searchidx: index "diff --git a/... b/..." headers

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index e5c872d52fd3fd477f42301f7407acbd8d0061fb..6e2e614c5085c7e45fa33ad06375a9137af1ee31 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -259,6 +259,7 @@ sub index_diff ($$$) {
                } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
                        # wait until "---" and "+++" to capture filenames
                        $in_diff = 1;
+                       push @xnq, $_;
                # traditional diff:
                } elsif (m/^diff -(.+) (\S+) (\S+)$/) {
                        my ($opt, $fa, $fb) = ($1, $2, $3);
@@ -451,10 +452,9 @@ sub add_xapian ($$$$) {
 sub _msgmap_init ($) {
        my ($self) = @_;
        die "BUG: _msgmap_init is only for v1\n" if $self->{ibx}->version != 1;
-       $self->{mm} //= eval {
+       $self->{mm} //= do {
                require PublicInbox::Msgmap;
-               my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1;
-               PublicInbox::Msgmap->new($self->{ibx}->{inboxdir}, $rw);
+               PublicInbox::Msgmap->new_file($self->{ibx}, 1);
        };
 }
 
@@ -518,6 +518,12 @@ sub add_eidx_info {
        $self->{xdb}->replace_document($docid, $doc);
 }
 
+sub get_terms {
+       my ($self, $pfx, $docid) = @_;
+       begin_txn_lazy($self);
+       xap_terms($pfx, $self->{xdb}, $docid);
+}
+
 sub remove_eidx_info {
        my ($self, $docid, $eidx_key, $eml) = @_;
        begin_txn_lazy($self);
@@ -637,14 +643,24 @@ sub update_vmd {
 
 sub xdb_remove {
        my ($self, @docids) = @_;
-       $self->begin_txn_lazy;
-       my $xdb = $self->{xdb} or return;
+       begin_txn_lazy($self);
+       my $xdb = $self->{xdb} // die 'BUG: missing {xdb}';
        for my $docid (@docids) {
                eval { $xdb->delete_document($docid) };
                warn "E: #$docid not in in Xapian? $@\n" if $@;
        }
 }
 
+sub xdb_remove_quiet {
+       my ($self, $docid) = @_;
+       begin_txn_lazy($self);
+       my $xdb = $self->{xdb} // die 'BUG: missing {xdb}';
+       eval { $xdb->delete_document($docid) };
+       ++$self->{-quiet_rm} unless $@;
+}
+
+sub nr_quiet_rm { delete($_[0]->{-quiet_rm}) // 0 }
+
 sub index_git_blob_id {
        my ($doc, $pfx, $objid) = @_;
 
@@ -784,6 +800,7 @@ sub v1_checkpoint ($$;$) {
        ${$sync->{max}} = $self->{batch_bytes};
 
        $self->{mm}->{dbh}->commit;
+       eval { $self->{mm}->{dbh}->do('PRAGMA optimize') };
        my $xdb = $self->{xdb};
        if ($newest && $xdb) {
                my $cur = $xdb->get_metadata('last_commit');
@@ -1098,25 +1115,4 @@ sub eidx_shard_new {
        $self;
 }
 
-# ensure there's no stale Xapian docs by treating $over as canonical
-sub over_check {
-       my ($self, $over) = @_;
-       begin_txn_lazy($self);
-       my $sth = $over->dbh->prepare(<<'');
-SELECT COUNT(*) FROM over WHERE num = ?
-
-       my $xdb = $self->{xdb};
-       my $cur = $xdb->postlist_begin('');
-       my $end = $xdb->postlist_end('');
-       my $xdir = $self->xdir;
-       for (; $cur != $end; $cur++) {
-               my $docid = $cur->get_docid;
-               $sth->execute($docid);
-               my $x = $sth->fetchrow_array;
-               next if $x > 0;
-               warn "I: removing $xdir #$docid, not in `over'\n";
-               $xdb->delete_document($docid);
-       }
-}
-
 1;