phash: canonicalize order, fix handling of ignored duplicates

Canonicalize the order of the prehash entries, so we don't have to
worry about looking up both pairs of edges.

When we find a collision that we decide to ignore, there is no point
in adding the same edge into the array again; instead, just skip the
current edge.

1 files changed, 4 insertions, 1 deletions

diff --git a/perllib/phash.ph b/perllib/phash.ph
index 4efc651..8feb6b7 100644
--- a/perllib/phash.ph
+++ b/perllib/phash.ph
@@ -79,11 +79,14 @@ sub gen_hash_n($$$$) {
     %edges = ();
     foreach $k (@keys) {
 	my ($pf1, $pf2) = prehash($k, $n, $sv);
+	($pf1,$pf2) = ($pf2,$pf1) if ($pf1 > $pf2); # Canonicalize order
+
 	my $pf = "$pf1,$pf2";
 	my $e = ${$href}{$k};
 	my $xkey;
 
-	if (defined($xkey = $edges{$pf}) && ${$href}{$xkey} != $e) {
+	if (defined($xkey = $edges{$pf})) {
+	    next if ($e == ${$href}{$xkey}); # Duplicate hash, safe to ignore
 	    if (defined($run)) {
 		print STDERR "$run: Collision: $pf: $k with $xkey\n";
 	    }