X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOverIdx.pm;h=9f4a56fbd4861b9978a3a3146317a42d597a95f1;hb=5f6a0d2342323541e44ff2f1e7329053d0263800;hp=fcb450794fc2c05bffab9a49a330b686d22f1913;hpb=0e68dbad3dc5e3fbc44e8ba8be576b81455d3359;p=public-inbox.git diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm index fcb45079..9f4a56fb 100644 --- a/lib/PublicInbox/OverIdx.pm +++ b/lib/PublicInbox/OverIdx.pm @@ -12,7 +12,7 @@ use strict; use warnings; use base qw(PublicInbox::Over); use IO::Handle; -use DBI; +use DBI qw(:sql_types); # SQL_BLOB use PublicInbox::MID qw/id_compress mids_for_index references/; use PublicInbox::Smsg qw(subject_normalized); use Compress::Zlib qw(compress); @@ -21,12 +21,7 @@ use Carp qw(croak); sub dbh_new { my ($self) = @_; - my $dbh = $self->SUPER::dbh_new($self->{-no_sync} ? 2 : 1); - - # TRUNCATE reduces I/O compared to the default (DELETE) - # We do not use WAL since we're optimized for read-only ops, - # (and read-only requires SQLite 3.22.0 (2018-01-22)). - $dbh->do('PRAGMA journal_mode = TRUNCATE'); + my $dbh = $self->SUPER::dbh_new($self->{-no_fsync} ? 2 : 1); # 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 @@ -271,11 +266,10 @@ sub subject_path ($) { } sub add_overview { - my ($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, $mids); + my ($self, $eml, $smsg) = @_; + $smsg->{lines} = $eml->body_raw =~ tr!\n!\n!; + my $mids = mids_for_index($eml); + my $refs = parse_references($smsg, $eml, $mids); my $subj = $smsg->{subject}; my $xpath; if ($subj ne '') { @@ -285,7 +279,7 @@ sub add_overview { my $dd = $smsg->to_doc_data; utf8::encode($dd); $dd = compress($dd); - add_over($self, [ @$smsg{qw(ts ds num)}, $mids, $refs, $xpath, $dd ]); + add_over($self, $smsg, $mids, $refs, $xpath, $dd); } sub _add_over { @@ -312,10 +306,10 @@ sub _add_over { } sub add_over { - my ($self, $values) = @_; - my ($ts, $ds, $num, $mids, $refs, $xpath, $ddd) = @$values; + my ($self, $smsg, $mids, $refs, $xpath, $ddd) = @_; my $old_tid; my $vivified = 0; + my $num = $smsg->{num}; begin_lazy($self); delete_by_num($self, $num, \$old_tid); @@ -327,17 +321,17 @@ sub add_over { $v > 1 and warn "BUG: vivified multiple ($v) ghosts for $mid\n"; $vivified += $v; } - my $tid = $vivified ? $old_tid : link_refs($self, $refs, $old_tid); - my $sid = sid($self, $xpath); + $smsg->{tid} = $vivified ? $old_tid : link_refs($self, $refs, $old_tid); + $smsg->{sid} = sid($self, $xpath); my $dbh = $self->{dbh}; my $sth = $dbh->prepare_cached(<<''); INSERT INTO over (num, tid, sid, ts, ds, ddd) VALUES (?,?,?,?,?,?) - my $n = 0; - my @v = ($num, $tid, $sid, $ts, $ds); - foreach (@v) { $sth->bind_param(++$n, $_) } - $sth->bind_param(++$n, $ddd); + my $nc = 1; + $sth->bind_param($nc, $num); + $sth->bind_param(++$nc, $smsg->{$_}) for (qw(tid sid ts ds)); + $sth->bind_param(++$nc, $ddd, SQL_BLOB); $sth->execute; $sth = $dbh->prepare_cached(<<''); INSERT INTO id2num (id, num) VALUES (?,?)