v1: remove articles from overview DB

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 4256263124b74fdbb21f22311e00a569ec3763b9..fd76627791f681cb20ff545d0496ea10ccd35284 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -12,7 +12,7 @@ use warnings;
 use base qw(PublicInbox::Search PublicInbox::Lock);
 use PublicInbox::MIME;
 use PublicInbox::InboxWritable;
-use PublicInbox::MID qw/mid_clean id_compress mid_mime mids references/;
+use PublicInbox::MID qw/mid_clean id_compress mid_mime mids/;
 use PublicInbox::MsgIter;
 use Carp qw(croak);
 use POSIX qw(strftime);
@@ -273,23 +273,12 @@ sub add_message {
                my $smsg = PublicInbox::SearchMsg->new($mime);
                my $doc = $smsg->{doc};
                my $subj = $smsg->subject;
-               my $xpath;
-               if ($subj ne '') {
-                       $xpath = $self->subject_path($subj);
-                       $xpath = id_compress($xpath);
-               }
-
-               $smsg->{lines} = $mime->body_raw =~ tr!\n!\n!;
-               defined $bytes or $bytes = length($mime->as_string);
-               $smsg->{bytes} = $bytes;
-
                add_val($doc, PublicInbox::Search::TS(), $smsg->ts);
                my @ds = gmtime($smsg->ds);
                my $yyyymmdd = strftime('%Y%m%d', @ds);
                add_val($doc, PublicInbox::Search::YYYYMMDD(), $yyyymmdd);
                my $dt = strftime('%Y%m%d%H%M%S', @ds);
                add_val($doc, PublicInbox::Search::DT(), $dt);
-               my @vals = ($smsg->{ts}, $smsg->{ds});
 
                my $tg = $self->term_generator;
 
@@ -338,12 +327,11 @@ sub add_message {
                        index_body($tg, \@orig, $doc) if @orig;
                });
 
-               # populates smsg->references for smsg->to_doc_data
-               my $refs = parse_references($smsg, $mid0, $mids);
-               my $data = $smsg->to_doc_data($oid, $mid0);
                foreach my $mid (@$mids) {
                        $tg->index_text($mid, 1, 'XM');
                }
+               $smsg->{to} = $smsg->{cc} = '';
+               my $data = $smsg->to_doc_data($oid, $mid0);
                $doc->set_data($data);
                if (my $altid = $self->{-altid}) {
                        foreach my $alt (@$altid) {
@@ -356,15 +344,11 @@ sub add_message {
                        }
                }
 
-               $self->delete_article($num) if defined $num; # for reindexing
-
-               utf8::encode($data);
-               $data = compress($data);
-               push @vals, $num, $mids, $refs, $xpath, $data;
-               $self->{over}->add_over(\@vals);
+               if (my $over = $self->{over}) {
+                       $over->add_overview($mime, $bytes, $num, $oid, $mid0);
+               }
                $doc->add_boolean_term('Q' . $_) foreach @$mids;
-               $doc->add_boolean_term('XNUM' . $num) if defined $num;
-               $doc_id = $self->{xdb}->add_document($doc);
+               $self->{xdb}->replace_document($doc_id = $num, $doc);
        };
 
        if ($@) {
@@ -401,11 +385,13 @@ sub remove_message {
        my $db = $self->{xdb};
        my $called;
        $mid = mid_clean($mid);
+       my $over = $self->{over};
 
        eval {
                batch_do($self, 'Q' . $mid, sub {
                        my ($ids) = @_;
                        $db->delete_document($_) for @$ids;
+                       $over->delete_articles($ids) if $over;
                        $called = 1;
                });
        };
@@ -416,21 +402,13 @@ sub remove_message {
        }
 }
 
-sub delete_article {
-       my ($self, $num) = @_;
-       my $ndel = 0;
-       batch_do($self, 'XNUM' . $num, sub {
-               my ($ids) = @_;
-               $ndel += scalar @$ids;
-               $self->{xdb}->delete_document($_) for @$ids;
-       });
-}
-
 # MID is a hint in V2
 sub remove_by_oid {
        my ($self, $oid, $mid) = @_;
        my $db = $self->{xdb};
 
+       $self->{over}->remove_oid($oid, $mid) if $self->{over};
+
        # XXX careful, we cannot use batch_do here since we conditionally
        # delete documents based on other factors, so we cannot call
        # find_doc_ids twice.
@@ -440,7 +418,6 @@ sub remove_by_oid {
        # there is only ONE element in @delete unless we
        # have bugs in our v2writable deduplication check
        my @delete;
-       my @over_del;
        for (; $head != $tail; $head->inc) {
                my $docid = $head->get_docid;
                my $doc = $db->get_document($docid);
@@ -448,11 +425,9 @@ sub remove_by_oid {
                $smsg->load_expand;
                if ($smsg->{blob} eq $oid) {
                        push(@delete, $docid);
-                       push(@over_del, $smsg->num);
                }
        }
        $db->delete_document($_) foreach @delete;
-       $self->{over}->remove_oid($oid, $mid);
        scalar(@delete);
 }
 
@@ -468,29 +443,6 @@ sub term_generator { # write-only
        $self->{term_generator} = $tg;
 }
 
-sub parse_references ($$$) {
-       my ($smsg, $mid0, $mids) = @_;
-       my $mime = $smsg->{mime};
-       my $hdr = $mime->header_obj;
-       my $refs = references($hdr);
-       push(@$refs, @$mids) if scalar(@$mids) > 1;
-       return $refs if scalar(@$refs) == 0;
-
-       # prevent circular references here:
-       my %seen = ( $mid0 => 1 );
-       my @keep;
-       foreach my $ref (@$refs) {
-               if (length($ref) > PublicInbox::MID::MAX_MID_SIZE) {
-                       warn "References: <$ref> too long, ignoring\n";
-                       next;
-               }
-               next if $seen{$ref}++;
-               push @keep, $ref;
-       }
-       $smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
-       \@keep;
-}
-
 sub index_git_blob_id {
        my ($doc, $pfx, $objid) = @_;
 
@@ -618,7 +570,7 @@ sub _git_log {
                                --raw -r --no-abbrev/, $range);
 }
 
-# indexes all unindexed messages
+# indexes all unindexed messages (v1 only)
 sub _index_sync {
        my ($self, $opts) = @_;
        my $tip = $opts->{ref} || 'HEAD';
@@ -749,7 +701,7 @@ sub begin_txn_lazy {
        my ($self) = @_;
        return if $self->{txn};
        my $xdb = $self->{xdb} || $self->_xdb_acquire;
-       $self->{over}->begin_lazy;
+       $self->{over}->begin_lazy if $self->{over};
        $xdb->begin_transaction;
        $self->{txn} = 1;
        $xdb;
@@ -759,7 +711,7 @@ sub commit_txn_lazy {
        my ($self) = @_;
        delete $self->{txn} or return;
        $self->{xdb}->commit_transaction;
-       $self->{over}->commit_lazy;
+       $self->{over}->commit_lazy if $self->{over};
 }
 
 sub worker_done {