update copyrights for 2021

[public-inbox.git] / lib / PublicInbox / SearchIdx.pm

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index b731f6982f8bd1e6d44179d26a94f32c67726ae7..88349faa38b7a9325a11900155d4715c9faa90de 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -1,6 +1,6 @@
-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-# based on notmuch, but with no concept of folders, files or flags
+# based on notmuch, but with no concept of folders, files
 #
 # Indexes mail with Xapian and our (SQLite-based) ::Msgmap for use
 # with the web and NNTP interfaces.  This index maintains thread
@@ -54,20 +54,16 @@ sub new {
                }
        }
        $ibx = PublicInbox::InboxWritable->new($ibx);
-       my $self = bless {
-               ibx => $ibx,
-               xpfx => $inboxdir, # for xpfx_init
-               -altid => $altid,
-               ibx_ver => $version,
-               indexlevel => $indexlevel,
-       }, $class;
-       $self->xpfx_init;
+       my $self = PublicInbox::Search->new($ibx);
+       bless $self, $class;
+       $self->{ibx} = $ibx;
+       $self->{-altid} = $altid;
+       $self->{indexlevel} = $indexlevel;
        $self->{-set_indexlevel_once} = 1 if $indexlevel eq 'medium';
        if ($ibx->{-skip_docdata}) {
                $self->{-set_skip_docdata_once} = 1;
                $self->{-skip_docdata} = 1;
        }
-       $ibx->umask_prepare;
        if ($version == 1) {
                $self->{lock_path} = "$inboxdir/ssoma.lock";
                my $dir = $self->xdir;
@@ -106,7 +102,6 @@ sub load_xapian_writable () {
        }
        eval 'require '.$X->{WritableDatabase} or die;
        *sortable_serialise = $xap.'::sortable_serialise';
-       *sortable_unserialise = $xap.'::sortable_unserialise';
        $DB_CREATE_OR_OPEN = eval($xap.'::DB_CREATE_OR_OPEN()');
        $DB_OPEN = eval($xap.'::DB_OPEN()');
        my $ver = (eval($xap.'::major_version()') << 16) |
@@ -371,7 +366,7 @@ sub eml2doc ($$$;$) {
        index_headers($self, $smsg);
 
        if (defined(my $eidx_key = $smsg->{eidx_key})) {
-               $doc->add_boolean_term('O'.$eidx_key);
+               $doc->add_boolean_term('O'.$eidx_key) if $eidx_key ne '.';
        }
        msg_iter($eml, \&index_xapian, [ $self, $doc ]);
        index_ids($self, $doc, $eml, $mids);
@@ -408,7 +403,7 @@ sub add_xapian ($$$$) {
 
 sub _msgmap_init ($) {
        my ($self) = @_;
-       die "BUG: _msgmap_init is only for v1\n" if $self->{ibx_ver} != 1;
+       die "BUG: _msgmap_init is only for v1\n" if $self->{ibx}->version != 1;
        $self->{mm} //= eval {
                require PublicInbox::Msgmap;
                my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1;
@@ -467,7 +462,7 @@ sub add_eidx_info {
        begin_txn_lazy($self);
        my $doc = _get_doc($self, $docid) or return;
        term_generator($self)->set_document($doc);
-       $doc->add_boolean_term('O'.$eidx_key);
+       $doc->add_boolean_term('O'.$eidx_key) if $eidx_key ne '.';
        index_list_id($self, $doc, $eml);
        $self->{xdb}->replace_document($docid, $doc);
 }
@@ -501,17 +496,53 @@ sub remove_eidx_info {
        $self->{xdb}->replace_document($docid, $doc);
 }
 
-sub get_val ($$) {
-       my ($doc, $col) = @_;
-       sortable_unserialise($doc->get_value($col));
+sub set_keywords {
+       my ($self, $docid, @kw) = @_;
+       begin_txn_lazy($self);
+       my $doc = _get_doc($self, $docid) or return;
+       my %keep = map { $_ => 1 } @kw;
+       my %add = %keep;
+       my @rm;
+       my $end = $doc->termlist_end;
+       for (my $cur = $doc->termlist_begin; $cur != $end; $cur++) {
+               $cur->skip_to('K');
+               last if $cur == $end;
+               my $kw = $cur->get_termname;
+               $kw =~ s/\AK//s or next;
+               $keep{$kw} ? delete($add{$kw}) : push(@rm, $kw);
+       }
+       return unless (scalar(@rm) + scalar(keys %add));
+       $doc->remove_term('K'.$_) for @rm;
+       $doc->add_boolean_term('K'.$_) for (keys %add);
+       $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub add_keywords {
+       my ($self, $docid, @kw) = @_;
+       begin_txn_lazy($self);
+       my $doc = _get_doc($self, $docid) or return;
+       $doc->add_boolean_term('K'.$_) for @kw;
+       $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub remove_keywords {
+       my ($self, $docid, @kw) = @_;
+       begin_txn_lazy($self);
+       my $doc = _get_doc($self, $docid) or return;
+       my $replace;
+       eval {
+               $doc->remove_term('K'.$_);
+               $replace = 1
+       } for @kw;
+       $self->{xdb}->replace_document($docid, $doc) if $replace;
 }
 
 sub smsg_from_doc ($) {
        my ($doc) = @_;
        my $data = $doc->get_data or return;
        my $smsg = bless {}, 'PublicInbox::Smsg';
-       $smsg->{ts} = get_val($doc, PublicInbox::Search::TS());
-       my $dt = get_val($doc, PublicInbox::Search::DT());
+       $smsg->{ts} = int_val($doc, PublicInbox::Search::TS());
+       my $dt = int_val($doc, PublicInbox::Search::DT());
        my ($yyyy, $mon, $dd, $hh, $mm, $ss) = unpack('A4A2A2A2A2A2', $dt);
        $smsg->{ds} = timegm($ss, $mm, $hh, $dd, $mon - 1, $yyyy);
        $smsg->load_from_data($data);
@@ -622,6 +653,7 @@ sub index_both { # git->cat_async callback
        $smsg->{num} = index_mm($self, $eml, $oid, $sync) or
                die "E: could not generate NNTP article number for $oid";
        add_message($self, $eml, $smsg, $sync);
+       ++$self->{nidx};
        my $cur_cmt = $sync->{cur_cmt} // die 'BUG: {cur_cmt} missing';
        ${$sync->{latest_cmt}} = $cur_cmt;
 }
@@ -636,6 +668,7 @@ sub unindex_both { # git->cat_async callback
        if (defined(my $cur_cmt = $sync->{cur_cmt})) {
                ${$sync->{latest_cmt}} = $cur_cmt;
        }
+       ++$self->{nidx};
 }
 
 sub with_umask {