thread: last Reference always wins

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

diff --git a/lib/PublicInbox/SearchThread.pm b/lib/PublicInbox/SearchThread.pm
index 5774a9562b55f27956fd8e8e1baad11389e95e08..601a84b0e263428618fafc5d74540a704f4e3bfa 100644 (file)
--- a/lib/PublicInbox/SearchThread.pm
+++ b/lib/PublicInbox/SearchThread.pm
@@ -33,7 +33,8 @@ sub thread {
        my $self = shift;
        _add_message($self, $_) foreach @{$self->{messages}};
        my $id_table = delete $self->{id_table};
-       $self->{rootset} = [ grep { !delete $_->{parent} } values %$id_table ];
+       $self->{rootset} = [ grep {
+               !delete($_->{parent}) && $_->visible } values %$id_table ];
 }
 
 sub _get_cont_for_id ($$) {
@@ -51,6 +52,10 @@ sub _add_message ($$) {
        # B. For each element in the message's References field:
        defined(my $refs = $smsg->{references}) or return;
 
+       # This loop exists to help fill in gaps left from missing
+       # messages.  It is not needed in a perfect world where
+       # everything is perfectly referenced, only the last ref
+       # matters.
        my $prev;
        foreach my $ref ($refs =~ m/<([^>]+)>/g) {
                # Find a Container object for the given Message-ID
@@ -73,10 +78,8 @@ sub _add_message ($$) {
        }
 
        # C. Set the parent of this message to be the last element in
-       # References...
-       if ($prev && !$this->has_descendent($prev)) { # would loop
-               $prev->add_child($this)
-       }
+       # References.
+       $prev->add_child($this) if defined $prev;
 }
 
 sub order {
@@ -126,22 +129,31 @@ sub add_child {
 
 sub has_descendent {
        my ($self, $child) = @_;
+       my %seen; # loop prevention XXX may not be necessary
        while ($child) {
-               return 1 if $self == $child;
+               return 1 if $self == $child || $seen{$child}++;
                $child = $child->{parent};
        }
        0;
 }
 
+# Do not show/keep ghosts iff they have no children.  Sometimes
+# a ghost Message-ID is the result of a long header line
+# being folded/mangled by a MUA, and not a missing message.
+sub visible ($) {
+       my ($self) = @_;
+       $self->{smsg} || scalar values %{$self->{children}};
+}
+
 sub order_children {
        my ($cur, $ordersub) = @_;
 
-       my %seen = ($cur => 1);
+       my %seen = ($cur => 1); # self-referential loop prevention
        my @q = ($cur);
        while (defined($cur = shift @q)) {
                my $c = $cur->{children}; # The hashref here...
 
-               $c = [ grep { !$seen{$_}++ } values %$c ]; # spot/break loops
+               $c = [ grep { !$seen{$_}++ && visible($_) } values %$c ];
                $c = $ordersub->($c) if scalar @$c > 1;
                $cur->{children} = $c; # ...becomes an arrayref
                push @q, @$c;