_message_id ($$$) { # optimize XHDR Message-ID [range] for slrnpull. $range = $self->{article} unless defined $range; my $r = get_range($self, $range); return $r unless ref $r; - my $mm = $self->{ng}->mm; - my ($beg, $end) = @$r; more($self, $xhdr ? r221 : r225); - long_response($self, sub { - my $r = $mm->msg_range($beg, $end); - @$r or return; - more($self, join("\r\n", map { - "$_->[0] <$_->[1]>" - } @$r)); - 1; - }); + long_response($self, \&hdr_msgid_range_i, @$r); } } @@ -695,7 +694,7 @@ sub xref_range_i { sub hdr_xref ($$$) { # optimize XHDR Xref [range] for rtin my ($self, $xhdr, $range) = @_; - if (defined $range && $range =~ /\A<(.+)>\z/) { # Message-ID + if (defined $range && $range =~ $ONE_MSGID) { my $mid = $1; my ($ng, $n) = mid_lookup($self, $mid); return r430 unless $n; @@ -713,37 +712,37 @@ sub hdr_xref ($$$) { # optimize XHDR Xref [range] for rtin sub over_header_for { my ($over, $num, $field) = @_; my $smsg = $over->get_art($num) or return; - return PublicInbox::SearchMsg::date($smsg) if $field eq 'date'; + return PublicInbox::Smsg::date($smsg) if $field eq 'date'; $smsg->{$field}; } -sub hdr_searchmsg ($$$$) { +sub smsg_range_i { + my ($self, $beg, $end, $field) = @_; + my $over = $self->{ng}->over; + my $msgs = $over->query_xover($$beg, $end); + scalar(@$msgs) or return; + my $tmp = ''; + foreach my $s (@$msgs) { + $tmp .= $s->{num} . ' ' . $s->$field . "\r\n"; + } + utf8::encode($tmp); + $self->msg_more($tmp); + $$beg = $msgs->[-1]->{num} + 1; +} + +sub hdr_smsg ($$$$) { my ($self, $xhdr, $field, $range) = @_; - if (defined $range && $range =~ /\A<(.+)>\z/) { # Message-ID + if (defined $range && $range =~ $ONE_MSGID) { my ($ng, $n) = mid_lookup($self, $1); return r430 unless defined $n; my $v = over_header_for($ng->over, $n, $field); hdr_mid_response($self, $xhdr, $ng, $n, $range, $v); } else { # numeric range $range = $self->{article} unless defined $range; - my $over = $self->{ng}->over; - my $mm = $self->{ng}->mm; my $r = get_range($self, $range); return $r unless ref $r; - my ($beg, $end) = @$r; more($self, $xhdr ? r221 : r225); - my $cur = $$beg; - long_response($self, sub { - my $msgs = $over->query_xover($cur, $end); - my $nr = scalar @$msgs or return; - my $tmp = ''; - foreach my $s (@$msgs) { - $tmp .= $s->{num} . ' ' . $s->$field . "\r\n"; - } - utf8::encode($tmp); - $self->msg_more($tmp); - $cur = $msgs->[-1]->{num} + 1; - }); + long_response($self, \&smsg_range_i, @$r, $field); } } @@ -756,9 +755,9 @@ sub do_hdr ($$$;$) { hdr_xref($self, $xhdr, $range); } elsif ($sub =~ /\A(?:subject|references|date|from|to|cc| bytes|lines)\z/x) { - hdr_searchmsg($self, $xhdr, $sub, $range); + hdr_smsg($self, $xhdr, $sub, $range); } elsif ($sub =~ /\A:(bytes|lines)\z/) { - hdr_searchmsg($self, $xhdr, $1, $range); + hdr_smsg($self, $xhdr, $1, $range); } else { $xhdr ? (r221 . "\r\n.") : "503 HDR not permitted on $header"; } @@ -803,6 +802,13 @@ sub hdr_mid_response ($$$$$$) { undef; } +sub xrover_i { + my ($self, $beg, $end) = @_; + my $h = over_header_for($self->{ng}->over, $$beg, 