X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FView.pm;h=8969e17576f60de54152ebb2d4502571610801ef;hb=f76f265a851944b5dedcc3be5f3b5224b6ebda89;hp=08d78945a49e65a882143b2c5086afd97633aaa6;hpb=50e279d1b84f8cf69a5cffd13201ad41b8c7c8cf;p=public-inbox.git

diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 08d78945..8969e175 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014, Eric Wong <normalperson@yhbt.net> and all contributors
+# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
 # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
 package PublicInbox::View;
 use strict;
@@ -10,7 +10,8 @@ use Encode::MIME::Header;
 use Email::MIME::ContentType qw/parse_content_type/;
 use PublicInbox::Hval;
 use PublicInbox::MID qw/mid_clean mid_compress mid2path/;
-use Digest::SHA;
+use Digest::SHA qw/sha1_hex/;
+my $SALT = rand;
 require POSIX;
 
 # TODO: make these constants tunable
@@ -18,6 +19,7 @@ use constant MAX_INLINE_QUOTED => 12; # half an 80x24 terminal
 use constant MAX_TRUNC_LEN => 72;
 use constant PRE_WRAP => "<pre\nstyle=\"white-space:pre-wrap\">";
 use constant T_ANCHOR => '#u';
+use constant INDENT => '  ';
 
 *ascii_html = *PublicInbox::Hval::ascii_html;
 
@@ -31,10 +33,9 @@ sub msg_html {
 	} else {
 		$footer = '';
 	}
-	my $srch = $ctx->{srch} if $ctx;
-	headers_to_html_header($mime, $full_pfx, $srch) .
+	headers_to_html_header($mime, $full_pfx, $ctx) .
 		multipart_text_as_html($mime, $full_pfx) .
-		'</pre><hr /><pre>' .
+		'</pre><hr />' . PRE_WRAP .
 		html_footer($mime, 1, $full_pfx, $ctx) .
 		$footer .
 		'</pre></body></html>';
@@ -46,6 +47,19 @@ sub feed_entry {
 	PRE_WRAP . multipart_text_as_html($mime, $full_pfx) . '</pre>';
 }
 
+sub in_reply_to {
+	my ($header_obj) = @_;
+	my $irt = $header_obj->header('In-Reply-To');
+
+	return mid_clean($irt) if (defined $irt);
+
+	my $refs = $header_obj->header('References');
+	if ($refs && $refs =~ /<([^>]+)>\s*\z/s) {
+		return $1;
+	}
+	undef;
+}
+
 # this is already inside a <pre>
 sub index_entry {
 	my ($fh, $mime, $level, $state) = @_;
@@ -61,7 +75,7 @@ sub index_entry {
 	my $mid_raw = $header_obj->header('Message-ID');
 	my $id = anchor_for($mid_raw);
 	my $seen = $state->{seen};
-	$seen->{$id} = "#$id"; # save the anchor for later
+	$seen->{$id} = "#$id"; # save the anchor for children, later
 
 	my $mid = PublicInbox::Hval->new_msgid($mid_raw);
 	my $from = PublicInbox::Hval->new_oneline($mime->header('From'))->raw;
@@ -71,34 +85,24 @@ sub index_entry {
 	$from = PublicInbox::Hval->new_oneline($from)->as_html;
 	$subj = PublicInbox::Hval->new_oneline($subj)->as_html;
 	my $more = 'permalink';
-	my $root_anchor = $state->{root_anchor};
+	my $root_anchor = $state->{root_anchor} || '';
 	my $path = $root_anchor ? '../../' : '';
 	my $href = $mid->as_href;
-	my $irt = $header_obj->header('In-Reply-To');
-	my ($anchor_idx, $anchor, $t_anchor);
-	if (defined $irt) {
-		$anchor_idx = anchor_for($irt);
-		$anchor = $seen->{$anchor_idx};
-		$t_anchor = T_ANCHOR;
-	} else {
-		$t_anchor = '';
-	}
+	my $irt = in_reply_to($header_obj);
+	my $parent_anchor = $seen->{anchor_for($irt)} if defined $irt;
+
 	if ($srch) {
-		$subj = "<a\nhref=\"${path}t/$href/#u\">$subj</a>";
+		my $t = $ctx->{flat} ? 'T' : 't';
+		$subj = "<a\nhref=\"${path}$href/$t/#u\">$subj</a>";
 	}
-	if ($root_anchor && $root_anchor eq $id) {
+	if ($root_anchor eq $id) {
 		$subj = "<u\nid=\"u\">$subj</u>";
 	}
 
