lei: support remote externals

[public-inbox.git] / lib / PublicInbox / LeiOverview.pm

diff --git a/lib/PublicInbox/LeiOverview.pm b/lib/PublicInbox/LeiOverview.pm
index 8781259addfb8bb33440dc7c337f4f1f15a59a7a..49538a609c577a4cab5b7a2e3327040d6f131d41 100644 (file)
--- a/lib/PublicInbox/LeiOverview.pm
+++ b/lib/PublicInbox/LeiOverview.pm
@@ -38,6 +38,19 @@ sub ovv_out_lk_cancel ($) {
                unlink(delete($self->{lock_path}));
 }
 
+sub detect_fmt ($$) {
+       my ($lei, $dst) = @_;
+       if ($dst =~ m!\A([:/]+://)!) {
+               $lei->fail("$1 support not implemented, yet\n");
+       } elsif (!-e $dst || -d _) {
+               'maildir'; # the default TODO: MH?
+       } elsif (-f _ || -p _) {
+               $lei->fail("unable to determine mbox family of $dst\n");
+       } else {
+               $lei->fail("unable to determine format of $dst\n");
+       }
+}
+
 sub new {
        my ($class, $lei) = @_;
        my $opt = $lei->{opt};
@@ -54,7 +67,7 @@ sub new {
 
        }
        $fmt //= 'json' if $dst eq '/dev/stdout';
-       $fmt //= 'maildir';
+       $fmt //= detect_fmt($lei, $dst) or return;
 
        if (index($dst, '://') < 0) { # not a URL, so assume path
                 $dst = File::Spec->canonpath($dst);
@@ -82,7 +95,8 @@ sub new {
        if (!$json) {
                # default to the cheapest sort since MUA usually resorts
                $lei->{opt}->{'sort'} //= 'docid' if $dst ne '/dev/stdout';
-               $lei->{l2m} = PublicInbox::LeiToMail->new($lei);
+               $lei->{l2m} = eval { PublicInbox::LeiToMail->new($lei) };
+               return $lei->fail($@) if $@;
        }
        $lei->{dedupe} //= PublicInbox::LeiDedupe->new($lei);
        $self;
@@ -121,11 +135,9 @@ sub _unbless_smsg {
        delete @$smsg{qw(lines bytes num tid)};
        $smsg->{rt} = _iso8601(delete $smsg->{ts}); # JMAP receivedAt
        $smsg->{dt} = _iso8601(delete $smsg->{ds}); # JMAP UTCDate
-       $smsg->{relevance} = get_pct($mitem) if $mitem;
-
+       $smsg->{pct} = get_pct($mitem) if $mitem;
        if (my $r = delete $smsg->{references}) {
-               $smsg->{refs} = [
-                               map { "<$_>" } ($r =~ m/$MID_EXTRACT/go) ];
+               $smsg->{refs} = [ map { "<$_>" } ($r =~ m/$MID_EXTRACT/go) ];
        }
        if (my $m = delete($smsg->{mid})) {
                $smsg->{'m'} = "<$m>";
@@ -197,7 +209,15 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
                $json->ascii(1) if $lei->{opt}->{ascii};
        }
        my $l2m = $lei->{l2m};
-       if ($l2m && $l2m->{-wq_s1}) {
+       if ($l2m && $ibxish->can('scheme')) { # remote https?:// mboxrd
+               delete $l2m->{-wq_s1};
+               my $g2m = $l2m->can('git_to_mail');
+               my $wcb = $l2m->write_cb($lei);
+               sub {
+                       my ($smsg, undef, $eml) = @_; # no mitem in $_[1]
+                       $wcb->(undef, $smsg, $eml);
+               };
+       } elsif ($l2m && $l2m->{-wq_s1}) {
                my ($lei_ipc, @io) = $lei->atfork_parent_wq($l2m);
                # n.b. $io[0] = qry_status_wr, $io[1] = mbox|stdout,
                # $io[4] becomes a notification pipe that triggers EOF
@@ -212,9 +232,9 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
                my $git_dir = $git->{git_dir};
                sub {
                        my ($smsg, $mitem) = @_;
-                       my $kw = []; # TODO get from mitem
-                       $l2m->wq_do('write_mail', \@io, $git_dir,
-                                       $smsg->{blob}, $lei_ipc, $kw)
+                       $smsg->{pct} = get_pct($mitem) if $mitem;
+                       $l2m->wq_do('write_mail', \@io, $git_dir, $smsg,
+                                       $lei_ipc);
                }
        } elsif ($l2m) {
                my $wcb = $l2m->write_cb($lei);
@@ -223,8 +243,8 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
                my $g2m = $l2m->can('git_to_mail');
                sub {
                        my ($smsg, $mitem) = @_;
-                       my $kw = []; # TODO get from mitem
-                       $git->cat_async($smsg->{blob}, $g2m, [ $wcb, $kw ]);
+                       $smsg->{pct} = get_pct($mitem) if $mitem;
+                       $git->cat_async($smsg->{blob}, $g2m, [ $wcb, $smsg ]);
                };
        } elsif ($self->{fmt} =~ /\A(concat)?json\z/ && $lei->{opt}->{pretty}) {
                my $EOR = ($1//'') eq 'concat' ? "\n}" : "\n},";
@@ -254,7 +274,6 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
                $lei->{ovv_buf} = \(my $buf = '');
                sub {
                        my ($smsg, $mitem) = @_;
-                       delete @$smsg{qw(tid num)};
                        $buf .= $json->encode(_unbless_smsg(@_)) . $ORS;
                        if (length($buf) > 65536) {
                                my $lk = $self->lock_for_scope;