X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOver.pm;h=3e74b7a6f3ccd9372d67078fab01a38ebc92aa05;hb=5f6a0d2342323541e44ff2f1e7329053d0263800;hp=e3f264564434ef477fd90c25de29b8450bebb27c;hpb=f06e84220e5566e74c4af675a7afaf1636b024e4;p=public-inbox.git

diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index e3f26456..3e74b7a6 100644
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -18,7 +18,9 @@ sub dbh_new {
 	my $f = delete $self->{filename};
 	if (!-f $f) { # SQLite defaults mode to 0644, we want 0666
 		if ($rw) {
+			require PublicInbox::Spawn;
 			open my $fh, '+>>', $f or die "failed to open $f: $!";
+			PublicInbox::Spawn::nodatacow_fd(fileno($fh));
 		} else {
 			$self->{filename} = $f; # die on stat() below:
 		}
@@ -40,6 +42,28 @@ sub dbh_new {
 		$st = pack('dd', $st[0], $st[1]);
 	} while ($st ne $self->{st} && $tries++ < 3);
 	warn "W: $f: .st_dev, .st_ino unstable\n" if $st ne $self->{st};
+
+	if ($rw) {
+		# TRUNCATE reduces I/O compared to the default (DELETE).
+		#
+		# Do not use WAL by default since we expect the case
+		# where any users may read via read-only daemons
+		# (-httpd/-imapd/-nntpd); but only a single user has
+		# write permissions for -watch/-mda.
+		#
+		# Read-only WAL support in SQLite 3.22.0 (2018-01-22)
+		# doesn't do what we need: it is only intended for
+		# immutable read-only media (e.g. CD-ROM) and not
+		# usable for our use case described above.
+		#
+		# If an admin is willing to give read-only daemons R/W
+		# permissions; they can enable WAL manually and we will
+		# respect that by not clobbering it.
+		my $jm = $dbh->selectrow_array('PRAGMA journal_mode');
+		$dbh->do('PRAGMA journal_mode = TRUNCATE') if $jm ne 'wal';
+
+		$dbh->do('PRAGMA synchronous = OFF') if $rw > 1;
+	}
 	$dbh;
 }
 
@@ -51,6 +75,7 @@ sub new {
 sub disconnect {
 	my ($self) = @_;
 	if (my $dbh = delete $self->{dbh}) {
+		delete $self->{-get_art};
 		$self->{filename} = $dbh->sqlite_db_filename;
 	}
 }
@@ -62,7 +87,6 @@ sub load_from_row ($;$) {
 	bless $smsg, 'PublicInbox::Smsg';
 	if (defined(my $data = delete $smsg->{ddd})) {
 		$data = uncompress($data);
-		utf8::decode($data);
 		PublicInbox::Smsg::load_from_data($smsg, $data);
 
 		# saves over 600K for 1000+ message threads
@@ -98,6 +122,15 @@ ORDER BY num ASC
 
 }
 
+sub get_all {
+	my $self = shift;
+	my $nr = scalar(@_) or return [];
+	my $in = '?' . (',?' x ($nr - 1));
+	do_get($self, <<"", { cull => 1, limit => $nr }, @_);
+SELECT num,ds,ddd FROM over WHERE num IN ($in)
+
+}
+
 sub nothing () { wantarray ? (0, []) : [] };
 
 sub get_thread {
@@ -164,6 +197,35 @@ ORDER BY $sort_col DESC
 	($nr, $msgs);
 }
 
+# strict `tid' matches, only, for thread-expanded mbox.gz search results
+# and future CLI interface
+# returns true if we have IDs, undef if not
+sub expand_thread {
+	my ($self, $ctx) = @_;
+	my $dbh = $self->connect;
+	do {
+		defined(my $num = $ctx->{ids}->[0]) or return;
+		my ($tid) = $dbh->selectrow_array(<<'', undef, $num);
+SELECT tid FROM over WHERE num = ?
+
+		if (defined($tid)) {
+			my $sql = <<'';
+SELECT num FROM over WHERE tid = ? AND num > ?
+ORDER BY num ASC LIMIT 1000
+
+			my $xids = $dbh->selectcol_arrayref($sql, undef, $tid,
+							$ctx->{prev} // 0);
+			if (scalar(@$xids)) {
+				$ctx->{prev} = $xids->[-1];
+				$ctx->{xids} = $xids;
+				return 1; # success
+			}
+		}
+		$ctx->{prev} = 0;
+		shift @{$ctx->{ids}};
+	} while (1);
+}
+
 sub recent {
 	my ($self, $opts, $after, $before) = @_;
 	my ($s, @v);
@@ -196,9 +258,9 @@ SELECT COUNT(num) FROM over WHERE num > 0
 
 sub get_art {
 	my ($self, $num) = @_;
-	my $dbh = $self->connect;
-	my $sth = $dbh->prepare_cached(<<'', undef, 1);
-SELECT num,ds,ts,ddd FROM over WHERE num = ? LIMIT 1
+	# caching $sth ourselves is faster than prepare_cached
+	my $sth = $self->{-get_art} //= $self->connect->prepare(<<'');
+SELECT num,tid,ds,ts,ddd FROM over WHERE num = ? LIMIT 1
 
 	$sth->execute($num);
 	my $smsg = $sth->fetchrow_hashref;
@@ -225,13 +287,7 @@ ORDER BY num ASC LIMIT 1
 	$sth->execute($$id, $$prev);
 	my $num = $sth->fetchrow_array or return;
 	$$prev = $num;
-
-	$sth = $dbh->prepare_cached(<<"", undef, 1);
-SELECT num,ts,ds,ddd FROM over WHERE num = ? LIMIT 1
-
-	$sth->execute($num);
-	my $smsg = $sth->fetchrow_hashref or return;
-	load_from_row($smsg);
+	get_art($self, $num);
 }
 
 # IMAP search, this is limited by callers to UID_SLICE size (50K)
@@ -273,10 +329,7 @@ sub check_inodes {
 		my $st = pack('dd', $st[0], $st[1]);
 
 		# don't actually reopen, just let {dbh} be recreated later
-		if ($st ne ($self->{st} // $st)) {
-			delete($self->{dbh});
-			$self->{filename} = $f;
-		}
+		disconnect($self) if $st ne ($self->{st} // $st);
 	} else {
 		warn "W: stat $f: $!\n";
 	}