X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiSearch.pm;h=936c275178dfc6908577487ce97d3a83c58c5449;hp=69ba8303189fda562b9f6a83eb8df1adf1f24ab1;hb=961690bae47c90a4a6960952587c6f4463fb4b19;hpb=1730d031a00654a64d1854480d0e83b62c2bfecd diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm index 69ba8303..936c2751 100644 --- a/lib/PublicInbox/LeiSearch.pm +++ b/lib/PublicInbox/LeiSearch.pm @@ -1,42 +1,54 @@ -# Copyright (C) 2020-2021 all contributors +# Copyright (C) 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 parent qw(PublicInbox::ExtSearch); # PublicInbox::Search->reopen use PublicInbox::Search qw(xap_terms); -use PublicInbox::ContentHash qw(content_digest content_hash); -use PublicInbox::MID qw(mids mids_in); +use PublicInbox::ContentHash qw(content_digest content_hash git_sha); +use PublicInbox::MID qw(mids mids_for_index); +use Carp qw(croak); -# get combined docid from over.num: -# (not generic Xapian, only works with our sharding scheme) -sub num2docid ($$) { +sub _msg_kw { # retry_reopen callback my ($self, $num) = @_; - my $nshard = $self->{nshard}; - ($num - 1) * $nshard + $num % $nshard + 1; + my $xdb = $self->xdb; # set {nshard} for num2docid; + xap_terms('K', $xdb, $self->num2docid($num)); } -sub msg_keywords { - my ($self, $num) = @_; # num_or_mitem +sub msg_keywords { # array or hashref + my ($self, $num) = @_; + $self->retry_reopen(\&_msg_kw, $num); +} + +sub _oid_kw { # retry_reopen callback + my ($self, $nums) = @_; my $xdb = $self->xdb; # set {nshard}; - my $docid = ref($num) ? $num->get_docid : num2docid($self, $num); - my $kw = xap_terms('K', $xdb, $docid); - warn "E: #$docid ($num): $@\n" if $@; - wantarray ? sort(keys(%$kw)) : $kw; + my %kw; + for my $num (@$nums) { # there should only be one... + my $doc = $xdb->get_document($self->num2docid($num)); + my $x = xap_terms('K', $doc); + %kw = (%kw, %$x); + } + \%kw; } -# lookup keywords+labels for external messages -sub xsmsg_vmd { +# returns undef if blob is unknown +sub oidbin_keywords { + my ($self, $oidbin) = @_; + my @num = $self->over->oidbin_exists($oidbin) or return; + $self->retry_reopen(\&_oid_kw, \@num); +} + +sub _xsmsg_vmd { # retry_reopen my ($self, $smsg, $want_label) = @_; - return if $smsg->{kw}; my $xdb = $self->xdb; # set {nshard}; my (%kw, %L, $doc, $x); $kw{flagged} = 1 if delete($smsg->{lei_q_tt_flagged}); my @num = $self->over->blob_exists($smsg->{blob}); for my $num (@num) { # there should only be one... - $doc = $xdb->get_document(num2docid($self, $num)); + $doc = $xdb->get_document($self->num2docid($num)); $x = xap_terms('K', $doc); %kw = (%kw, %$x); if ($want_label) { # JSON/JMAP only @@ -48,23 +60,32 @@ sub xsmsg_vmd { $smsg->{L} = [ sort keys %L ] if scalar(keys(%L)); } +# lookup keywords+labels for external messages +sub xsmsg_vmd { + my ($self, $smsg, $want_label) = @_; + return if $smsg->{kw}; # already set by LeiXSearch->mitem_kw + eval { $self->retry_reopen(\&_xsmsg_vmd, $smsg, $want_label) }; + warn "$$ $0 (nshard=$self->{nshard}) $smsg->{blob}: $@" if $@; +} + # when a message has no Message-IDs at all, this is needed for # unsent Draft messages, at least sub content_key ($) { my ($eml) = @_; my $dig = content_digest($eml); my $chash = $dig->clone->digest; - my $mids = mids_in($eml, - qw(Message-ID X-Alt-Message-ID Resent-Message-ID)); + my $mids = mids_for_index($eml); unless (@$mids) { $eml->{-lei_fake_mid} = $mids->[0] = - PublicInbox::Import::digest2mid($dig, $eml); + PublicInbox::Import::digest2mid($dig, $eml, 0); } ($chash, $mids); } sub _cmp_1st { # git->cat_async callback - my ($bref, $oid, $type, $size, $cmp) = @_; # cmp: [chash, xoids, smsg] + my ($bref, $oid, $type, $size, $cmp) = @_; + # cmp: [chash, xoids, smsg, lms] + $bref //= $cmp->[3] ? $cmp->[3]->local_blob($oid, 1) : undef; if ($bref && content_hash(PublicInbox::Eml->new($bref)) eq $cmp->[0]) { $cmp->[1]->{$oid} = $cmp->[2]->{num}; } @@ -79,6 +100,8 @@ sub xoids_for { my @overs = ($self->over // $self->overs_all); my $git = $self->git; my $xoids = {}; + # no lms when used via {ale}: + my $lms = $self->{-lms_rw} //= lms($self) if defined($self->{topdir}); for my $mid (@$mids) { for my $o (@overs) { my ($id, $prev); @@ -86,26 +109,53 @@ sub xoids_for { next if $cur->{bytes} == 0 || $xoids->{$cur->{blob}}; $git->cat_async($cur->{blob}, \&_cmp_1st, - [ $chash, $xoids, $cur ]); + [$chash, $xoids, $cur, $lms]); if ($min && scalar(keys %$xoids) >= $min) { - $git->cat_async_wait; + $git->async_wait_all; return $xoids; } } } } - $git->cat_async_wait; + $git->async_wait_all; + + # it could be an 'lei index'-ed file that just got renamed + if (scalar(keys %$xoids) < ($min // 1) && defined($self->{topdir})) { + my $hex = git_sha(1, $eml)->hexdigest; + my @n = $overs[0]->blob_exists($hex); + for (@n) { $xoids->{$hex} //= $_ } + } scalar(keys %$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, $docids->[0]); - join("\0", @$new_kw_sorted) eq join("\0", @cur_kw) ? 0 : 1; + my $cur_kw; + if ($eml) { + my $xoids = xoids_for($self, $eml) // return; + $docids //= []; + @$docids = sort { $a <=> $b } values %$xoids; + if (!@$docids && $self->over) { + my $bin = git_sha(1, $eml)->digest; + @$docids = $self->over->oidbin_exists($bin); + } + } + for my $id (@$docids) { + $cur_kw = eval { msg_keywords($self, $id) } and last; + } + if (!defined($cur_kw) && $@) { + $docids = join(', num:', @$docids); + croak "E: num:$docids keyword lookup failure: $@"; + } + # 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 $cur_kw ? 0 : 1; } sub all_terms { @@ -125,9 +175,28 @@ sub all_terms { sub qparse_new { my ($self) = @_; my $qp = $self->SUPER::qparse_new; # PublicInbox::Search + $self->{qp_flags} |= PublicInbox::Search::FLAG_PHRASE() | + PublicInbox::Search::FLAG_PURE_NOT(); $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; +} + +# allow SolverGit->resolve_patch to work with "lei index" +sub smsg_eml { + my ($self, $smsg) = @_; + PublicInbox::Inbox::smsg_eml($self, $smsg) // do { + my $lms = lms($self); + my $bref = $lms ? $lms->local_blob($smsg->{blob}, 1) : undef; + $bref ? PublicInbox::Eml->new($bref) : undef; + }; +} + 1;