use PublicInbox::Spawn qw(popen_rd spawn run_die);
use File::Path ();
use File::Temp ();
+use File::Spec ();
use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY);
use Carp qw(croak);
use URI;
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) = @_;
$n => [ URI->new($_), '' ]
} @v2_urls; # uniq
clone_v2($self, \%v2_epochs);
- reap_live() while keys(%LIVE);
+ reap_live() while keys(%$LIVE);
return;
}
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 ];
}
open my $fh, '+>>', $f or die "open($f): $!";
seek($fh, 0, SEEK_SET) or die "seek($f): $!";
my $d = do { local $/; <$fh> } // die "read($f): $!";
- my $orig = $d;
+ chomp(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";
+ $d //= 'mirror of '.($self->{cur_src} // $self->{src});
+ chomp $d;
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): $!";
+ print $fh $d, "\n" or die "print($f): $!";
close $fh or die "close($f): $!";
}
sub start_clone {
my ($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 {
my $dst = $self->{cur_dst} // $self->{dst};
my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self);
my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ];
+ my $ref = $self->{-ent} ? $self->{-ent}->{reference} : undef;
+ defined($ref) && -e "$self->{dst}$ref" and
+ push @$cmd, '--reference', "$self->{dst}$ref";
start_clone($self, $cmd, $opt, $fini);
- _get_txt_start($self, '_/text/config/raw', $fini);
+ $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v1)\z/s and
+ _get_txt_start($self, '_/text/config/raw', $fini);
+
my $d = $self->{-ent} ? $self->{-ent}->{description} : undef;
- defined($d) ? ($self->{'txt.description'} = $d) :
+ $self->{'txt.description'} = $d if defined $d;
+ (!defined($d) && !$nohang) and
_get_txt_start($self, 'description', $fini);
- reap_live() until ($nohang || !keys(%LIVE)); # for non-manifest clone
+ reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone
}
sub parse_epochs ($$) {
EOM
}
close $fh or die "close($f): $!";
- if (defined $ent->{head}) {
- $f = "$edst/HEAD";
- open $fh, '>', $f or die "open($f): $!";
- print $fh $ent->{head}, "\n" or die "print($f): $!";
- close $fh or die "close($f): $!";
+ my %map = (head => 'HEAD', description => undef);
+ while (my ($key, $fn) = each %map) {
+ my $val = $ent->{$key} // next;
+ $fn //= $key;
+ $fn = "$edst/$fn";
+ open $fh, '>', $fn or die "open($fn): $!";
+ print $fh $val, "\n" or die "print($fn): $!";
+ close $fh or die "close($fn): $!";
}
}
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} ? $self->{-ent}->{owner} : undef)) {
run_die([qw(git config -f), "$dst/config", 'gitweb.owner', $o]);
}
+ my $o = "$dst/objects";
+ if (open(my $fh, '<', "$o/info/alternates")) {
+ chomp(my @l = <$fh>);
+ for (@l) { $_ = File::Spec->abs2rel($_, $o)."\n" }
+ my $f = File::Temp->new(TEMPLATE => '.XXXX', DIR => "$o/info");
+ print $f @l;
+ $f->flush or die "flush($f): $!";
+ rename($f->filename, "$o/info/alternates") or
+ die "rename($f, $o/info/alternates): $!";
+ $f->unlink_on_destroy(0);
+ }
write_makefile($dst, 1);
index_cloned_inbox($self, 1);
}
sub v2_done { # called via OnDestroy
my ($self) = @_;
- return if $self->{dry_run};
+ return if $self->{dry_run} || !$LIVE;
+ my $dst = $self->{cur_dst} // $self->{dst};
+ require PublicInbox::Lock;
+ my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
+ my $lck = $lk->lock_for_scope($$);
_write_inbox_config($self);
require PublicInbox::MultiGit;
- my $dst = $self->{cur_dst} // $self->{dst};
my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
$mg->fill_alternates;
for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) }
- my $edst_owner = delete($self->{-owner}) // [];
- while (@$edst_owner) {
- my ($edst, $o) = splice(@$edst_owner);
- run_die [qw(git config -f), "$edst/config", 'gitweb.owner', $o];
+ my $entries = delete($self->{-ent}) // [];
+ while (@$entries) {
+ my ($edst, $ent) = splice(@$entries);
+ if (defined(my $o = $ent->{owner})) {
+ run_die [qw(git config -f), "$edst/config",
+ 'gitweb.owner', $o];
+ }
+ my $d = $ent->{description} // next;
+ my $fn = "$edst/description";
+ open my $fh, '>', $fn or die "open($fn): $!";
+ print $fh $d, "\n" or die "print($fn): $!";
+ close $fh or die "close($fn): $!";
}
for my $edst (@{delete($self->{-read_only}) // []}) {
my @st = stat($edst) or die "stat($edst): $!";
chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!";
}
write_makefile($dst, 2);
- delete $self->{-locked} // die "BUG: $dst not locked"; # unlock
+ undef $lck; # unlock
index_cloned_inbox($self, 2);
}
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 {
