From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id AB9D71FFA8 for ; Tue, 27 Oct 2020 07:54:54 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 08/52] searchidx: introduce "xref3" concept Date: Tue, 27 Oct 2020 07:54:09 +0000 Message-Id: <20201027075453.19163-9-e@80x24.org> In-Reply-To: <20201027075453.19163-1-e@80x24.org> References: <20201027075453.19163-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: This will be used to track cross-posted messages in the external/detached index. --- lib/PublicInbox/SearchIdx.pm | 78 ++++++++++++++++++++++++++----- lib/PublicInbox/SearchIdxShard.pm | 53 ++++++++++++++++++--- lib/PublicInbox/Smsg.pm | 13 ++++++ t/search.t | 28 +++++++++-- 4 files changed, 150 insertions(+), 22 deletions(-) diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index af707ced..283bdd6c 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -325,6 +325,16 @@ sub index_xapian { # msg_iter callback } } +sub index_list_id ($$$) { + my ($self, $doc, $hdr) = @_; + for my $l ($hdr->header_raw('List-Id')) { + $l =~ /<([^>]+)>/ or next; + my $lid = lc $1; + $doc->add_boolean_term('G' . $lid); + index_text($self, $lid, 1, 'XL'); # probabilistic + } +} + sub index_ids ($$$$) { my ($self, $doc, $hdr, $mids) = @_; for my $mid (@$mids) { @@ -338,12 +348,7 @@ sub index_ids ($$$$) { } } $doc->add_boolean_term('Q' . $_) for @$mids; - for my $l ($hdr->header_raw('List-Id')) { - $l =~ /<([^>]+)>/ or next; - my $lid = lc $1; - $doc->add_boolean_term('G' . $lid); - index_text($self, $lid, 1, 'XL'); # probabilistic - } + index_list_id($self, $doc, $hdr); } sub add_xapian ($$$$) { @@ -363,6 +368,10 @@ sub add_xapian ($$$$) { $tg->set_document($doc); index_headers($self, $smsg); + if (my $ng_or_dir = $self->{ng_or_dir}) { # external index + $doc->add_boolean_term('P'. + "$ng_or_dir:$smsg->{num}:$smsg->{blob}"); + } msg_iter($eml, \&index_xapian, [ $self, $doc ]); index_ids($self, $doc, $eml, $mids); @@ -436,6 +445,56 @@ sub add_message { $smsg->{num}; } +sub _get_doc ($$$) { + my ($self, $docid, $oid) = @_; + my $doc = eval { $self->{xdb}->get_document($docid) }; + $doc // do { + warn "E: $@\n" if $@; + warn "E: #$docid $oid missing in Xapian\n"; + undef; + } +} + +sub add_xref3 { + my ($self, $docid, $xnum, $oid, $ng_or_dir, $eml) = @_; + begin_txn_lazy($self); + my $doc = _get_doc($self, $docid, $oid) or return; + term_generator($self)->set_document($doc); + $doc->add_boolean_term('P'."$ng_or_dir:$xnum:$oid"); + index_list_id($self, $doc, $eml); + $self->{xdb}->replace_document($docid, $doc); +} + +sub remove_xref3 { + my ($self, $docid, $oid, $ng_or_dir, $eml) = @_; + begin_txn_lazy($self); + my $doc = _get_doc($self, $docid, $oid) or return; + my $xref3 = PublicInbox::Smsg::xref3(undef, $doc); + for (grep(/\A\Q$ng_or_dir\E:[0-9]+:\Q$oid\E\z/, @$xref3)) { + $doc->remove_term('P' . $_); + } + for my $l ($eml->header_raw('List-Id')) { + $l =~ /<([^>]+)>/ or next; + my $lid = lc $1; + $doc->remove_term('G' . $lid); + + # nb: we don't remove the XL probabilistic terms + # since terms may