over: store xref3 data in over.sqlite3

We may not end up storing xref3 data in Xapian, actually.
This will make indexlevel=basic possible, and along with
--sequential-shard indexing support for slow storage.

Making oidmap a separate table seems unnecessary, too, so
fold it into the xref3 table since it's unlikely a git blob
will be responsible for multiple xref3 rows.

diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index 081123868795fd9b22997488331b0bc39dc51800..f34e7fc1cb23e10630ea3ab9334a1b4b47e61824 100644 (file)
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -260,6 +260,25 @@ SELECT num,tid,ds,ts,ddd FROM over WHERE num = ? LIMIT 1
        $smsg ? load_from_row($smsg) : undef;
 }
 
+sub get_xref3 {
+       my ($self, $num) = @_;
+       my $dbh = dbh($self);
+       my $sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT ibx_id,xnum,oidbin FROM xref3 WHERE docid = ? ORDER BY ibx_id ASC
+
+       $sth->execute($num);
+       my $rows = $sth->fetchall_arrayref;
+       my $eidx_key_sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT eidx_key FROM inboxes WHERE ibx_id = ?
+
+       [ map {
+               my $r = $_;
+               $eidx_key_sth->execute($r->[0]);
+               my $eidx_key = $eidx_key_sth->fetchrow_array;
+               "$eidx_key:$r->[1]:".unpack('H*', $r->[2]);
+       } @$rows ];
+}
+
 sub next_by_mid {
        my ($self, $mid, $id, $prev) = @_;
        my $dbh = dbh($self);

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 09bca790f20a719925e3437072bf1fbb3513f8e4..dff2780d861f71326251744b383cebf9e10304ae 100644 (file)
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -517,20 +517,27 @@ sub eidx_prep ($) {
        my ($self) = @_;
        $self->{-eidx_prep} //= do {
                my $dbh = $self->dbh;
-               $dbh->do(<<'');
-INSERT OR IGNORE INTO counter (key) VALUES ('oidmap_num')
+               $dbh->do(<<"");
+INSERT OR IGNORE INTO counter (key) VALUES ('eidx_docid')
 
                $dbh->do(<<'');
-INSERT OR IGNORE INTO counter (key) VALUES ('eidx_docid')
+CREATE TABLE IF NOT EXISTS inboxes (
+       ibx_id INTEGER PRIMARY KEY AUTOINCREMENT,
+       eidx_key VARCHAR(255) NOT NULL, /* {newsgroup} // {inboxdir} */
+       UNIQUE (eidx_key)
+)
 
                $dbh->do(<<'');
-CREATE TABLE IF NOT EXISTS oidmap (
-       num INTEGER NOT NULL, /* NNTP article number == IMAP UID */
-       oidbin VARBINARY, /* 20-byte SHA-1 or 32-byte SHA-256 */
-       UNIQUE (num),
-       UNIQUE (oidbin)
+CREATE TABLE IF NOT EXISTS xref3 (
+       docid INTEGER NOT NULL, /* <=> over.num */
+       ibx_id INTEGER NOT NULL, /* <=> inboxes.ibx_id */
+       xnum INTEGER NOT NULL, /* NNTP article number in ibx */
+       oidbin VARBINARY NOT NULL, /* 20-byte SHA-1 or 32-byte SHA-256 */
+       UNIQUE (docid, ibx_id, xnum, oidbin)
 )
 
+       $dbh->do('CREATE INDEX IF NOT EXISTS idx_docid ON xref3 (docid)');
+
                $dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS eidx_meta (
        key VARCHAR(255) PRIMARY KEY,
@@ -564,28 +571,33 @@ sub eidx_max {
        get_counter($self->{dbh}, 'eidx_docid');
 }
 
