lei_mirror: load File::Path unconditionally

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

diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index da8987bec1c526e7b08a293029d4c9b67002a373..1ca603b3003b1b06ae4a4328e0e265deb97f6d2f 100644 (file)
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -10,6 +10,7 @@ use PublicInbox::Config;
 use IO::Uncompress::Gunzip qw(gunzip $GunzipError);
 use IO::Compress::Gzip qw(gzip $GzipError);
 use PublicInbox::Spawn qw(popen_rd spawn);
+use File::Path ();
 use File::Temp ();
 use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY);
 use Carp qw(croak);
@@ -118,9 +119,9 @@ sub _get_txt_start { # non-fatal
        my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o),
                                        $ft->filename);
        $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ];
-       $lei->qerr("# @$cmd");
        my $jobs = $lei->{opt}->{jobs} // 1;
        reap_live() while keys(%LIVE) >= $jobs;
+       $lei->qerr("# @$cmd");
        $LIVE{spawn($cmd, undef, $opt)} =
                        [ \&_get_txt_done, $self, $endpoint, $fini ];
 }
@@ -147,9 +148,11 @@ sub _write_inbox_config {
        open my $fh, '>', $f or die "open($f): $!";
        print $fh $buf or die "print: $!";
        chmod(0444 & ~umask, $fh) or die "chmod($f): $!";
-       my $mtime = delete $self->{'mtime._/text/config/raw'} // die 'BUG: no mtime';
+       my $mtime = delete $self->{'mtime._/text/config/raw'};
        $fh->flush or die "flush($f): $!";
-       utime($mtime, $mtime, $fh) or die "utime($f): $!";
+       if (defined $mtime) {
+               utime($mtime, $mtime, $fh) or die "utime($f): $!";
+       }
        my $cfg = PublicInbox::Config->git_config_dump($f, $self->{lei}->{2});
        my $ibx = $self->{ibx} = {};
        for my $sec (grep(/\Apublicinbox\./, @{$cfg->{-section_order}})) {
@@ -221,6 +224,14 @@ sub run_reap {
        $ret;
 }
 
+sub start_clone {
+       my ($self, $cmd, $opt, $fini) = @_;
+       my $jobs = $self->{lei}->{opt}->{jobs} // 1;
+       reap_live() while keys(%LIVE) >= $jobs;
+       $self->{lei}->qerr("# @$cmd");
+       $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ];
+}
+
 sub clone_v1 {
        my ($self, $nohang) = @_;
        my $lei = $self->{lei};
@@ -231,15 +242,15 @@ sub clone_v1 {
        my $pfx = $curl->torsocks($lei, $uri) or return;
        my $dst = $self->{cur_dst} // $self->{dst};
        my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self);
-       my $jobs = $self->{lei}->{opt}->{jobs} // 1;
        my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ];
-       $lei->qerr("# @$cmd");
-       $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $lei, $cmd, $fini ];
-       reap_live() while keys(%LIVE) >= $jobs;
+       start_clone($self, $cmd, $opt, $fini);
 
        _get_txt_start($self, '_/text/config/raw', $fini);
-       _get_txt_start($self, 'description', $fini);
-       reap_live() until ($nohang || !keys(%LIVE));
+       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
 }
 
 sub parse_epochs ($$) {
@@ -298,17 +309,18 @@ sub init_placeholder ($$) {
 
 ; This git epoch was created read-only and "public-inbox-fetch"
 ; will not fetch updates for it unless write permission is added.
+; Hint: chmod +w $edst
 EOM
        close $fh or die "close:($f): $!";
 }
 
 sub reap_clone { # async, called via SIGCHLD
-       my ($lei, $cmd) = @_;
+       my ($self, $cmd) = @_;
        my $cerr = $?;
        $? = 0; # don't let it influence normal exit
        if ($cerr) {
                kill('TERM', keys %LIVE);
-               $lei->child_error($cerr, "@$cmd failed");
+               $self->{lei}->child_error($cerr, "@$cmd failed");
        }
 }
 
@@ -376,11 +388,7 @@ failed to extract epoch number from $src
        # filter out the epochs we skipped
        $self->{-culled_manifest} = 1 if delete(@$m{@skip});
 
-       if (!-d $dst || !mkdir($dst)) {
-               require File::Path;
-               File::Path::mkpath($dst);
-               -d $dst or die "mkpath($dst): $!\n";
-       }
+       -d $dst || File::Path::mkpath($dst);
        my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
        my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
 
@@ -389,17 +397,10 @@ failed to extract epoch number from $src
 
        $task->{-locked} = $lk->lock_for_scope($$);
        my @cmd = clone_cmd($lei, my $opt = {});
-       my $jobs = $self->{lei}->{opt}->{jobs} // 1;
-       do {
-               reap_live() while keys(%LIVE) >= $jobs;
-               while (keys(%LIVE) < $jobs && @src_edst &&
-                               !$lei->{child_error}) {
-                       my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
-                       $lei->qerr("# @$cmd");
-                       $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone,
-                                                       $lei, $cmd, $fini ];
-               }
-       } while (@src_edst && !$lei->{child_error});
+       while (@src_edst && !$lei->{child_error}) {
+               my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
+               start_clone($self, $cmd, $opt, $fini);
+       }
 }
 
 sub decode_manifest ($$$) {
@@ -482,6 +483,7 @@ sub try_manifest {
        $uri->path($path . '/manifest.js.gz');
        my $pdir = $lei->rel2abs($self->{dst});
        $pdir =~ s!/[^/]+/?\z!!;
+       -d $pdir || File::Path::mkpath($pdir);
        my $ft = File::Temp->new(TEMPLATE => 'm-XXXX',
                                UNLINK => 1, DIR => $pdir, SUFFIX => '.tmp');
        my $fn = $ft->filename;
@@ -502,7 +504,6 @@ sub try_manifest {
        }
        my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m);
        return $lei->child_error(1, $multi) if !ref($multi);
-       my $jobs = $self->{lei}->{opt}->{jobs} // 1;
        if (my $v2 = delete $multi->{v2}) {
                for my $name (sort keys %$v2) {
                        my $epochs = delete $v2->{$name};
@@ -525,7 +526,6 @@ sub try_manifest {
 E: `$self->{cur_dst}' must not contain newline
 EOM
                        clone_v2($self, \%v2_epochs, $m);
-                       reap_live() while keys(%LIVE) >= $jobs;
                        return if $self->{lei}->{child_error};
                }
        }
@@ -534,10 +534,11 @@ EOM
                chop($p) if substr($p, -1, 1) eq '/';
                $uri->path($p);
                for my $name (@$v1) {
-                       reap_live() while keys(%LIVE) >= $jobs;
                        return if $self->{lei}->{child_error};
 
                        my $task = bless { %$self }, __PACKAGE__;
+                       $task->{-ent} = $m->{$name} //
+                                       die("BUG: no `$name' in manifest");
                        $task->{cur_src} = "$uri";
                        $task->{cur_dst} = $task->{dst};
                        if ($n > 1) {