-	my $ts = $mime->header('X-PI-TS');
-	unless (defined $ts) {
-		$ts = msg_timestamp($mime);
-	}
-	$ts = POSIX::strftime('%Y-%m-%d %H:%M', gmtime($ts));
-
+	my $ts = _msg_date($mime);
 	my $rv = "<table\nsummary=l$level><tr>";
 	if ($level) {
-		$rv .= '<td><pre>' . ('  ' x $level) . '</pre></td>';
+		$rv .= '<td><pre>' . (INDENT x $level) . '</pre></td>';
 	}
 	$rv .= "<td\nid=s$midx>" . PRE_WRAP;
 	$rv .= "<b\nid=\"$id\">$subj</b>\n";
@@ -110,9 +114,11 @@ sub index_entry {
 	$fh->write($rv .= "\n\n");
 
 	my ($fhref, $more_ref);
-	my $mhref = "${path}m/$href/";
-	if ($level > 0) {
-		$fhref = "${path}f/$href/";
+	my $mhref = "${path}$href/";
+
+	# show full message if it's our root message
+	if ($root_anchor ne $id) {
+		$fhref = "${path}$href/f/";
 		$more_ref = \$more;
 	}
 	# scan through all parts, looking for displayable text
@@ -121,23 +127,26 @@ sub index_entry {
 	});
 	$mime->body_set('');
 
-	my $txt = "${path}m/$href/raw";
+	my $txt = "${path}$href/raw";
 	$rv = "\n<a\nhref=\"$mhref\">$more</a> <a\nhref=\"$txt\">raw</a> ";
 	$rv .= html_footer($mime, 0, undef, $ctx);
 
 	if (defined $irt) {
-		unless (defined $anchor) {
-			my $v = PublicInbox::Hval->new_msgid($irt);
+		unless (defined $parent_anchor) {
+			my $v = PublicInbox::Hval->new_msgid($irt, 1);
 			$v = $v->as_href;
-			$anchor = "${path}m/$v/";
-			$seen->{$anchor_idx} = $anchor;
+			$parent_anchor = "${path}$v/";
 		}
-		$rv .= " <a\nhref=\"$anchor\">parent</a>";
+		$rv .= " <a\nhref=\"$parent_anchor\">parent</a>";
 	}
-
 	if ($srch) {
-		$rv .= " <a\nhref=\"${path}t/$href/$t_anchor\">" .
-		       "threadlink</a>";
+		if ($ctx->{flat}) {
+			$rv .= " [<a\nhref=\"${path}$href/t/#u\">threaded</a>" .
+				"|<b>flat</b>]";
+		} else {
+			$rv .= " [<b>threaded</b>|" .
+				"<a\nhref=\"${path}$href/T/#u\">flat</a>]";
+		}
 	}
 
 	$fh->write($rv .= '</pre></td></tr></table>');
@@ -152,32 +161,46 @@ sub thread_html {
 
 sub emit_thread_html {
 	my ($cb, $ctx, $foot, $srch) = @_;
-	my $mid = mid_compress($ctx->{mid});
+	my $mid = $ctx->{mid};
 	my $res = $srch->get_thread($mid);
 	my $msgs = load_results($res);
 	my $nr = scalar @$msgs;
-	return missing_thread($cb) if $nr == 0;
-	my $fh = $cb->([200,['Content-Type'=>'text/html; charset=UTF-8']]);
-	my $th = thread_results($msgs);
+	return missing_thread($cb, $ctx) if $nr == 0;
+	my $flat = $ctx->{flat};
+	my $orig_cb = $cb;
+	my $seen = {};
 	my $state = {
 		ctx => $ctx,
-		seen => {},
+		seen => $seen,
 		root_anchor => anchor_for($mid),
 		anchor_idx => 0,
 	};
-	{
-		require PublicInbox::GitCatFile;
-		my $git = PublicInbox::GitCatFile->new($ctx->{git_dir});
-		thread_entry($fh, $git, $state, $_, 0) for $th->rootset;
+
+	require PublicInbox::GitCatFile;
+	my $git = PublicInbox::GitCatFile->new($ctx->{git_dir});
+	if ($flat) {
+		pre_anchor_entry($seen, $_) for (@$msgs);
+		__thread_entry(\$cb, $git, $state, $_, 0) for (@$msgs);
+	} else {
+		my $th = thread_results($msgs);
+		thread_entry(\$cb, $git, $state, $_, 0) for $th->rootset;
 	}
+	$git = undef;
+	Email::Address->purge_cache;
+
+	# there could be a race due to a message being deleted in git
+	# but still being in the Xapian index:
+	return missing_thread($cb, $ctx) if ($orig_cb eq $cb);
+
 	my $final_anchor = $state->{anchor_idx};
 	my $next = "<a\nid=\"s$final_anchor\">";
 	$next .= $final_anchor == 1 ? 'only message in' : 'end of';
-	$next .= " thread</a>, back to <a\nhref=\"../../\">index</a>\n";
-	$next .= "download: <a\nhref=\"mbox.gz\">mbox.gz</a>\n\n";
-	$fh->write("<hr />" . PRE_WRAP . $next . $foot .
+	$next .= " thread</a>, back to <a\nhref=\"../../\">index</a>";
+	$next .= "\ndownload thread: <a\nhref=\"../t.mbox.gz\">mbox.gz</a>";
+	$next .= " / follow: <a\nhref=\"../t.atom\">Atom feed</a>";
+	$cb->write("<hr />" . PRE_WRAP . $next . "\n\n". $foot .
 		   "</pre></body></html>");
-	$fh->close;
+	$cb->close;
 }
 
