X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiSearch.pm;h=cd28a700647bf62a37655108d9fb1467f776fbcc;hb=b6b86cfd238c170ea3e2c4d4179f06c7af139086;hp=b7e337de38d7b870d1045ba417de28fedb1f010a;hpb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;p=public-inbox.git diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm index b7e337de..cd28a700 100644 --- a/lib/PublicInbox/LeiSearch.pm +++ b/lib/PublicInbox/LeiSearch.pm @@ -1,11 +1,14 @@ # Copyright (C) 2020-2021 all contributors # License: AGPL-3.0+ +# read-only counterpart for PublicInbox::LeiStore package PublicInbox::LeiSearch; use strict; use v5.10.1; use parent qw(PublicInbox::ExtSearch); -use PublicInbox::Search; +use PublicInbox::Search qw(xap_terms); +use PublicInbox::ContentHash qw(content_digest content_hash); +use PublicInbox::MID qw(mids mids_for_index); # get combined docid from over.num: # (not generic Xapian, only works with our sharding scheme) @@ -19,19 +22,126 @@ sub msg_keywords { my ($self, $num) = @_; # num_or_mitem my $xdb = $self->xdb; # set {nshard}; my $docid = ref($num) ? $num->get_docid : num2docid($self, $num); - my %kw; - eval { - my $end = $xdb->termlist_end($docid); - my $cur = $xdb->termlist_begin($docid); - for (; $cur != $end; $cur++) { - $cur->skip_to('K'); - last if $cur == $end; - my $kw = $cur->get_termname; - $kw =~ s/\AK//s and $kw{$kw} = undef; - } - }; + my $kw = xap_terms('K', $xdb, $docid); warn "E: #$docid ($num): $@\n" if $@; - wantarray ? sort(keys(%kw)) : \%kw; + wantarray ? sort(keys(%$kw)) : $kw; +} + +# lookup keywords+labels for external messages +sub xsmsg_vmd { + my ($self, $smsg, $want_label) = @_; + return if $smsg->{kw}; + my $xdb = $self->xdb; # set {nshard}; + my (%kw, %L, $doc, $x); + $kw{flagged} = 1 if delete($smsg->{lei_q_tt_flagged}); + my @num = $self->over->blob_exists($smsg->{blob}); + for my $num (@num) { # there should only be one... + $doc = $xdb->get_document(num2docid($self, $num)); + $x = xap_terms('K', $doc); + %kw = (%kw, %$x); + if ($want_label) { # JSON/JMAP only + $x = xap_terms('L', $doc); + %L = (%L, %$x); + } + } + $smsg->{kw} = [ sort keys %kw ] if scalar(keys(%kw)); + $smsg->{L} = [ sort keys %L ] if scalar(keys(%L)); +} + +# when a message has no Message-IDs at all, this is needed for +# unsent Draft messages, at least +sub content_key ($) { + my ($eml) = @_; + my $dig = content_digest($eml); + my $chash = $dig->clone->digest; + my $mids = mids_for_index($eml); + unless (@$mids) { + $eml->{-lei_fake_mid} = $mids->[0] = + PublicInbox::Import::digest2mid($dig, $eml, 0); + } + ($chash, $mids); +} + +sub _cmp_1st { # git->cat_async callback + my ($bref, $oid, $type, $size, $cmp) = @_; # cmp: [chash, xoids, smsg] + if ($bref && content_hash(PublicInbox::Eml->new($bref)) eq $cmp->[0]) { + $cmp->[1]->{$oid} = $cmp->[2]->{num}; + } +} + +# returns { OID => num } mapping for $eml matches +# The `num' hash value only makes sense from LeiSearch itself +# and is nonsense from the PublicInbox::LeiALE subclass +sub xoids_for { + my ($self, $eml, $min) = @_; + my ($chash, $mids) = content_key($eml); + my @overs = ($self->over // $self->overs_all); + my $git = $self->git; + my $xoids = {}; + for my $mid (@$mids) { + for my $o (@overs) { + my ($id, $prev); + while (my $cur = $o->next_by_mid($mid, \$id, \$prev)) { + next if $cur->{bytes} == 0 || + $xoids->{$cur->{blob}}; + $git->cat_async($cur->{blob}, \&_cmp_1st, + [ $chash, $xoids, $cur ]); + if ($min && scalar(keys %$xoids) >= $min) { + $git->cat_async_wait; + return $xoids; + } + } + } + } + $git->cat_async_wait; + scalar(keys %$xoids) ? $xoids : undef; +} + +# returns true if $eml is indexed by lei/store and keywords don't match +sub kw_changed { + my ($self, $eml, $new_kw_sorted, $docids) = @_; + my $xoids = xoids_for($self, $eml) // return; + $docids //= []; + @$docids = sort { $a <=> $b } values %$xoids; + my $cur_kw = msg_keywords($self, $docids->[0]); + + # RFC 5550 sec 5.9 on the $Forwarded keyword states: + # "Once set, the flag SHOULD NOT be cleared" + if (exists($cur_kw->{forwarded}) && + !grep(/\Aforwarded\z/, @$new_kw_sorted)) { + delete $cur_kw->{forwarded}; + } + $cur_kw = join("\0", sort keys %$cur_kw); + join("\0", @$new_kw_sorted) eq $cur_kw ? 0 : 1; +} + +sub all_terms { + my ($self, $pfx) = @_; + my $xdb = $self->xdb; + my $cur = $xdb->allterms_begin($pfx); + my $end = $xdb->allterms_end($pfx); + my %ret; + for (; $cur != $end; $cur++) { + my $tn = $cur->get_termname; + index($tn, $pfx) == 0 and + $ret{substr($tn, length($pfx))} = undef; + } + wantarray ? (sort keys %ret) : \%ret; +} + +sub qparse_new { + my ($self) = @_; + my $qp = $self->SUPER::qparse_new; # PublicInbox::Search + $qp->add_boolean_prefix('kw', 'K'); + $qp->add_boolean_prefix('L', 'L'); + $qp +} + +sub lms { + my ($self) = @_; + require PublicInbox::LeiMailSync; + my $f = "$self->{topdir}/mail_sync.sqlite3"; + -f $f ? PublicInbox::LeiMailSync->new($f) : undef; } 1;