# are denoted by a negative NNTP article number.
package PublicInbox::OverIdx;
use strict;
-use warnings;
-use base qw(PublicInbox::Over);
+use v5.10.1;
+use parent 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);
-use PublicInbox::Search;
use Carp qw(croak);
sub dbh_new {
my ($self) = @_;
- my $dbh = $self->SUPER::dbh_new(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
if (my $del = delete $self->{-ghosts_to_delete}) {
delete_by_num($self, $_) for @$del;
}
- $tid // create_ghost($self, $mid);
-}
-
-sub create_ghost {
- my ($self, $mid) = @_;
- my $id = mid2id($self, $mid);
- my $num = next_ghost_num($self);
- $num < 0 or die "ghost num is non-negative: $num\n";
- my $tid = next_tid($self);
- my $dbh = $self->{dbh};
- $dbh->prepare_cached(<<'')->execute($num, $tid);
+ $tid // do { # create a new ghost
+ my $id = mid2id($self, $mid);
+ my $num = next_ghost_num($self);
+ $num < 0 or die "ghost num is non-negative: $num\n";
+ $tid = next_tid($self);
+ my $dbh = $self->{dbh};
+ $dbh->prepare_cached(<<'')->execute($num, $tid);
INSERT INTO over (num, tid) VALUES (?,?)
- $dbh->prepare_cached(<<'')->execute($id, $num);
+ $dbh->prepare_cached(<<'')->execute($id, $num);
INSERT INTO id2num (id, num) VALUES (?,?)
- $tid;
+ $tid;
+ };
}
sub merge_threads {
}
sub add_overview {
- my ($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 '') {
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, $dd);
}
sub _add_over {
}
sub add_over {
- my ($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);
$v > 1 and warn "BUG: vivified multiple ($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 (?,?)
$dbh->do(<<'');
CREATE TABLE IF NOT EXISTS over (
- num INTEGER NOT NULL,
- tid INTEGER NOT NULL,
- sid INTEGER,
- ts INTEGER,
- ds INTEGER,
- ddd VARBINARY, /* doc-data-deflated */
+ num INTEGER NOT NULL, /* NNTP article number == IMAP UID */
+ tid INTEGER NOT NULL, /* THREADID (IMAP REFERENCES threading, JMAP) */
+ sid INTEGER, /* Subject ID (IMAP ORDEREDSUBJECT "threading") */
+ ts INTEGER, /* IMAP INTERNALDATE (Received: header, git commit time) */
+ ds INTEGER, /* RFC-2822 sent Date: header, git author time */
+ ddd VARBINARY, /* doc-data-deflated (->to_doc_data, ->load_from_data) */
UNIQUE (num)
)
$dbh->do(<<'');
CREATE TABLE IF NOT EXISTS subject (
sid INTEGER PRIMARY KEY AUTOINCREMENT,
- path VARCHAR(40) NOT NULL,
+ path VARCHAR(40) NOT NULL, /* SHA-1 of normalized subject */
UNIQUE (path)
)
$dbh->do(<<'');
CREATE TABLE IF NOT EXISTS id2num (
- id INTEGER NOT NULL,
+ id INTEGER NOT NULL, /* <=> msgid.id */
num INTEGER NOT NULL,
UNIQUE (id, num)
)
$dbh->do(<<'');
CREATE TABLE IF NOT EXISTS msgid (
- id INTEGER PRIMARY KEY AUTOINCREMENT,
+ id INTEGER PRIMARY KEY AUTOINCREMENT, /* <=> id2num.id */
mid VARCHAR(244) NOT NULL,
UNIQUE (mid)
)
sub begin_lazy {
my ($self) = @_;
return if $self->{txn};
- my $dbh = $self->connect or return;
+ my $dbh = $self->dbh or return;
$dbh->begin_work;
# $dbh->{Profile} = 2;
$self->{txn} = 1;
$self->{dbh}->rollback;
}
-sub disconnect {
+sub dbh_close {
my ($self) = @_;
die "in transaction" if $self->{txn};
- $self->SUPER::disconnect;
+ $self->SUPER::dbh_close;
}
sub create {
File::Path::mkpath(File::Basename::dirname($self->{filename}));
}
# create the DB:
- PublicInbox::Over::connect($self);
- $self->disconnect;
+ PublicInbox::Over::dbh($self);
+ $self->dbh_close;
}
sub rethread_prepare {