lei_mirror: retrieve v2 description properly

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

diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index b6e12b95bdb8ea6a5118574473eda3ff4513838f..9c457fcab054c6a68bdceaea5dce3c803dd05d8b 100644 (file)
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -20,7 +20,7 @@ use PublicInbox::Inbox;
 use PublicInbox::LeiCurl;
 use PublicInbox::OnDestroy;
 
-our %LIVE; # pid => callback
+our $LIVE; # pid => callback
 
 sub _wq_done_wait { # dwaitpid callback (via wq_eof)
        my ($arg, $pid) = @_;
@@ -68,7 +68,7 @@ sub try_scrape {
                        $n => [ URI->new($_), '' ]
                } @v2_urls; # uniq
                clone_v2($self, \%v2_epochs);
-               reap_live() while keys(%LIVE);
+               reap_live() while keys(%$LIVE);
                return;
        }
 
@@ -126,11 +126,11 @@ sub _get_txt_start { # non-fatal
        my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o),
                                        $ft->filename);
        my $jobs = $lei->{opt}->{jobs} // 1;
-       reap_live() while keys(%LIVE) >= $jobs;
+       reap_live() while keys(%$LIVE) >= $jobs;
        $lei->qerr("# @$cmd");
        return if $self->{dry_run};
        $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ];
-       $LIVE{spawn($cmd, undef, $opt)} =
+       $LIVE->{spawn($cmd, undef, $opt)} =
                        [ \&_get_txt_done, $self, $endpoint, $fini ];
 }
 
@@ -237,10 +237,10 @@ sub run_reap {
 sub start_clone {
        my ($self, $cmd, $opt, $fini) = @_;
        my $jobs = $self->{lei}->{opt}->{jobs} // 1;
-       reap_live() while keys(%LIVE) >= $jobs;
+       reap_live() while keys(%$LIVE) >= $jobs;
        $self->{lei}->qerr("# @$cmd");
        return if $self->{dry_run};
-       $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ];
+       $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ]
 }
 
 sub clone_v1 {
@@ -259,12 +259,13 @@ sub clone_v1 {
                push @$cmd, '--reference', "$self->{dst}$ref";
        start_clone($self, $cmd, $opt, $fini);
 
-       _get_txt_start($self, '_/text/config/raw', $fini);
+       $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v1)\z/s and
+               _get_txt_start($self, '_/text/config/raw', $fini);
        my $d = $self->{-ent} ? $self->{-ent}->{description} : undef;
        defined($d) ? ($self->{'txt.description'} = $d) :
                _get_txt_start($self, 'description', $fini);
 
-       reap_live() until ($nohang || !keys(%LIVE)); # for non-manifest clone
+       reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone
 }
 
 sub parse_epochs ($$) {
@@ -345,14 +346,14 @@ sub reap_clone { # async, called via SIGCHLD
        my $cerr = $?;
        $? = 0; # don't let it influence normal exit
        if ($cerr) {
-               kill('TERM', keys %LIVE);
+               kill('TERM', keys %$LIVE);
                $self->{lei}->child_error($cerr, "@$cmd failed");
        }
 }
 
 sub v1_done { # called via OnDestroy
        my ($self) = @_;
-       return if $self->{dry_run};
+       return if $self->{dry_run} || !$LIVE;
        _write_inbox_config($self);
        my $dst = $self->{cur_dst} // $self->{dst};
        if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) {
@@ -375,7 +376,7 @@ sub v1_done { # called via OnDestroy
 
 sub v2_done { # called via OnDestroy
        my ($self) = @_;
-       return if $self->{dry_run};
+       return if $self->{dry_run} || !$LIVE;
        _write_inbox_config($self);
        require PublicInbox::MultiGit;
        my $dst = $self->{cur_dst} // $self->{dst};
@@ -398,7 +399,7 @@ sub v2_done { # called via OnDestroy
 
 sub reap_live {
        my $pid = waitpid(-1, 0) // die "waitpid(-1): $!";
-       if (my $x = delete $LIVE{$pid}) {
+       if (my $x = delete $LIVE->{$pid}) {
                my $cb = shift @$x;
                $cb->(@$x);
        } else {
@@ -445,8 +446,10 @@ failed to extract epoch number from $src
        my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
        my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
 
-       _get_txt_start($task, '_/text/config/raw', $fini);
-       _get_txt_start($self, 'description', $fini);
+       $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and
+               _get_txt_start($task, '_/text/config/raw', $fini);
+
+       _get_txt_start($task, 'description', $fini);
 
        $task->{-locked} = $lk->lock_for_scope($$) if !$self->{dry_run};
        my @cmd = clone_cmd($lei, my $opt = {});
@@ -564,7 +567,7 @@ sub try_manifest {
        my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn);
        my %opt = map { $_ => $lei->{$_} } (0..2);
        my $cerr = run_reap($lei, $cmd, \%opt);
-       local %LIVE;
+       local $LIVE;
        if ($cerr) {
                return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing
                return $lei->child_error($cerr, "@$cmd failed");
@@ -627,7 +630,7 @@ EOM
                }
                clone_all($self, $todo, $m);
        }
-       reap_live() while keys(%LIVE);
+       reap_live() while keys(%$LIVE);
        return if $self->{lei}->{child_error} || $self->{dry_run};
 
        if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude
@@ -649,14 +652,18 @@ sub start_clone_url {
        die "TODO: non-HTTP/HTTPS clone of $self->{src} not supported, yet";
 }
 
-sub do_mirror { # via wq_io_do
+sub do_mirror { # via wq_io_do or public-inbox-clone
        my ($self) = @_;
        my $lei = $self->{lei};
        umask($lei->{client_umask}) if defined $lei->{client_umask};
        eval {
+               my $ic = $lei->{opt}->{'inbox-config'} //= 'always';
+               $ic =~ /\A(?:v1|v2|always|never)\z/s or die <<"";
+--inbox-config must be one of `always', `v2', `v1', or `never'
+
                my $iv = $lei->{opt}->{'inbox-version'};
                if (defined $iv) {
-                       local %LIVE;
+                       local $LIVE;
                        return clone_v1($self) if $iv == 1;
                        return try_scrape($self) if $iv == 2;
                        die "bad --inbox-version=$iv\n";