my $dst = $self->{cur_dst} // $self->{dst};
my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs);
my $task = $m ? bless { %$self }, __PACKAGE__ : $self;
- my (@src_edst, @skip);
+ my (@src_edst, @skip, $desc);
for my $nr (sort { $a <=> $b } keys %$v2_epochs) {
my ($uri, $key) = @{$v2_epochs->{$nr}};
my $src = $uri->as_string;
$1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr";
$edst .= "/git/$nr.git";
- $m->{$key} // die "BUG: `$key' not in manifest.js.gz";
+ my $ent = $m->{$key} // die "BUG: `$key' not in manifest.js.gz";
+ if (defined(my $d = $ent->{description})) {
+ $d =~ s/ \[epoch [0-9]+\]\z//s;
+ $desc = $d;
+ }
if (!$want || $want->{$nr}) {
push @src_edst, $src, $edst;
- my $o = $m->{$key}->{owner};
- push(@{$task->{-owner}}, $edst, $o) if defined($o);
+ push @{$task->{-ent}}, $edst, $ent;
} else { # create a placeholder so users only need to chmod +w
- init_placeholder($src, $edst, $m->{$key});
+ init_placeholder($src, $edst, $ent);
push @{$task->{-read_only}}, $edst;
push @skip, $key;
}
(!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst);
- require PublicInbox::Lock;
- my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
- _get_txt_start($task, '_/text/config/raw', $fini);
- _get_txt_start($self, 'description', $fini);
+ $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and
+ _get_txt_start($task, '_/text/config/raw', $fini);
+
+ defined($desc) ? ($task->{'txt.description'} = $desc) :
+ _get_txt_start($task, 'description', $fini);
- $task->{-locked} = $lk->lock_for_scope($$) if !$self->{dry_run};
my @cmd = clone_cmd($lei, my $opt = {});
while (@src_edst && !$lei->{child_error}) {
my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
my $n = scalar(keys %$v2) + scalar(@v1);
my @orig = defined($incl // $excl) ? (keys %$v2, @v1) : ();
if (defined $incl) {
- my $re = '(?:'.join('|', map {
- $self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/
- } @$incl).')';
+ my $re = '(?:'.join('\\z|', map {
+ $self->{lei}->glob2re($_) // qr/\A\Q$_\E/
+ } @$incl).'\\z)';
my @gone = delete @$v2{grep(!/$re/, keys %$v2)};
delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1;
delete @$m{grep(!/$re/, @v1)} and $self->{-culled_manifest} = 1;
@v1 = grep(/$re/, @v1);
}
if (defined $excl) {
- my $re = '(?:'.join('|', map {
- $self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/
- } @$excl).')';
+ my $re = '(?:'.join('\\z|', map {
+ $self->{lei}->glob2re($_) // qr/\A\Q$_\E/
+ } @$excl).'\\z)';
my @gone = delete @$v2{grep(/$re/, keys %$v2)};
delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1;
delete @$m{grep(/$re/, @v1)} and $self->{-culled_manifest} = 1;
($path_pfx, $n, $ret);
}
+sub clone_all {
+ my ($self, $todo, $m) = @_;
+ # handle no-dependency repos, first
+ for (@{delete($todo->{''}) // []}) {
+ clone_v1($_, 1);
+ return if $self->{lei}->{child_error};
+ }
+ # resolve references, deepest, first:
+ while (scalar keys %$todo) {
+ for my $x (keys %$todo) {
+ my $nr;
+ # resolve multi-level references
+ while (defined(my $nxt = $m->{$x}->{reference})) {
+ exists($todo->{$nxt}) or last;
+ die <<EOM if ++$nr > 1000;
+E: dependency loop detected (`$x' => `$nxt')
+EOM
+ $x = $nxt;
+ }
+ my $y = delete $todo->{$x} // next; # already done
+ for (@$y) {
+ clone_v1($_, 1);
+ return if $self->{lei}->{child_error};
+ }
+ last; # restart %$todo iteration
+ }
+ }
+}
+
# FIXME: this gets confused by single inbox instance w/ global manifest.js.gz
sub try_manifest {
my ($self) = @_;
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, "@$cmd failed");
}
my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m);
return $lei->child_error(1, $multi) if !ref($multi);
- if (my $v2 = delete $multi->{v2}) {
+ my $v2 = delete $multi->{v2};
+ if ($v2) {
for my $name (sort keys %$v2) {
my $epochs = delete $v2->{$name};
my %v2_epochs = map {
}
}
if (my $v1 = delete $multi->{v1}) {
+ delete local $lei->{opt}->{epoch} if defined($v2);
my $p = $path_pfx.$path;
chop($p) if substr($p, -1, 1) eq '/';
$uri->path($p);
+ my $todo = {};
+ my %want = map { $_ => 1 } @$v1;
for my $name (@$v1) {
- return if $self->{lei}->{child_error};
-
my $task = bless { %$self }, __PACKAGE__;
$task->{-ent} = $m->{$name} //
die("BUG: no `$name' in manifest");
E: `$task->{cur_dst}' must not contain newline
EOM
$task->{cur_src} .= '/';
- clone_v1($task, 1);
+ my $dep = $task->{-ent}->{reference} // '';
+ $dep = '' if !$want{$dep};
+ push @{$todo->{$dep}}, $task;
}
+ clone_all($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
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";