overlap if cross-posted. + # + # IOW, a message which has both + # and would have overlapping + # "XLexample" and "XLcom" as terms and which we + # wouldn't know if they're safe to remove if we just + # unindex while preserving + # . + # + # In any case, this entire sub is will likely never + # be needed and users using the "l:" prefix are probably + # rarer. + } + $self->{xdb}->replace_document($docid, $doc); +} + sub get_val ($$) { my ($doc, $col) = @_; sortable_unserialise($doc->get_value($col)); @@ -457,12 +516,7 @@ sub xdb_remove { my ($self, $oid, @removed) = @_; my $xdb = $self->{xdb} or return; for my $num (@removed) { - my $doc = eval { $xdb->get_document($num) }; - unless ($doc) { - warn "E: $@\n" if $@; - warn "E: #$num $oid missing in Xapian\n"; - next; - } + my $doc = _get_doc($self, $num, $oid) or next; my $smsg = smsg_from_doc($doc); my $blob = $smsg->{blob}; # may be undef if --skip-docdata if (!defined($blob) || $blob eq $oid) { diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm index f23d23d0..8e24aa1b 100644 --- a/lib/PublicInbox/SearchIdxShard.pm +++ b/lib/PublicInbox/SearchIdxShard.pm @@ -7,6 +7,7 @@ package PublicInbox::SearchIdxShard; use strict; use v5.10.1; use parent qw(PublicInbox::SearchIdx); +use bytes qw(length); use IO::Handle (); # autoflush use PublicInbox::Eml; @@ -47,6 +48,13 @@ sub spawn_worker { close $r or die "failed to close: $!"; } +sub eml ($$) { + my ($r, $len) = @_; + my $n = read($r, my $bref, $len) or die "read: $!\n"; + $n == $len or die "short read: $n != $len\n"; + PublicInbox::Eml->new(\$bref); +} + # this reads all the writes to $self->{w} from the parent process sub shard_worker_loop ($$$$$) { my ($self, $v2w, $r, $shard, $bnote) = @_; @@ -65,25 +73,32 @@ sub shard_worker_loop ($$$$$) { die "write failed for barrier $!\n"; } elsif ($line =~ /\AD ([a-f0-9]{40,}) ([0-9]+)\n\z/s) { $self->remove_by_oid($1, $2 + 0); + } elsif ($line =~ s/\A\+X //) { + my ($len, $docid, $xnum, $oid, $ng_or_dir) = + split(/ /, $line, 5); + $self->add_xref3($docid, $xnum, $oid, $ng_or_dir, + eml($r, $len)); + } elsif ($line =~ s/\A-X //) { + my ($len, $docid, $xnum, $oid, $ng_or_dir) = + split(/ /, $line, 5); + $self->remove_xref3($docid, $xnum, $oid, + $ng_or_dir, eml($r, $len)); } else { chomp $line; # n.b. $mid may contain spaces(!) - my ($to_read, $bytes, $num, $blob, $ds, $ts, $tid, $mid) + my ($len, $bytes, $num, $oid, $ds, $ts, $tid, $mid) = split(/ /, $line, 8); $self->begin_txn_lazy; - my $n = read($r, my $msg, $to_read) or die "read: $!\n"; - $n == $to_read or die "short read: $n != $to_read\n"; - my $mime = PublicInbox::Eml->new(\$msg); my $smsg = bless { bytes => $bytes, num => $num + 0, - blob => $blob, + blob => $oid, mid => $mid, tid => $tid, ds => $ds, ts => $ts, }, 'PublicInbox::Smsg'; - $self->add_message($mime, $smsg); + $self->add_message(eml($r, $len), $smsg); } } $self->worker_done; @@ -107,6 +122,32 @@ sub index_raw { } } +sub shard_add_xref3 { + my ($self, $docid, $xnum, $oid, $xibx, $eml) = @_; + my $ng_or_dir = $xibx->{newsgroup} // $xibx->{inboxdir}; + if (my $w = $self->{w}) { + my $hdr = $eml->header_obj->as_string; + my $len = length($hdr); + print $w "+X $len $docid $xnum $oid $ng_or_dir\n", $hdr or + die "failed to write shard: $!"; + } else { + $self->add_xref3($docid, $xnum, $oid, $ng_or_dir, $eml); + } +} + +sub shard_remove_xref3 { + my ($self, $docid, $oid, $xibx, $eml) = @_; + my $ng_or_dir = $xibx->{newsgroup} // $xibx->{inboxdir}; + if (my $w = $self->{w}) { + my $hdr = $eml->header_obj->as_string; + my $len = length($hdr); + print $w "-X $len $docid $oid $ng_or_dir\n", $hdr or + die "failed to write shard: $!"; + } else { + $self->remove_xref3($docid, $oid, $ng_or_dir, $eml); + } +} + sub atfork_child { close $_[0]->{w} or die "failed to close write pipe: $!\n"; } diff --git a/lib/PublicInbox/Smsg.pm b/lib/PublicInbox/Smsg.pm index 14086538..c0fd85fd 100644 --- a/lib/PublicInbox/Smsg.pm +++ b/lib/PublicInbox/Smsg.pm @@ -137,4 +137,17 @@ sub subject_normalized ($) { $subj; } +sub xref3 { + my ($self, $doc) = @_; + my $end = $doc->termlist_end; + my $it = $doc->termlist_begin; + $it->skip_to('P'); + my @ret; + for (; $it != $end; $it++) { + my $val = $it->get_termname; + $val =~ s/\AP// and push @ret, $val; + } + \@ret; +} + 1; diff --git a/t/search.t b/t/search.t index a66aec36..e789b81e 100644 --- a/t/search.t +++ b/t/search.t @@ -341,6 +341,14 @@ $ibx->with_umask(sub { my $uid = PublicInbox::SearchIdx::get_val($doc, $col); is($uid, $smsg->{num}, 'UID column matches {num}'); is($uid, $m->get_docid, 'UID column matches docid'); + + # check ->xref3 for external index: + is_deeply($smsg->xref3($doc), [], 'xref3 empty by default'); + my $exp = "inbox.com.example:$uid:deadbeef"; + $doc->add_boolean_term('P'.$exp); + is_deeply($smsg->xref3($doc), [ $exp ], 'xref3 can be set'); + $doc->remove_term('P'.$exp); + is_deeply($smsg->xref3($doc), [], 'xref3 can be unset'); } $mset = $ibx->search->mset('tc:list@example.com'); @@ -513,8 +521,13 @@ $ibx->with_umask(sub { $rw_commit->(); my $doc_id = $rw->add_message(eml_load('t/data/message_embed.eml')); ok($doc_id > 0, 'messages within messages'); - $rw->commit_txn_lazy; - $ibx->search->reopen; + + my $eml = PublicInbox::Eml->new(< + +EOF + $rw->add_xref3($doc_id, 1, 'deadbeef', 'newsgroup1.example', $eml); + $rw_commit->(); my $n_test_eml = $query->('n:test.eml'); is(scalar(@$n_test_eml), 1, 'got a result'); my $n_embed2x_eml = $query->('n:embed2x.eml'); @@ -532,8 +545,15 @@ $ibx->with_umask(sub { is($query->('s:"mail header experiments"')->[0]->{mid}, '20200418222508.GA13918@dcvr', 'Subject search reaches inside message/rfc822'); + is($query->('l:blahblah.example.com')->[0]->{num}, $doc_id, + 'xref3 List-Id probabilistic works'); + is($query->('lid:blahblah.example.com')->[0]->{num}, $doc_id, + 'xref3 List-Id boolean term works'); + $rw->remove_xref3($doc_id, 'deadbeef', 'newsgroup1.example', $eml); + $rw->commit_txn_lazy; + $ibx->search->reopen; + my $res = $query->('lid:blahblah.example.com'); + is_deeply($res, [], '->remove_xref3 dropped boolean term'); }); done_testing(); - -1;