 sub index_walk {
@@ -228,7 +251,7 @@ sub multipart_text_as_html {
 	# scan through all parts, looking for displayable text
 	$mime->walk_parts(sub {
 		my ($part) = @_;
-		$rv .= add_text_body($enc, $part, \$part_nr, $full_pfx);
+		$rv .= add_text_body($enc, $part, \$part_nr, $full_pfx, 1);
 	});
 	$mime->body_set('');
 	$rv;
@@ -244,27 +267,56 @@ sub add_filename_line {
 	"$pad " . ascii_html($fn) . " $pad\n";
 }
 
-my $LINK_RE = qr!\b((?:ftp|https?|nntp)://[@\w\+\&\?\.\%\;/#=-]+)!;
+my $LINK_RE = qr!\b((?:ftp|https?|nntp)://
+		 [\@:\w\.-]+/
+		 ?[\@\w\+\&\?\.\%\;/#=-]*)!x;
+
+sub linkify_1 {
+	my ($link_map, $s) = @_;
+	$s =~ s!$LINK_RE!
+		my $url = $1;
+		# salt this, as this could be exploited to show
+		# links in the HTML which don't show up in the raw mail.
+		my $key = sha1_hex($url . $SALT);
+		$link_map->{$key} = $url;
+		'PI-LINK-'. $key;
+	!ge;
+	$s;
+}
+
+sub linkify_2 {
+	my ($link_map, $s) = @_;
 
-sub linkify {
-	# no newlines added here since it'd break the splitting we do
-	# to fold quotes
-	$_[0] =~ s!$LINK_RE!<a\nhref="$1">$1</a>!g;
+	# Added "PI-LINK-" prefix to avoid false-positives on git commits
+	$s =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+		my $key = $1;
+		my $url = $link_map->{$key};
+		if (defined $url) {
+			$url = ascii_html($url);
+			"<a\nhref=\"$url\">$url</a>";
+		} else {
+			# false positive or somebody tried to mess with us
+			$key;
+		}
+	!ge;
+	$s;
 }
 
 sub flush_quote {
-	my ($quot, $n, $part_nr, $full_pfx, $final) = @_;
+	my ($quot, $n, $part_nr, $full_pfx, $final, $do_anchor) = @_;
 
 	if ($full_pfx) {
 		if (!$final && scalar(@$quot) <= MAX_INLINE_QUOTED) {
 			# show quote inline
-			my $rv = join('', map { linkify($_); $_ } @$quot);
+			my %l;
+			my $rv = join('', map { linkify_1(\%l, $_) } @$quot);
 			@$quot = ();
-			return $rv;
+			$rv = ascii_html($rv);
+			return linkify_2(\%l, $rv);
 		}
 
 		# show a short snippet of quoted text and link to full version:
-		@$quot = map { s/^(?:&gt;\s*)+//gm; $_ } @$quot;
+		@$quot = map { s/^(?:>\s*)+//gm; $_ } @$quot;
 		my $cur = join(' ', @$quot);
 		@$quot = split(/\s+/, $cur);
 		$cur = '';
@@ -279,21 +331,24 @@ sub flush_quote {
 		} while (@$quot && length($cur) < MAX_TRUNC_LEN);
 		@$quot = ();
 		$cur =~ s/ \z/ .../s;
+		$cur = ascii_html($cur);
 		my $nr = ++$$n;
 		"&gt; [<a\nhref=\"$full_pfx#q${part_nr}_$nr\">$cur</a>]\n";
 	} else {
 		# show everything in the full version with anchor from
 		# short version (see above)
-		my $nr = ++$$n;
-		my $rv = "<a\nid=q${part_nr}_$nr></a>";
-		$rv .= join('', map { linkify($_); $_ } @$quot);
+		my %l;
+		my $rv .= join('', map { linkify_1(\%l, $_) } @$quot);
 		@$quot = ();
-		$rv;
+		$rv = ascii_html($rv);
+		return linkify_2(\%l, $rv) unless $do_anchor;
+		my $nr = ++$$n;
+		"<a\nid=q${part_nr}_$nr></a>" . linkify_2(\%l, $rv);
 	}
 }
 
