over: skip nodatacow on the journal

[public-inbox.git] / lib / PublicInbox / Over.pm

diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index f32743c05a8a461baf0c4f5a52c983d5fecd25af..a2f0411776ac9f2b413aedbeb6daea72aa3273fc 100644 (file)
--- 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} = $f; # die on stat() below:
                }
@@ -52,6 +54,7 @@ sub new {
 sub disconnect {
        my ($self) = @_;
        if (my $dbh = delete $self->{dbh}) {
+               delete $self->{-get_art};
                $self->{filename} = $dbh->sqlite_db_filename;
        }
 }
@@ -63,7 +66,6 @@ sub load_from_row ($;$) {
        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
@@ -99,6 +101,15 @@ 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 {
@@ -165,6 +176,35 @@ 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);
@@ -197,9 +237,9 @@ 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;
@@ -226,13 +266,7 @@ 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)
@@ -274,10 +308,7 @@ 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";
        }