use DBI qw(:sql_types); # SQL_BLOB
use PublicInbox::MID qw/id_compress mids_for_index references/;
use PublicInbox::Smsg qw(subject_normalized);
-use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
use Compress::Zlib qw(compress);
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);
$dbh;
}
}
sub add_overview {
- my ($self, $mime, $bytes, $num, $oid, $mid0, $times) = @_;
- my $lines = $mime->body_raw =~ tr!\n!\n!;
- my $smsg = bless {
- mime => $mime,
- mid => $mid0,
- bytes => $bytes,
- lines => $lines,
- blob => $oid,
- }, 'PublicInbox::Smsg';
+ my ($self, $mime, $smsg) = @_;
+ $smsg->{lines} = $mime->body_raw =~ tr!\n!\n!;
my $hdr = $mime->header_obj;
my $mids = mids_for_index($hdr);
my $refs = parse_references($smsg, $hdr, $mids);
my $dd = $smsg->to_doc_data;
utf8::encode($dd);
$dd = compress($dd);
- my $ds = msg_timestamp($hdr, $times->{autime});
- my $ts = msg_datestamp($hdr, $times->{cotime});
- my $values = [ $ts, $ds, $num, $mids, $refs, $xpath, $dd ];
- add_over($self, $values);
+ add_over($self, [ @$smsg{qw(ts ds num)}, $mids, $refs, $xpath, $dd ]);
}
sub add_over {