lei q: support --thread-id=$MSGID || -T $MSGID

This adds support for the "POST /$INBOX/$MSGID/?x=m?q=..."
added last year to support per-thread searches
764035c83 (www: support POST /$INBOX/$MSGID/?x=m&q=, 2023-03-30)
This only supports instances of public-inbox since 764035c83,
but unfortunately there hasn't been a release since then.

diff --git a/Documentation/lei-q.pod b/Documentation/lei-q.pod
index 4476a806dae7659f46b4d6d0e8f62e5a2bfe3e17..79156750e91be12897ec798e5ad157d395dd7db5 100644 (file)
--- a/Documentation/lei-q.pod
+++ b/Documentation/lei-q.pod
@@ -129,6 +129,15 @@ lei/store unless an MUA unflags it!  (Behavior undecided)
 Caveat: C<-tt> only works on locally-indexed messages at the
 moment, and not on remote (HTTP(S)) endpoints.
 
+=item --thread-id=MSGID
+
+=item -T MSGID
+
+Only search messages in the same thread as the given Message-ID.
+
+For HTTP(S) externals, this only works on instances running
+public-inbox 2.0+ (UNRELEASED).
+
 =item --jobs=QUERY_WORKERS[,WRITE_WORKERS]
 
 =item --jobs=,WRITE_WORKERS

diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm
index 7c31ab43ab3610fccae78b85d4d5b65277c82316..06592358510abf53bc53c86277f47f6ad6847878 100644 (file)
--- a/lib/PublicInbox/LEI.pm
+++ b/lib/PublicInbox/LEI.pm
@@ -177,6 +177,7 @@ our %CMD = ( # sorted in order of importance/use:
        'stdin|', # /|\z/ must be first for lone dash
        @lxs_opt, @net_opt,
        qw(save! output|mfolder|o=s format|f=s dedupe|d=s threads|t+
+       thread-id|T=s
        sort|s=s reverse|r offset=i pretty jobs|j=s globoff|g augment|a
        import-before! lock=s@ rsyncable alert=s@ mua=s verbose|v+
        shared color! mail-sync!), @c_opt, opt_dash('limit|n=i', '[0-9]+') ],

diff --git a/lib/PublicInbox/LeiXSearch.pm b/lib/PublicInbox/LeiXSearch.pm
index fc95d401e23c921518d8c4a048cdc670b96c7d9a..d4f34733a07b6bae8552c0d1d5b16148beb93355 100644 (file)
--- a/lib/PublicInbox/LeiXSearch.pm
+++ b/lib/PublicInbox/LeiXSearch.pm
@@ -13,7 +13,7 @@ use File::Temp 0.19 (); # 0.19 for ->newdir
 use File::Spec ();
 use PublicInbox::Search qw(xap_terms);
 use PublicInbox::Spawn qw(popen_rd popen_wr which);
-use PublicInbox::MID qw(mids);
+use PublicInbox::MID qw(mids mid_escape);
 use PublicInbox::Smsg;
 use PublicInbox::Eml;
 use PublicInbox::LEI;
@@ -160,6 +160,8 @@ sub query_one_mset { # for --threads and l2m w/o sort
        my $can_kw = !!$ibxish->can('msg_keywords');
        my $threads = $lei->{opt}->{threads} // 0;
        my $fl = $threads > 1 ? 1 : undef;
+       my $mid = $lei->{opt}->{'thread-id'};
+       $mo->{threadid} = $over->mid2tid($mid) if defined $mid;
        my $lss = $lei->{lss};
        my $maxk = "external.$dir.maxuid"; # max of previous, so our min
        my $min = $lss ? ($lss->{-cfg}->{$maxk} // 0) : 0;
@@ -339,6 +341,12 @@ print STDERR $_;
        push @$curl, '-s', '-d', '';
        my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
        $self->{import_sto} = $lei->{sto} if $lei->{opt}->{'import-remote'};
+       if (defined(my $mid = $opt->{'thread-id'})) {
+               $mid = mid_escape($mid);
+               for my $uri (@$uris) {
+                       $uri->path($uri->path.$mid.'/');
+               }
+       }
        for my $uri (@$uris) {
                $lei->{-current_url} = $uri->as_string;
                my $start = time;
@@ -459,7 +467,9 @@ sub concurrency {
 sub start_query ($$) { # always runs in main (lei-daemon) process
        my ($self, $lei) = @_;
        local $PublicInbox::LEI::current_lei = $lei;
-       if ($self->{opt_threads} || ($lei->{l2m} && !$self->{opt_sort})) {
+       if ($lei->{opt}->{threads} ||
+                       defined($lei->{opt}->{'thread-id'}) ||
+                       ($lei->{l2m} && !$lei->{opt}->{'sort'})) {
                for my $ibxish (locals($self)) {
                        $self->wq_io_do('query_one_mset', [], $ibxish);
                }
@@ -546,8 +556,6 @@ sub do_query {
        my $op_c = delete $lei->{pkt_op_c};
        delete $lei->{pkt_op_p};
        @$end = ();
-       $self->{opt_threads} = $lei->{opt}->{threads};
-       $self->{opt_sort} = $lei->{opt}->{'sort'};
        $self->{-do_lcat} = !!(delete $lei->{lcat_todo});
        if ($l2m) {
                $l2m->net_merge_all_done($lei) unless $lei->{auth};

diff --git a/t/psgi_v2.t b/t/psgi_v2.t
index 54faae9b4c60801ddf23e57e5497dddfa1d307c5..d5c328f0f0fcee4ea0c16062aea3c32b0dcc529e 100644 (file)
--- a/t/psgi_v2.t
+++ b/t/psgi_v2.t
@@ -101,6 +101,19 @@ EOM
        }
 };
 
+my $test_lei_q_threadid = sub {
+       my ($u) = @_;
+       test_lei(sub {
+               lei_ok qw(q -f text --only), $u, qw(-T t@1 s:unrelated);
+               is $lei_out, '', 'no results on unrelated thread';
+               lei_ok qw(q -f text --only), $u, qw(-T t@1 dt:19931002000300..);
+               my @m = ($lei_out =~ m!^Message-ID: <([^>]+)>\n!gms);
+               is_deeply \@m, ['t@3'], 'got expected result from -T MSGID';
+       });
+};
+
+$test_lei_q_threadid->($m2t->{inboxdir});
+
 my $cfgpath = "$ibx->{inboxdir}/pi_config";
 {
        open my $fh, '>', $cfgpath or BAIL_OUT $!;
@@ -374,6 +387,9 @@ my $client3 = sub {
 
        $res = $cb->(POST("/m2t/t\@1/?q=s:unrelated&x=m"));
        is($res->code, 404, '404 on cross-thread search');
+
+       my $rmt = $ENV{PLACK_TEST_EXTERNALSERVER_URI};
+       $rmt and $test_lei_q_threadid->("$rmt/m2t/");
 };
 test_psgi(sub { $www->call(@_) }, $client3);
 test_httpd($env, $client3, 4);