-sub oid2num {
-       my ($self, $oidhex) = @_;
-       my $dbh = eidx_prep($self);
-       my $sth = $dbh->prepare_cached(<<'', undef, 1);
-SELECT num FROM oidmap WHERE oidbin = ?
-
-       $sth->bind_param(1, pack('H*', $oidhex), SQL_BLOB);
+sub add_xref3 {
+       my ($self, $docid, $xnum, $oidhex, $eidx_key) = @_;
+       begin_lazy($self);
+       my $ibx_id = id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+       my $oidbin = pack('H*', $oidhex);
+       my $sth = $self->{dbh}->prepare_cached(<<'');
+INSERT OR IGNORE INTO xref3 (docid, ibx_id, xnum, oidbin) VALUES (?, ?, ?, ?)
+
+       $sth->bind_param(1, $docid);
+       $sth->bind_param(2, $ibx_id);
+       $sth->bind_param(3, $xnum);
+       $sth->bind_param(4, $oidbin, SQL_BLOB);
        $sth->execute;
-       $sth->fetchrow_array;
 }
 
-sub oid_add {
-       my ($self, $oidhex) = @_;
-       my $dbh = eidx_prep($self);
-       my $num = adj_counter($self, 'oidmap_num', '+');
-       my $sth = $dbh->prepare_cached(<<'');
-INSERT INTO oidmap (num, oidbin) VALUES (?,?)
-
-       $sth->bind_param(1, $num);
-       $sth->bind_param(2, pack('H*', $oidhex), SQL_BLOB);
+sub remove_xref3 {
+       my ($self, $docid, $oidhex, $eidx_key) = @_;
+       begin_lazy($self);
+       my $ibx_id = id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+       my $oidbin = pack('H*', $oidhex);
+       my $sth = $self->{dbh}->prepare_cached(<<'');
+DELETE FROM xref3 WHERE docid = ? AND ibx_id = ? AND oidbin = ?
+
+       $sth->bind_param(1, $docid);
+       $sth->bind_param(2, $ibx_id);
+       $sth->bind_param(3, $oidbin, SQL_BLOB);
        $sth->execute;
-       $num;
 }
 
 1;

diff --git a/t/over.t b/t/over.t
index 3e2860f8f96d0d40805b72f5b954b79e5970c67b..56c20d01799ce7a244eaa82fc3abb13b524efebe 100644 (file)
--- a/t/over.t
+++ b/t/over.t
@@ -75,14 +75,27 @@ SKIP: {
 }
 
 # ext index additions
+$over->eidx_prep;
 {
-       my $hex = 'deadbeefcafe';
-       my $n = $over->oid_add($hex);
-       ok($n > 0, 'oid_add returned number');
-       is($over->oid2num($hex), $n, 'oid2num works');
-       my $n2 = $over->oid_add($hex.$hex);
-       ok($n2 > $n, 'oid_add increments');
-       is($over->oid2num($hex.$hex), $n2, 'oid2num works again');
+       my @arg = qw(1349 2019 adeadba7cafe example.key);
+       ok($over->add_xref3(@arg), 'first add');
+       ok($over->add_xref3(@arg), 'add idempotent');
+       my $xref3 = $over->get_xref3(1349);
+       is_deeply($xref3, [ 'example.key:2019:adeadba7cafe' ], 'xref3 works');
+
+       @arg = qw(1349 2018 deadbeefcafe example.kee);
+       ok($over->add_xref3(@arg), 'add another xref3');
+       $xref3 = $over->get_xref3(1349);
+       is_deeply($xref3, [ 'example.key:2019:adeadba7cafe',
+                       'example.kee:2018:deadbeefcafe' ],
+                       'xref3 works forw two');
+
+       @arg = qw(1349 adeadba7cafe example.key);
+       ok($over->remove_xref3(@arg), 'remove first');
+       $xref3 = $over->get_xref3(1349);
+       is_deeply($xref3, [ 'example.kee:2018:deadbeefcafe' ],
+               'confirm removal successful');
+       $over->rollback_lazy;
 }
 
 done_testing();