ds: remove fields.pm usage

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

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index acbf2c8de6092742e10cdda77415812cbf6778d6..c7f45a6c910a91b98ca3500c0b06ed5e4a8c35c5 100644 (file)
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -21,8 +21,16 @@ use PublicInbox::Search;
 sub dbh_new {
        my ($self) = @_;
        my $dbh = $self->SUPER::dbh_new(1);
+
+       # TRUNCATE reduces I/O compared to the default (DELETE)
        $dbh->do('PRAGMA journal_mode = TRUNCATE');
+
+       # 80000 pages (80MiB on SQLite <3.12.0, 320MiB on 3.12.0+)
+       # was found to be good in 2018 during the large LKML import
+       # at the time.  This ought to be configurable based on HW
+       # and inbox size; I suspect it's overkill for many inboxes.
        $dbh->do('PRAGMA cache_size = 80000');
+
        create_tables($dbh);
        $dbh;
 }
@@ -246,11 +254,10 @@ sub subject_path ($) {
 sub add_overview {
        my ($self, $mime, $smsg) = @_;
        $smsg->{lines} = $mime->body_raw =~ tr!\n!\n!;
-       $smsg->{mime} = $mime; # XXX temporary?
        my $hdr = $mime->header_obj;
        my $mids = mids_for_index($hdr);
        my $refs = parse_references($smsg, $hdr, $mids);
-       my $subj = $smsg->subject;
+       my $subj = $smsg->{subject};
        my $xpath;
        if ($subj ne '') {
                $xpath = subject_path($subj);