X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchThread.pm;h=8b2cb8059db94043affbbf82abbfbea2eddb57ba;hb=906393b801050e303d2ec2a660c85de4a5fa4740;hp=2cd066dbf6a58ef837ca803a64025ae2516d9f46;hpb=90b3d23352a0c37680ac266acaf4fef73a781bc9;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchThread.pm b/lib/PublicInbox/SearchThread.pm
index 2cd066db..8b2cb805 100644
--- a/lib/PublicInbox/SearchThread.pm
+++ b/lib/PublicInbox/SearchThread.pm
@@ -7,7 +7,7 @@
 # Mail::Thread is unmaintained and unavailable on some distros.
 # We also do not want pruning or subject grouping, since we want
 # to encourage strict threading and hopefully encourage people
-# to use proper In-Reply-To.
+# to use proper In-Reply-To/References.
 #
 # This includes fixes from several open bugs for Mail::Thread
 #
@@ -20,16 +20,26 @@
 package PublicInbox::SearchThread;
 use strict;
 use warnings;
+use PublicInbox::MID qw($MID_EXTRACT);
 
 sub thread {
-	my ($messages, $ordersub) = @_;
+	my ($msgs, $ordersub, $ctx) = @_;
 	my $id_table = {};
-	_add_message($id_table, $_) foreach @$messages;
+
+	# Sadly, we sort here anyways since the fill-in-the-blanks References:
+	# can be shakier if somebody used In-Reply-To with multiple, disparate
+	# messages.  So, take the client Date: into account since we can't
+	# alway determine ordering when somebody uses multiple In-Reply-To.
+	# We'll trust the client Date: header here instead of the Received:
+	# time since this is for display (and not retrieval)
+	_add_message($id_table, $_) for sort { $a->{ds} <=> $b->{ds} } @$msgs;
+	my $ibx = $ctx->{-inbox};
 	my $rootset = [ grep {
-		!delete($_->{parent}) && $_->visible } values %$id_table ];
+			!delete($_->{parent}) && $_->visible($ibx)
+		} values %$id_table ];
 	$id_table = undef;
 	$rootset = $ordersub->($rootset);
-	$_->order_children($ordersub) for @$rootset;
+	$_->order_children($ordersub, $ctx) for @$rootset;
 	$rootset;
 }
 
@@ -45,6 +55,11 @@ sub _add_message ($$) {
 	my $this = _get_cont_for_id($id_table, $smsg->{mid});
 	$this->{smsg} = $smsg;
 
+	# saves around 4K across 1K messages
+	# TODO: move this to a more appropriate place, breaks tests
+	# if we do it during psgi_cull
+	delete $smsg->{num};
+
 	# B. For each element in the message's References field:
 	defined(my $refs = $smsg->{references}) or return;
 
@@ -53,7 +68,7 @@ sub _add_message ($$) {
 	# everything is perfectly referenced, only the last ref
 	# matters.
 	my $prev;
-	foreach my $ref ($refs =~ m/<([^>]+)>/g) {
+	foreach my $ref ($refs =~ m/$MID_EXTRACT/go) {
 		# Find a Container object for the given Message-ID
 		my $cont = _get_cont_for_id($id_table, $ref);
 
@@ -75,7 +90,9 @@ sub _add_message ($$) {
 
 	# C. Set the parent of this message to be the last element in
 	# References.
-	$prev->add_child($this) if defined $prev;
+	if (defined $prev && !$this->has_descendent($prev)) { # would loop
+		$prev->add_child($this);
+	}
 }
 
 package PublicInbox::SearchThread::Msg;
@@ -129,20 +146,22 @@ sub has_descendent {
 # 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 visible ($$) {
+	my ($self, $ibx) = @_;
+	($self->{smsg} ||= eval { $ibx->smsg_by_mid($self->{id}) }) ||
+	 (scalar values %{$self->{children}});
 }
 
 sub order_children {
-	my ($cur, $ordersub) = @_;
+	my ($cur, $ordersub, $ctx) = @_;
 
 	my %seen = ($cur => 1); # self-referential loop prevention
 	my @q = ($cur);
+	my $ibx = $ctx->{-inbox};
 	while (defined($cur = shift @q)) {
 		my $c = $cur->{children}; # The hashref here...
 
-		$c = [ grep { !$seen{$_}++ && visible($_) } values %$c ];
+		$c = [ grep { !$seen{$_}++ && visible($_, $ibx) } values %$c ];
 		$c = $ordersub->($c) if scalar @$c > 1;
 		$cur->{children} = $c; # ...becomes an arrayref
 		push @q, @$c;