X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchThread.pm;h=38d1aa6e2c99e961b7caae4562adf840ef5e59b8;hb=4da62f284003d75abe7cb35594414eb2224f42bc;hp=be29098073cab4bd1f67884750c5ee273e572336;hpb=c204da04aa24e85236f82ba5a7c6c7e19c8a20d3;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchThread.pm b/lib/PublicInbox/SearchThread.pm
index be290980..38d1aa6e 100644
--- a/lib/PublicInbox/SearchThread.pm
+++ b/lib/PublicInbox/SearchThread.pm
@@ -20,24 +20,26 @@
 package PublicInbox::SearchThread;
 use strict;
 use warnings;
+use PublicInbox::MID qw($MID_EXTRACT);
 
 sub thread {
-	my ($msgs, $ordersub, $ibx) = @_;
+	my ($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.
+	# always 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, $ibx) for @$rootset;
+	$_->order_children($ordersub, $ctx) for @$rootset;
 	$rootset;
 }
 
@@ -53,6 +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;
 
@@ -61,7 +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);
 
@@ -146,10 +153,11 @@ sub visible ($$) {
 }
 
 sub order_children {
-	my ($cur, $ordersub, $ibx) = @_;
+	my ($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...