 sub add_text_body {
-	my ($enc_msg, $part, $part_nr, $full_pfx) = @_;
+	my ($enc_msg, $part, $part_nr, $full_pfx, $do_anchor) = @_;
 	return '' if $part->subparts;
 
 	my $ct = $part->content_type;
@@ -308,7 +363,6 @@ sub add_text_body {
 	my $s = $part->body;
 	$part->body_set('');
 	$s = $enc->decode($s);
-	$s = ascii_html($s);
 	my @lines = split(/^/m, $s);
 	$s = '';
 
@@ -320,29 +374,34 @@ sub add_text_body {
 
 	my @quot;
 	while (defined(my $cur = shift @lines)) {
-		if ($cur !~ /^&gt;/) {
+		if ($cur !~ /^>/) {
 			# show the previously buffered quote inline
 			if (scalar @quot) {
 				$s .= flush_quote(\@quot, \$n, $$part_nr,
-						  $full_pfx, 0);
+						  $full_pfx, 0, $do_anchor);
 			}
 
 			# regular line, OK
-			linkify($cur);
-			$s .= $cur;
+			my %l;
+			$cur = linkify_1(\%l, $cur);
+			$cur = ascii_html($cur);
+			$s .= linkify_2(\%l, $cur);
 		} else {
 			push @quot, $cur;
 		}
 	}
-	$s .= flush_quote(\@quot, \$n, $$part_nr, $full_pfx, 1) if scalar @quot;
+	if (scalar @quot) {
+		$s .= flush_quote(\@quot, \$n, $$part_nr, $full_pfx, 1,
+				  $do_anchor);
+	}
 	$s .= "\n" unless $s =~ /\n\z/s;
 	++$$part_nr;
 	$s;
 }
 
 sub headers_to_html_header {
-	my ($mime, $full_pfx, $srch) = @_;
-
+	my ($mime, $full_pfx, $ctx) = @_;
+	my $srch = $ctx->{srch} if $ctx;
 	my $rv = "";
 	my @title;
 	my $header_obj = $mime->header_obj;
@@ -360,7 +419,8 @@ sub headers_to_html_header {
 		} elsif ($h eq 'Subject') {
 			$title[0] = $v->as_html;
 			if ($srch) {
-				$rv .= "$h: <a\nhref=\"../../t/$mid_href/\">";
+				my $p = $full_pfx ? '' : '../';
+				$rv .= "$h: <a\nid=\"t\"\nhref=\"${p}t/#u\">";
 				$rv .= $v->as_html . "</a>\n";
 				next;
 			}
@@ -368,14 +428,59 @@ sub headers_to_html_header {
 		$rv .= "$h: " . $v->as_html . "\n";
 
 	}
-
 	$rv .= 'Message-ID: &lt;' . $mid->as_html . '&gt; ';
-	my $raw_ref = $full_pfx ? 'raw' : "../../m/$mid_href/raw";
+	my $raw_ref = $full_pfx ? 'raw' : '../raw';
 	$rv .= "(<a\nhref=\"$raw_ref\">raw</a>)\n";
+	if ($srch) {
+		$rv .= "<a\nhref=\"#r\">References: [see below]</a>\n";
+	} else {
+		$rv .= _parent_headers_nosrch($header_obj);
+	}
+	$rv .= "\n";
 
