use v5.10.1;
use parent qw(PublicInbox::IPC);
use PublicInbox::Config;
-use PublicInbox::AutoReap;
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);
# e.g.: git -c http.proxy=socks5h://127.0.0.1:9050
push(@cmd, '-c', $_) for @{$lei->{opt}->{c} // []};
push @cmd, qw(clone --mirror);
- push @cmd, '-q' if $lei->{opt}->{quiet};
+ push @cmd, '-q' if $lei->{opt}->{quiet} ||
+ ($lei->{opt}->{jobs} // 1) > 1;
push @cmd, '-v' if $lei->{opt}->{verbose};
# XXX any other options to support?
# --reference is tricky with multiple epochs...
}
sub _get_txt_start { # non-fatal
- my ($self, $endpoint, $file, $mode) = @_;
+ my ($self, $endpoint, $fini) = @_;
my $uri = URI->new($self->{cur_src} // $self->{src});
my $lei = $self->{lei};
my $path = $uri->path;
chop($path) eq '/' or die "BUG: $uri not canonicalized";
$uri->path("$path/$endpoint");
- my $dst = $self->{cur_dst} // $self->{dst};
- my $ft = File::Temp->new(TEMPLATE => "$file-XXXX", DIR => $dst);
+ my $f = (split(m!/!, $endpoint))[-1];
+ my $ft = File::Temp->new(TEMPLATE => "$f-XXXX", TMPDIR => 1);
my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} };
- my $cmd = $self->{curl}->for_uri($lei, $uri,
- qw(--compressed -R -o), $ft->filename);
- $self->{-get_txt} = [ $ft, $cmd, $uri, $file, $mode ];
+ my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o),
+ $ft->filename);
+ $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ];
+ my $jobs = $lei->{opt}->{jobs} // 1;
+ reap_live() while keys(%LIVE) >= $jobs;
$lei->qerr("# @$cmd");
- spawn($cmd, undef, $opt);
+ $LIVE{spawn($cmd, undef, $opt)} =
+ [ \&_get_txt_done, $self, $endpoint, $fini ];
}
-sub _get_txt_done {
- my ($self) = @_;
- my ($ft, $cmd, $uri, $file, $mode) = @{delete $self->{-get_txt}};
+sub _get_txt_done { # returns true on error (non-fatal), undef on success
+ my ($self, $endpoint) = @_;
+ my ($fh, $cmd, $uri) = @{delete $self->{"-get_txt.$endpoint"}};
my $cerr = $?;
- $? = 0;
- return "$uri missing" if ($cerr >> 8) == 22;
- return "# @$cmd failed (non-fatal)" if $cerr;
- my $dst = $self->{cur_dst} // $self->{dst};
- ft_rename($ft, "$dst/$file", $mode);
+ $? = 0; # don't influence normal lei exit
+ return warn("$uri missing\n") if ($cerr >> 8) == 22;
+ return warn("# @$cmd failed (non-fatal)\n") if $cerr;
+ seek($fh, SEEK_SET, 0) or die "seek: $!";
+ $self->{"mtime.$endpoint"} = (stat($fh))[9];
+ local $/;
+ $self->{"txt.$endpoint"} = <$fh>;
undef; # success
}
-# tries the relatively new /$INBOX/_/text/config/raw endpoint
-sub _try_config_start {
- my ($self) = @_;
- my $dst = $self->{cur_dst} // $self->{dst};
- if (!-d $dst || !mkdir($dst)) {
- require File::Path;
- File::Path::mkpath($dst);
- -d $dst or die "mkpath($dst): $!\n";
- }
- _get_txt_start($self, qw(_/text/config/raw inbox.config.example), 0444);
-}
-
-sub _try_config_done {
+sub _write_inbox_config {
my ($self) = @_;
- my $err = _get_txt_done($self);
- return warn($err, "\n") if $err;
+ my $buf = delete($self->{'txt._/text/config/raw'}) // return;
my $dst = $self->{cur_dst} // $self->{dst};
my $f = "$dst/inbox.config.example";
+ 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'};
+ $fh->flush or die "flush($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}})) {
}
}
-sub _get_txt { # non-fatal temporary compat function
- waitpid(_get_txt_start(@_), 0) > 0 or die "waitpid: $!";
- _get_txt_done($_[0]);
-}
-
-# tries the relatively new /$INBOX/_/text/config/raw endpoint
-sub _try_config { # temporary compat function
- waitpid(_try_config_start($_[0]), 0) > 0 or die "waitpid: $!";
- _try_config_done($_[0]);
-}
-
sub set_description ($) {
my ($self) = @_;
my $dst = $self->{cur_dst} // $self->{dst};
my $f = "$dst/description";
open my $fh, '+>>', $f or die "open($f): $!";
seek($fh, 0, SEEK_SET) or die "seek($f): $!";
- chomp(my $d = do { local $/; <$fh> } // die "read($f): $!");
- if ($d eq '($INBOX_DIR/description missing)' ||
- $d =~ /^Unnamed repository/ || $d !~ /\S/) {
- seek($fh, 0, SEEK_SET) or die "seek($f): $!";
- truncate($fh, 0) or die "truncate($f): $!";
- my $src = $self->{cur_src} // $self->{src};
- print $fh "mirror of $src\n" or die "print($f): $!";
- close $fh or die "close($f): $!";
+ my $d = do { local $/; <$fh> } // die "read($f): $!";
+ my $orig = $d;
+ while (defined($d) && ($d =~ m!^\(\$INBOX_DIR/description missing\)! ||
+ $d =~ /^Unnamed repository/ || $d !~ /\S/)) {
