From 764035c83fe1aff1a0dda778a47b0c9751e74d34 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Thu, 30 Mar 2023 11:29:51 +0000
Subject: www: support POST /$INBOX/$MSGID/?x=m&q=

This allows filtering the contents of any existing thread using
a search query.  It uses the existing THREADID column in Xapian
so we can internally add a Xapian OP_FILTER to the results.

This new functionality is orthogonal to the existing `t=1'
parameter which gives mairix-style thread expansion.  It doesn't
make sense to use `t=1' with this functionality, but it's not
disallowed, either.

The indentation change in Over->next_by_mid is to ensure
DBI->prepare_cached can share across both ->next_by_mid
and ->mid2tid.

I also noticed the existing regex for `POST /$INBOX/?x=m&q=' was
allowing extra characters.  With an added \z, it's now as strict
was originally intended and AFAIK nothing was generating invalid
URLs for it

Reported-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
Link: https://public-inbox.org/meta/aaniyhk7wfm4e6m5mbukcrhevzoc6ftctyrfwvmz4fkykwwtlj@mverfng6ytas/T/
---
 lib/PublicInbox/Mbox.pm   |  5 +++++
 lib/PublicInbox/Over.pm   | 24 +++++++++++++++++++++++-
 lib/PublicInbox/Search.pm |  6 ++++++
 lib/PublicInbox/WWW.pm    |  4 +++-
 4 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'lib/PublicInbox')

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 18db9d38..e1abf7ec 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -229,6 +229,11 @@ sub mbox_all {
 		return PublicInbox::WWW::need($ctx, 'Overview');
 
 	my $qopts = $ctx->{qopts} = { relevance => -2 }; # ORDER BY docid DESC
+
+	# {threadid} limits results to a given thread
+	# {threads} collapses results from messages in the same thread,
+	# allowing us to use ->expand_thread w/o duplicates in our own code
+	$qopts->{threadid} = $over->mid2tid($ctx->{mid}) if defined($ctx->{mid});
 	$qopts->{threads} = 1 if $q->{t};
 	$srch->query_approxidate($ctx->{ibx}->git, $q_string);
 	my $mset = $srch->mset($q_string, $qopts);
diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index d6409b2a..82034b30 100644
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -282,13 +282,35 @@ SELECT eidx_key FROM inboxes WHERE ibx_id = ?
 	$rows;
 }
 
+sub mid2tid {
+	my ($self, $mid) = @_;
+	my $dbh = dbh($self);
+
+	my $sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT id FROM msgid WHERE mid = ? LIMIT 1
+
+	$sth->execute($mid);
+	my $id = $sth->fetchrow_array or return;
+	$sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT num FROM id2num WHERE id = ? AND num > ?
+ORDER BY num ASC LIMIT 1
+
+	$sth->execute($id, 0);
+	my $num = $sth->fetchrow_array or return;
+	$sth = $dbh->prepare(<<'');
+SELECT tid FROM over WHERE num = ? LIMIT 1
+
+	$sth->execute($num);
+	$sth->fetchrow_array;
+}
+
 sub next_by_mid {
 	my ($self, $mid, $id, $prev) = @_;
 	my $dbh = dbh($self);
 
 	unless (defined $$id) {
 		my $sth = $dbh->prepare_cached(<<'', undef, 1);
-	SELECT id FROM msgid WHERE mid = ? LIMIT 1
+SELECT id FROM msgid WHERE mid = ? LIMIT 1
 
 		$sth->execute($mid);
 		$$id = $sth->fetchrow_array;
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 5133a3b7..6c3d9f93 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -386,6 +386,12 @@ sub mset {
 					sortable_serialise($uid_range->[1]));
 		$query = $X{Query}->new(OP_FILTER(), $query, $range);
 	}
+	if (defined(my $tid = $opt->{threadid})) {
+		$tid = sortable_serialise($tid);
+		$query = $X{Query}->new(OP_FILTER(), $query,
+				$X{Query}->new(OP_VALUE_RANGE(), THREADID, $tid, $tid));
+	}
+
 	my $xdb = xdb($self);
 	my $enq = $X{Enquire}->new($xdb);
 	$enq->set_query($query);
diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 9ffcb879..a8f1ad17 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -68,7 +68,9 @@ sub call {
 			my ($idx, $fn) = ($3, $4);
 			return invalid_inbox_mid($ctx, $1, $2) ||
 				get_attach($ctx, $idx, $fn);
-		} elsif ($path_info =~ m!$INBOX_RE/!o) {
+		} elsif ($path_info =~ m!$INBOX_RE/$MID_RE/\z!o) {
+			return invalid_inbox_mid($ctx, $1, $2) || mbox_results($ctx);
+		} elsif ($path_info =~ m!$INBOX_RE/\z!o) {
 			return invalid_inbox($ctx, $1) || mbox_results($ctx);
 		}
 	}
-- 
cgit v1.2.3-24-ge0c7