-	my $irt = $header_obj->header('In-Reply-To');
+	("<html><head><title>".  join(' - ', @title) .
+	 '</title></head><body>' . PRE_WRAP . $rv);
+}
+
+sub thread_inline {
+	my ($dst, $ctx, $cur, $full_pfx) = @_;
+	my $srch = $ctx->{srch};
+	my $mid = mid_clean($cur->header('Message-ID'));
+	my $res = $srch->get_thread($mid);
+	my $nr = $res->{total};
+
+	if ($nr <= 1) {
+		$$dst .= "\n[no followups, yet]\n";
+		return (undef, in_reply_to($cur));
+	}
+	my $upfx = $full_pfx ? '' : '../';
+
+	$$dst .= "\n\n~$nr messages in thread: ".
+		 "(<a\nhref=\"${upfx}t/#u\">expand</a>)\n";
+	my $subj = $srch->subject_path($cur->header('Subject'));
+	my $parent = in_reply_to($cur);
+	my $state = {
+		seen => { $subj => 1 },
+		srch => $srch,
+		cur => $mid,
+		parent_cmp => defined $parent ? $parent : '',
+		parent => $parent,
+		prev_attr => '',
+		prev_level => 0,
+	};
+	for (thread_results(load_results($res))->rootset) {
+		inline_dump($dst, $state, $upfx, $_, 0);
+	}
+	($state->{next_msg}, $state->{parent});
+}
+
+sub _parent_headers_nosrch {
+	my ($header_obj) = @_;
+	my $rv = '';
+
+	my $irt = in_reply_to($header_obj);
 	if (defined $irt) {
-		my $v = PublicInbox::Hval->new_msgid($irt);
+		my $v = PublicInbox::Hval->new_msgid($irt, 1);
 		my $html = $v->as_html;
 		my $href = $v->as_href;
 		$rv .= "In-Reply-To: &lt;";
@@ -386,24 +491,20 @@ sub headers_to_html_header {
 	if ($refs) {
 		# avoid redundant URLs wasting bandwidth
 		my %seen;
-		$seen{mid_clean($irt)} = 1 if defined $irt;
+		$seen{$irt} = 1 if defined $irt;
 		my @refs;
 		my @raw_refs = ($refs =~ /<([^>]+)>/g);
 		foreach my $ref (@raw_refs) {
 			next if $seen{$ref};
 			$seen{$ref} = 1;
-			push @refs, linkify_ref($ref);
+			push @refs, linkify_ref_nosrch($ref);
 		}
 
 		if (@refs) {
 			$rv .= 'References: '. join(' ', @refs) . "\n";
 		}
 	}
-
-	$rv .= "\n";
-
-	("<html><head><title>".  join(' - ', @title) .
-	 '</title></head><body>' . PRE_WRAP . $rv);
+	$rv;
 }
 
 sub html_footer {
@@ -436,33 +537,21 @@ sub html_footer {
 	my $href = "mailto:$to?In-Reply-To=$irt&Cc=${cc}&Subject=$subj";
 
 	my $srch = $ctx->{srch} if $ctx;
-	my $idx = $standalone ? " <a\nhref=\"../../\">index</a>" : '';
+	my $upfx = $full_pfx ? '../' : '../../';
+	my $idx = $standalone ? " <a\nhref=\"$upfx\">index</a>" : '';
 	if ($idx && $srch) {
-		$mid = mid_compress(mid_clean($mid));
-		my $t_anchor = defined $irt ? T_ANCHOR : '';
-		$irt = $mime->header('In-Reply-To');
-		$idx = " <a\nhref=\"../../t/$mid/$t_anchor\">".
-		       "threadlink</a>$idx";
-		my $res = $srch->get_followups($mid);
-		if (my $c = $res->{total}) {
-			my $nr = scalar @{$res->{msgs}};
-			if ($nr < $c) {
-				$c = "$nr of $c followups";
-			} else {
-				$c = $c == 1 ? '1 followup' : "$c followups";
-			}
-			$idx .= "\n$c:\n";
-			$res->{srch} = $srch;
-			thread_followups(\$idx, $mime, $res);
+		my ($next, $p) = thread_inline(\$idx, $ctx, $mime, $full_pfx);
+		if (defined $p) {
+			$p = PublicInbox::Hval->new_oneline($p);
+			$p = $p->as_href;
+			$irt = "<a\nhref=\"$upfx$p/\">parent</a> ";
 		} else {
-			$idx .= "\n(no followups, yet)\n";
+			$irt = ' ' x length('parent ');
 		}
-		if (defined $irt) {
-			$irt = PublicInbox::Hval->new_msgid($irt);
-			$irt = $irt->as_href;
-			$irt = "<a\nhref=\"../$irt/\">parent</a> ";
+		if ($next) {
+			$irt .= "<a\nhref=\"$upfx$next/\">next</a> ";
 		} else {
-			$irt = ' ' x length('parent ');
+			$irt .= '     ';
 		}
 	} else {
 		$irt = '';
@@ -471,8 +560,8 @@ sub html_footer {
 	"$irt<a\nhref=\"" . ascii_html($href) . '">reply</a>' . $idx;
 }
 
-sub linkify_ref {
-	my $v = PublicInbox::Hval->new_msgid($_[0]);
+sub linkify_ref_nosrch {
+	my $v = PublicInbox::Hval->new_msgid($_[0], 1);
 	my $html = $v->as_html;
 	my $href = $v->as_href;
 	"&lt;<a\nhref=\"../$href/\">$html</a>&gt;";
@@ -487,85 +576,77 @@ sub anchor_for {
 	'm' . $id;
 }
 