+ $d = delete($self->{'txt.description'});
}
+ $d //= 'mirror of '.($self->{cur_src} // $self->{src})."\n";
+ return if $d eq $orig;
+ seek($fh, 0, SEEK_SET) or die "seek($f): $!";
+ truncate($fh, 0) or die "truncate($f): $!";
+ print $fh $d or die "print($f): $!";
+ close $fh or die "close($f): $!";
}
sub index_cloned_inbox {
my ($self, $iv) = @_;
my $lei = $self->{lei};
- my $err = _get_txt($self, qw(description description), 0666);
- warn($err, "\n") if $err; # non fatal
eval { set_description($self) };
warn $@ if $@;
sub run_reap {
my ($lei, $cmd, $opt) = @_;
$lei->qerr("# @$cmd");
- my $ar = PublicInbox::AutoReap->new(spawn($cmd, undef, $opt));
- $ar->join;
+ waitpid(spawn($cmd, undef, $opt), 0) // die "waitpid: $!";
my $ret = $?;
$? = 0; # don't let it influence normal exit
$ret;
}
+sub start_clone {
+ my ($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) = @_;
+ my ($self, $nohang) = @_;
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
my $uri = URI->new($self->{cur_src} // $self->{src});
die "$uri is a v1 inbox, --epoch is not supported\n";
my $pfx = $curl->torsocks($lei, $uri) or return;
my $dst = $self->{cur_dst} // $self->{dst};
- my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}),
- $uri->as_string, $dst ];
- my $cerr = run_reap($lei, $cmd, $opt);
- return $lei->child_error($cerr, "@$cmd failed") if $cerr;
- _try_config($self);
- write_makefile($dst, 1);
- index_cloned_inbox($self, 1);
+ my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self);
+ my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ];
+ start_clone($self, $cmd, $opt, $fini);
+
+ _get_txt_start($self, '_/text/config/raw', $fini);
+ my $d = $self->{-ent} ? $self->{-ent}->{description} : undef;
+ defined($d) ? ($self->{'txt.description'} = $d) :
+ _get_txt_start($self, 'description', $fini);
+
+ reap_live() until ($nohang || !keys(%LIVE)); # for non-manifest clone
}
sub parse_epochs ($$) {
; 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, "@$cmd failed");
}
}
+sub v1_done { # called via OnDestroy
+ my ($self) = @_;
+ _write_inbox_config($self);
+ write_makefile($self->{cur_dst} // $self->{dst}, 1);
+ index_cloned_inbox($self, 1);
+}
+
sub v2_done { # called via OnDestroy
my ($self) = @_;
+ _write_inbox_config($self);
require PublicInbox::MultiGit;
my $dst = $self->{cur_dst} // $self->{dst};
my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
}
# filter out the epochs we skipped
$self->{-culled_manifest} = 1 if delete(@$m{@skip});
+
+ -d $dst || File::Path::mkpath($dst);
my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
- $LIVE{_try_config_start($task)} = [ \&_try_config_done, $task, $fini ];
+
+ _get_txt_start($task, '_/text/config/raw', $fini);
+ _get_txt_start($self, 'description', $fini);
+
$task->{-locked} = $lk->lock_for_scope($$);
my @cmd = clone_cmd($lei, my $opt = {});
- my $jobs = $self->{lei}->{opt}->{jobs} // 2;
- 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 ($$$) {
$uri->path($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 = $ft->filename;
}
my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m);
return $lei->child_error(1, $multi) if !ref($multi);
- my $jobs = $self->{lei}->{opt}->{jobs} // 2;
if (my $v2 = delete $multi->{v2}) {
for my $name (sort keys %$v2) {
my $epochs = delete $v2->{$name};
E: `$self->{cur_dst}' must not contain newline
EOM
clone_v2($self, \%v2_epochs, $m);
- reap_live() while keys(%LIVE) >= $jobs;
return if $self->{lei}->{child_error};
}
}
chop($p) if substr($p, -1, 1) eq '/';
$uri->path($p);
for my $name (@$v1) {
- local $self->{cur_src} = "$uri";
- local $self->{cur_dst} = $self->{dst};
+ 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) {
- $self->{cur_dst} .= $name;
- $self->{cur_src} .= $name;
+ $task->{cur_dst} .= $name;
+ $task->{cur_src} .= $name;
}
- index($self->{cur_dst}, "\n") >= 0 and die <<EOM;
-E: `$self->{cur_dst}' must not contain newline
+ index($task->{cur_dst}, "\n") >= 0 and die <<EOM;
+E: `$task->{cur_dst}' must not contain newline
EOM
- $self->{cur_src} .= '/';
- clone_v1($self, 1);
+ $task->{cur_src} .= '/';
+ clone_v1($task, 1);
}
}
reap_live() while keys(%LIVE);
+ return if $self->{lei}->{child_error};
+
if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude
# write the smaller manifest if epochs were skipped so
# users won't have to delete manifest if they +w an