'references'); + more($self, "$$beg $h") if defined($h); + $$beg++ < $end; +} + sub cmd_xrover ($;$) { my ($self, $range) = @_; my $ng = $self->{ng} or return '412 no newsgroup selected'; @@ -812,16 +818,8 @@ sub cmd_xrover ($;$) { $range = $self->{article} unless defined $range; my $r = get_range($self, $range); return $r unless ref $r; - my ($beg, $end) = @$r; - my $mm = $ng->mm; - my $over = $ng->over; more($self, '224 Overview information follows'); - - long_response($self, sub { - my $h = over_header_for($over, $$beg, 'references'); - more($self, "$$beg $h") if defined($h); - $$beg++ < $end; - }); + long_response($self, \&xrover_i, @$r); } sub over_line ($$$$) { @@ -831,7 +829,7 @@ sub over_line ($$$$) { my $s = join("\t", $num, $smsg->{subject}, $smsg->{from}, - PublicInbox::SearchMsg::date($smsg), + PublicInbox::Smsg::date($smsg), "<$smsg->{mid}>", $smsg->{references}, $smsg->{bytes}, @@ -843,7 +841,7 @@ sub over_line ($$$$) { sub cmd_over ($;$) { my ($self, $range) = @_; - if ($range && $range =~ /\A<(.+)>\z/) { + if ($range && $range =~ $ONE_MSGID) { my ($ng, $n) = mid_lookup($self, $1); defined $n or return r430; my $smsg = $ng->over->get_art($n) or return r430; @@ -859,6 +857,19 @@ sub cmd_over ($;$) { } } +sub xover_i { + my ($self, $beg, $end) = @_; + my $ng = $self->{ng}; + my $msgs = $ng->over->query_xover($$beg, $end); + my $nr = scalar @$msgs or return; + + # OVERVIEW.FMT + more($self, join("\r\n", map { + over_line($self, $ng, $_->{num}, $_); + } @$msgs)); + $$beg = $msgs->[-1]->{num} + 1; +} + sub cmd_xover ($;$) { my ($self, $range) = @_; $range = $self->{article} unless defined $range; @@ -866,18 +877,7 @@ sub cmd_xover ($;$) { return $r unless ref $r; my ($beg, $end) = @$r; more($self, "224 Overview information follows for $$beg to $end"); - my $over = $self->{ng}->over; - my $cur = $$beg; - long_response($self, sub { - my $msgs = $over->query_xover($cur, $end); - my $nr = scalar @$msgs or return; - - # OVERVIEW.FMT - more($self, join("\r\n", map { - over_line($self, $self->{ng}, $_->{num}, $_); - } @$msgs)); - $cur = $msgs->[-1]->{num} + 1; - }); + long_response($self, \&xover_i, @$r); } sub compressed { undef } @@ -899,7 +899,7 @@ sub cmd_starttls ($) { sub cmd_compress ($$) { my ($self, $alg) = @_; return '503 Only DEFLATE is supported' if uc($alg) ne 'DEFLATE'; - return r502 if $self->compressed || !$have_deflate; + return r502 if $self->compressed; PublicInbox::NNTPdeflate->enable($self); $self->requeue; undef @@ -909,7 +909,7 @@ sub zflush {} # overridden by NNTPdeflate sub cmd_xpath ($$) { my ($self, $mid) = @_; - return r501 unless $mid =~ /\A<(.+)>\z/; + return r501 unless $mid =~ $ONE_MSGID; $mid = $1; my @paths; foreach my $ng (values %{$self->{nntpd}->{groups}}) { @@ -986,10 +986,4 @@ sub busy { ($self->{rbuf} || $self->{wbuf} || $self->not_idle_long($now)); } -# this is an import to prevent "perl -c" from complaining about fields -sub import { - $have_deflate = eval { require PublicInbox::NNTPdeflate } and - $CAPABILITIES .= "COMPRESS DEFLATE\r\n"; -} - 1;