-sub simple_dump {
-	my ($dst, $root, $node, $level) = @_;
-	return unless $node;
-	# $root = [ undef, \%seen, $srch ];
-	if (my $x = $node->message) {
-		my $f = $x->header('X-PI-From');
-		my $d = $x->header('X-PI-Date');
-		if (defined $f && defined $d) {
-			my $mid = $x->header('Message-ID');
-			my $pfx = '  ' x $level;
-			$$dst .= $pfx;
-
-			# Subject is never undef, this mail was loaded from
-			# our Xapian which would've resulted in '' if it were
-			# really missing (and Filter rejects empty subjects)
-			my $s = $x->header('Subject');
-			my $h = $root->[2]->subject_path($s);
-			if ($root->[1]->{$h}) {
-				$s = undef;
-			} else {
-				$root->[1]->{$h} = 1;
-				$s = PublicInbox::Hval->new($s);
-				$s = $s->as_html;
-			}
-			my $m = PublicInbox::Hval->new_msgid($mid);
-			$f = PublicInbox::Hval->new($f);
-			$d = PublicInbox::Hval->new($d);
-			$m = '../' . $m->as_href . '/';
-			$f = $f->as_html;
-			$d = $d->as_html . ' UTC';
-			if (defined $s) {
-				$$dst .= "` <a\nhref=\"$m\">$s</a>\n" .
-				     "$pfx  by $f @ $d\n";
-			} else {
-				$$dst .= "` <a\nhref=\"$m\">$f @ $d</a>\n";
-			}
-		}
-	}
-	simple_dump($dst, $root, $node->child, $level+1);
-	simple_dump($dst, $root, $node->next, $level);
+sub thread_html_head {
+	my ($cb, $mime) = @_;
+	$$cb = $$cb->([200, ['Content-Type'=> 'text/html; charset=UTF-8']]);
+
+	my $s = PublicInbox::Hval->new_oneline($mime->header('Subject'));
+	$s = $s->as_html;
+	$$cb->write("<html><head><title>$s</title></head><body>");
 }
 
-sub thread_followups {
-	my ($dst, $root, $res) = @_;
-	$root->header_set('X-PI-TS', '0');
-	my $msgs = load_results($res);
-	push @$msgs, $root;
-	my $th = thread_results($msgs);
-	my $srch = $res->{srch};
-	my $subj = $srch->subject_path($root->header('Subject'));
-	my %seen = ($subj => 1);
-	$root = [ undef, \%seen, $srch ];
-	simple_dump($dst, $root, $_, 0) for $th->rootset;
+sub pre_anchor_entry {
+	my ($seen, $mime) = @_;
+	my $id = anchor_for($mime->header('Message-ID'));
+	$seen->{$id} = "#$id"; # save the anchor for children, later
 }
 
-sub thread_html_head {
-	my ($mime) = @_;
-	my $s = PublicInbox::Hval->new_oneline($mime->header('Subject'));
-	$s = $s->as_html;
-	"<html><head><title>$s</title></head><body>";
+sub ghost_parent {
+	my ($upfx, $mid) = @_;
+	# 'subject dummy' is used internally by Mail::Thread
+	return '[no common parent]' if ($mid eq 'subject dummy');
+
+	$mid = PublicInbox::Hval->new_msgid($mid);
+	my $href = $mid->as_href;
+	my $html = $mid->as_html;
+	qq{[parent not found: &lt;<a\nhref="$upfx../$href/">$html</a>&gt;]};
+}
+
+sub __thread_entry {
+	my ($cb, $git, $state, $mime, $level) = @_;
+
+	# lazy load the full message from mini_mime:
+	$mime = eval {
+		my $path = mid2path(mid_clean($mime->header('Message-ID')));
+		Email::MIME->new($git->cat_file('HEAD:'.$path));
+	} or return;
+
+	if ($state->{anchor_idx} == 0) {
+		thread_html_head($cb, $mime, $state);
+	}
+
+	if (my $ghost = delete $state->{ghost}) {
+		# n.b. ghost messages may only be parents, not children
+		foreach my $g (@$ghost) {
+			$$cb->write("<table\nsummary=ghost><tr><td>" .
+				(INDENT x $g->[1]) . "</td><td>" .
+				PRE_WRAP . ghost_parent('../', $g->[0]) .
+				'</pre></td></table>');
+		}
+	}
+	index_entry($$cb, $mime, $level, $state);
+	1;
+}
+
+sub __ghost_entry {
+	my ($state, $node, $level) = @_;
+	my $ghost = $state->{ghost} ||= [];
+	push @$ghost, [ $node->messageid, $level ];
 }
 
