X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchThread.pm;h=60f692b276bb41dd83d292b1b96794e01e31b70a;hb=d0147582e289fdd4cdd84e91d8b0f8ae9c230124;hp=fafe7d7bd4e04b87e4ce91a2183d45c932993ac6;hpb=93474f58d361b2ace4d5e51d5be4c220513da8d0;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchThread.pm b/lib/PublicInbox/SearchThread.pm
index fafe7d7b..60f692b2 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
 #
@@ -20,46 +20,52 @@
 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}) && $_->visible } values %$id_table ];
-}
-
-sub _get_cont_for_id ($$) {
-	my ($self, $mid) = @_;
-	$self->{id_table}{$mid} ||= PublicInbox::SearchThread::Msg->new($mid);
+	my ($msgs, $ordersub, $ctx) = @_;
+
+	# A. put all current $msgs (non-ghosts) into %id_table
+	my %id_table = map {;
+		# this delete saves around 4K across 1K messages
+		# TODO: move this to a more appropriate place, breaks tests
+		# if we do it during psgi_cull
+		delete $_->{num};
+
+		$_->{mid} => PublicInbox::SearchThread::Msg::cast($_);
+	} @$msgs;
+
+	# 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
+	# 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)
+	_set_parent(\%id_table, $_) for sort { $a->{ds} <=> $b->{ds} } @$msgs;
+	my $ibx = $ctx->{-inbox};
+	my $rootset = [ grep {
+			!delete($_->{parent}) && $_->visible($ibx)
+		} values %id_table ];
+	$rootset = $ordersub->($rootset);
+	$_->order_children($ordersub, $ctx) for @$rootset;
+	$rootset;
 }
 
-sub _add_message ($$) {
-	my ($self, $smsg) = @_;
-
-	# A. if id_table...
-	my $this = _get_cont_for_id($self, $smsg->{mid});
-	$this->{smsg} = $smsg;
+sub _set_parent ($$) {
+	my ($id_table, $this) = @_;
 
 	# B. For each element in the message's References field:
-	defined(my $refs = $smsg->{references}) or return;
+	defined(my $refs = $this->{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 = $id_table->{$ref} //=
+			PublicInbox::SearchThread::Msg::ghost($ref);
 
 		# Link the References field's Containers together in
 		# the order implied by the References header
@@ -79,33 +85,37 @@ sub _add_message ($$) {
 
 	# C. Set the parent of this message to be the last element in
 	# References.
-	$prev->add_child($this) if defined $prev;
-}
-
-sub order {
-	my ($self, $ordersub) = @_;
-	my $rootset = $ordersub->($self->{rootset});
-	$self->{rootset} = $rootset;
-	$_->order_children($ordersub) for @$rootset;
+	if (defined $prev && !$this->has_descendent($prev)) { # would loop
+		$prev->add_child($this);
+	}
 }
 
 package PublicInbox::SearchThread::Msg;
+use base qw(PublicInbox::Smsg);
 use strict;
 use warnings;
 use Carp qw(croak);
 
-sub new {
+# declare a ghost smsg (determined by absence of {blob})
+sub ghost {
 	bless {
-		id => $_[1],
+		mid => $_[0],
 		children => {}, # becomes an array when sorted by ->order(...)
-	}, $_[0];
+	}, __PACKAGE__;
+}
+
+# give a existing smsg the methods of this class
+sub cast {
+	my ($smsg) = @_;
+	$smsg->{children} = {};
+	bless $smsg, __PACKAGE__;
 }
 
 sub topmost {
 	my ($self) = @_;
 	my @q = ($self);
 	while (my $cont = shift @q) {
-		return $cont if $cont->{smsg};
+		return $cont if $cont->{blob};
 		push @q, values %{$cont->{children}};
 	}
 	undef;
@@ -116,7 +126,7 @@ sub add_child {
 	croak "Cowardly refusing to become my own parent: $self"
 	  if $self == $child;
 
-	my $cid = $child->{id};
+	my $cid = $child->{mid};
 
 	# reparenting:
 	if (defined(my $parent = $child->{parent})) {
@@ -140,20 +150,27 @@ sub has_descendent {
 # Do not show/keep ghosts iff they have no children.  Sometimes
 # a ghost Message-ID is the result of a long header line
 # being folded/mangled by a MUA, and not a missing message.
-sub visible ($) {
-	my ($self) = @_;
-	$self->{smsg} || scalar values %{$self->{children}};
+sub visible ($$) {
+	my ($self, $ibx) = @_;
+	return 1 if $self->{blob};
+	if (my $by_mid = $ibx->smsg_by_mid($self->{mid})) {
+		%$self = (%$self, %$by_mid);
+		1;
+	} else {
+		(scalar values %{$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;