X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchThread.pm;h=8b2cb8059db94043affbbf82abbfbea2eddb57ba;hb=906393b801050e303d2ec2a660c85de4a5fa4740;hp=24a56d2d965a4826f2d9e25fc586f5278921523d;hpb=f2b07568e623c2a0aff4d0135617a26c887d2755;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchThread.pm b/lib/PublicInbox/SearchThread.pm
index 24a56d2d..8b2cb805 100644
--- a/lib/PublicInbox/SearchThread.pm
+++ b/lib/PublicInbox/SearchThread.pm
@@ -4,10 +4,10 @@
 # This license differs from the rest of public-inbox
 #
 # Our own jwz-style threading class based on Mail::Thread from CPAN.
-# Mail::Thread is unmaintained and available on some distros.
+# 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
 #
@@ -20,41 +20,57 @@
 package PublicInbox::SearchThread;
 use strict;
 use warnings;
-
-sub new {
-	return bless {
-		messages => $_[1],
-		id_table => {},
-		rootset  => []
-	}, $_[0];
-}
+use PublicInbox::MID qw($MID_EXTRACT);
 
 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 ];
+	my ($msgs, $ordersub, $ctx) = @_;
+	my $id_table = {};
+
+	# Sadly, we sort here anyways since the fill-in-the-blanks References:
+	# can be shakier if somebody used In-Reply-To with multiple, disparate
+	# messages.  So, take the client Date: into account since we can't
+	# alway determine ordering when somebody uses multiple In-Reply-To.
+	# We'll trust the client Date: header here instead of the Received:
+	# time since this is for display (and not retrieval)
+	_add_message($id_table, $_) for sort { $a->{ds} <=> $b->{ds} } @$msgs;
+	my $ibx = $ctx->{-inbox};
+	my $rootset = [ grep {
+			!delete($_->{parent}) && $_->visible($ibx)
+		} values %$id_table ];
+	$id_table = undef;
+	$rootset = $ordersub->($rootset);
+	$_->order_children($ordersub, $ctx) for @$rootset;
+	$rootset;
 }
 
 sub _get_cont_for_id ($$) {
-	my ($self, $mid) = @_;
-	$self->{id_table}{$mid} ||= PublicInbox::SearchThread::Msg->new($mid);
+	my ($id_table, $mid) = @_;
+	$id_table->{$mid} ||= PublicInbox::SearchThread::Msg->new($mid);
 }
 
 sub _add_message ($$) {
-	my ($self, $smsg) = @_;
+	my ($id_table, $smsg) = @_;
 
 	# A. if id_table...
-	my $this = _get_cont_for_id($self, $smsg->{mid});
+	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;
 
+	# 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) {
+	foreach my $ref ($refs =~ m/$MID_EXTRACT/go) {
 		# Find a Container object for the given Message-ID
-		my $cont = _get_cont_for_id($self, $ref);
+		my $cont = _get_cont_for_id($id_table, $ref);
 
 		# Link the References field's Containers together in
 		# the order implied by the References header
@@ -73,19 +89,12 @@ 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.
+	if (defined $prev && !$this->has_descendent($prev)) { # would loop
+		$prev->add_child($this);
 	}
 }
 
-sub order {
-	my ($self, $ordersub) = @_;
-	my $rootset = $ordersub->($self->{rootset});
-	$self->{rootset} = $rootset;
-	$_->order_children($ordersub) for @$rootset;
-}
-
 package PublicInbox::SearchThread::Msg;
 use strict;
 use warnings;
@@ -98,6 +107,16 @@ sub new {
 	}, $_[0];
 }
 
+sub topmost {
+	my ($self) = @_;
+	my @q = ($self);
+	while (my $cont = shift @q) {
+		return $cont if $cont->{smsg};
+		push @q, values %{$cont->{children}};
+	}
+	undef;
+}
+
 sub add_child {
 	my ($self, $child) = @_;
 	croak "Cowardly refusing to become my own parent: $self"
@@ -116,22 +135,33 @@ sub add_child {
 
 sub has_descendent {
 	my ($self, $child) = @_;
+	my %seen; # loop prevention
 	while ($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, $ibx) = @_;
+	($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 = ($cur => 1);
+	my %seen = ($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{$_}++ } values %$c ]; # spot/break loops
+		$c = [ grep { !$seen{$_}++ && visible($_, $ibx) } values %$c ];
 		$c = $ordersub->($c) if scalar @$c > 1;
 		$cur->{children} = $c; # ...becomes an arrayref
 		push @q, @$c;