 sub thread_entry {
-	my ($fh, $git, $state, $node, $level) = @_;
+	my ($cb, $git, $state, $node, $level) = @_;
 	return unless $node;
 	if (my $mime = $node->message) {
-
-		# lazy load the full message from mini_mime:
-		my $path = mid2path(mid_clean($mime->header('Message-ID')));
-		$mime = eval { Email::MIME->new($git->cat_file("HEAD:$path")) };
-		if ($mime) {
-			if ($state->{anchor_idx} == 0) {
-				$fh->write(thread_html_head($mime));
-			}
-			index_entry($fh, $mime, $level, $state);
+		unless (__thread_entry($cb, $git, $state, $mime, $level)) {
+			__ghost_entry($state, $node, $level);
 		}
+	} else {
+		__ghost_entry($state, $node, $level);
 	}
-	thread_entry($fh, $git, $state, $node->child, $level + 1);
-	thread_entry($fh, $git, $state, $node->next, $level);
+
+	thread_entry($cb, $git, $state, $node->child, $level + 1);
+	thread_entry($cb, $git, $state, $node->next, $level);
 }
 
 sub load_results {
@@ -581,22 +662,217 @@ sub msg_timestamp {
 }
 
 sub thread_results {
-	my ($msgs) = @_;
+	my ($msgs, $nosubject) = @_;
 	require PublicInbox::Thread;
 	my $th = PublicInbox::Thread->new(@$msgs);
-	$th->thread;
 	no warnings 'once';
-	$th->order(*PublicInbox::Thread::sort_ts);
+	$Mail::Thread::nosubject = $nosubject;
+	$th->thread;
+	$th->order(*sort_ts);
 	$th
 }
 
 sub missing_thread {
-	my ($cb) = @_;
-	my $title = 'Thread does not exist';
-	$cb->([404, ['Content-Type' => 'text/html']])->write(<<EOF);
-<html><head><title>$title</title></head><body><pre>$title
-<a href="../../">Return to index</a></pre></body></html>
-EOF
+	my ($cb, $ctx) = @_;
+	require PublicInbox::ExtMsg;
+
+	$cb->(PublicInbox::ExtMsg::ext_msg($ctx))
+}
+
+sub _msg_date {
+	my ($mime) = @_;
+	my $ts = $mime->header('X-PI-TS') || msg_timestamp($mime);
+	POSIX::strftime('%Y-%m-%d %H:%M', gmtime($ts));
+}
+
+sub _inline_header {
+	my ($dst, $state, $upfx, $mime, $level) = @_;
+	my $pfx = INDENT x ($level - 1);
+	my $dot = $level == 0 ? '' : '` ';
+
+	my $cur = $state->{cur};
+	my $mid = mid_clean($mime->header('Message-ID'));
+	my $f = $mime->header('X-PI-From');
+	my $d = _msg_date($mime);
+	$f = PublicInbox::Hval->new($f)->as_html;
+	$d = PublicInbox::Hval->new($d)->as_html;
+	my $attr = "$f @ $d";
+	$state->{first_level} ||= $level;
+	if ($attr ne $state->{prev_attr} || $state->{prev_level} > $level) {
+		$state->{prev_attr} = $attr;
+		$attr = ' - ' . $attr;
+		$attr .= ' UTC' if $level >= $state->{first_level};
+	} else {
+		$attr = '';
+	}
+	$state->{prev_level} = $level;
+
+	if ($cur) {
+		if ($cur eq $mid) {
+			delete $state->{cur};
+			$$dst .= "$pfx$dot<b><a\nid=\"r\"\nhref=\"#t\">".
+				 "[this message]</a></b>$attr\n";
+
+			return;
+		}
+	} else {
+		$state->{next_msg} ||= $mid;
+	}
+
+	# Subject is never undef, this mail was loaded from
+	# our Xapian which would've resulted in '' if it were
+	# really missing (and Filter rejects empty subjects)
+	my $s = $mime->header('Subject');
+	my $h = $state->{srch}->subject_path($s);
+	if ($state->{seen}->{$h}) {
+		$s = undef;
+	} else {
+		$state->{seen}->{$h} = 1;
+		$s = PublicInbox::Hval->new($s);
+		$s = $s->as_html;
+	}
+	my $m = PublicInbox::Hval->new_msgid($mid);
+	$m = $upfx . '../' . $m->as_href . '/';
+	if (defined $s) {
+		$$dst .= "$pfx$dot<a\nhref=\"$m\">$s</a>$attr\n";
+	} else {
+		$$dst .= "$pfx$dot<a\nhref=\"$m\">$f @ $d</a>\n";
+	}
+}
+
+sub inline_dump {
+	my ($dst, $state, $upfx, $node, $level) = @_;
+	return unless $node;
+	if (my $mime = $node->message) {
+		my $mid = mid_clean($mime->header('Message-ID'));
+		if ($mid eq $state->{parent_cmp}) {
+			$state->{parent} = $mid;
+		}
+		_inline_header($dst, $state, $upfx, $mime, $level);
+	} else {
+		my $dot = $level == 0 ? '' : '` ';
+		my $pfx = (INDENT x $level) . $dot;
+		$$dst .= $pfx . ghost_parent($upfx, $node->messageid) . "\n";
+	}
+	inline_dump($dst, $state, $upfx, $node->child, $level+1);
+	inline_dump($dst, $state, $upfx, $node->next, $level);
+}
+
+sub sort_ts {
+	sort {
+		(eval { $a->topmost->message->header('X-PI-TS') } || 0) <=>
+		(eval { $b->topmost->message->header('X-PI-TS') } || 0)
+	} @_;
+}
+
+sub rsort_ts {
+	sort {
+		(eval { $b->topmost->message->header('X-PI-TS') } || 0) <=>
+		(eval { $a->topmost->message->header('X-PI-TS') } || 0)
+	} @_;
+}
+
+# accumulate recent topics if search is supported
+# returns 1 if done, undef if not
+sub add_topic {
+	my ($state, $node, $level) = @_;
+	return unless $node;
+	my $child_adjust = 1;
+
+	if (my $x = $node->message) {
+		$x = $x->header_obj;
+		my ($topic, $subj);
+
+		$subj = $x->header('Subject');
+		$subj = $state->{srch}->subject_normalized($subj);
+		$topic = $subj;
+
+		# kill "[PATCH v2]" etc. for summarization
+		$topic =~ s/\A\s*\[[^\]]+\]\s*//g;
+		$topic = substr($topic, 0, 30);
+
+		if (++$state->{subjs}->{$topic} == 1) {
+			push @{$state->{order}}, [ $level, $subj, $topic ];
+		}
+
+		my $mid = mid_clean($x->header('Message-ID'));
+
+		my $u = $x->header('X-PI-From');
+		my $ts = $x->header('X-PI-TS');
+		$state->{latest}->{$topic} = [ $mid, $u, $ts ];
+	} else {
+		# ghost message, do not bump level
+		$child_adjust = 0;
+	}
+
+	add_topic($state, $node->child, $level + $child_adjust);
+	add_topic($state, $node->next, $level);
+}
+
+sub dump_topics {
+	my ($state) = @_;
+	my $order = $state->{order};
+	my $subjs = $state->{subjs};
+	my $latest = $state->{latest};
+	return "\n[No recent topics]</pre>" unless (scalar @$order);
+	my $dst = '';
+	my $pfx;
+	my $prev = 0;
+	my $prev_attr = '';
+	while (defined(my $info = shift @$order)) {
+		my ($level, $subj, $topic) = @$info;
+		my $n = delete $subjs->{$topic};
+		my ($mid, $u, $ts) = @{delete $latest->{$topic}};
+		$mid = PublicInbox::Hval->new($mid)->as_href;
+		$subj = PublicInbox::Hval->new($subj)->as_html;
+		$u = PublicInbox::Hval->new($u)->as_html;
+		$pfx = INDENT x ($level - 1);
+		my $nl = $level == $prev ? "\n" : '';
+		my $dot = $level == 0 ? '' : '` ';
+		$dst .= "$nl$pfx$dot<a\nhref=\"$mid/t/#u\"><b>$subj</b></a>\n";
+
+		my $attr;
+		$ts = POSIX::strftime('%Y-%m-%d %H:%M', gmtime($ts));
+		if ($n == 1) {
+			$attr = "created by $u @ $ts UTC";
+			$n = "\n";
+		} else {
+			# $n isn't the total number of posts on the topic,
+			# just the number of posts in the current results
+			# window, so leave it unlabeled
+			$attr = "updated by $u @ $ts UTC";
+			$n = " ($n)\n";
+		}
+		if ($level == 0 || $attr ne $prev_attr) {
+			$pfx .= INDENT if $level > 0;
+			$dst .= "$pfx- ". $attr . $n;
+			$prev_attr = $attr;
+		}
+	}
+	$dst .= '</pre>';
+}
+
+sub emit_index_topics {
+	my ($state, $fh) = @_;
+	my $off = $state->{ctx}->{cgi}->param('o');
+	$off = 0 unless defined $off;
+	$state->{order} = [];
+	$state->{subjs} = {};
+	$state->{latest} = {};
+	my $max = 25;
+	my %opts = ( offset => int $off, limit => $max * 4 );
+	while (scalar @{$state->{order}} < $max) {
+		my $res = $state->{srch}->query('', \%opts);
+		my $nr = scalar @{$res->{msgs}} or last;
+
+		for (rsort_ts(thread_results(load_results($res), 1)->rootset)) {
+			add_topic($state, $_, 0);
+		}
+		$opts{offset} += $nr;
+	}
+
+	$fh->write(dump_topics($state));
+	$opts{offset};
 }
 
 1;