use strict;
use v5.10.1;
use parent qw(PublicInbox::IPC);
-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 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);
-our %LIVE;
+use URI;
+use PublicInbox::Config;
+use PublicInbox::Inbox;
+use PublicInbox::LeiCurl;
+use PublicInbox::OnDestroy;
+
+our $LIVE; # pid => callback
sub _wq_done_wait { # dwaitpid callback (via wq_eof)
my ($arg, $pid) = @_;
my $f = "$mrr->{dst}/mirror.done";
if ($?) {
$lei->child_error($?);
- } elsif (!unlink($f)) {
+ } elsif (!$mrr->{dry_run} && !unlink($f)) {
warn("unlink($f): $!\n") unless $!{ENOENT};
} else {
- if ($lei->{cmd} ne 'public-inbox-clone') {
+ if (!$mrr->{dry_run} && $lei->{cmd} ne 'public-inbox-clone') {
# calls _finish_add_external
$lei->lazy_cb('add-external', '_finish_'
)->($lei, $mrr->{dst});
$n => [ URI->new($_), '' ]
} @v2_urls; # uniq
clone_v2($self, \%v2_epochs);
- reap_live() while keys(%LIVE);
+ reap_live() while keys(%$LIVE);
return;
}
my @st = stat($dst);
my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask);
chmod($mode, $ft) or croak "E: chmod $fn: $!";
- rename($fn, $dst) or croak "E: rename($fn => $ft): $!";
+ require File::Copy;
+ File::Copy::mv($fn, $dst) or croak "E: mv($fn => $ft): $!";
$ft->unlink_on_destroy(0);
}
sub _get_txt_start { # non-fatal
- my ($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);
+ my $jobs = $lei->{opt}->{jobs} // 1;
+ reap_live() while keys(%$LIVE) >= $jobs;
$lei->qerr("# @$cmd");
- spawn($cmd, undef, $opt);
+ return if $self->{dry_run};
+ $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ];
+ $LIVE->{spawn($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 {
+sub _write_inbox_config {
my ($self) = @_;
- _get_txt_start($self, qw(_/text/config/raw inbox.config.example), 0444);
-}
-
-sub _try_config_done {
- 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]);
-}
-
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 $@;
# n.b. public-inbox-clone works w/o (SQLite || Xapian)
# lei is useless without Xapian + SQLite
if ($lei->{cmd} ne 'public-inbox-clone') {
+ require PublicInbox::InboxWritable;
+ require PublicInbox::Admin;
my $ibx = delete($self->{ibx}) // {
address => [ 'lei@example.com' ],
version => $iv,
$ret;
}
+sub start_clone {
+ my ($self, $cmd, $opt, $fini) = @_;
+ my $jobs = $self->{lei}->{opt}->{jobs} // 1;
+ reap_live() while keys(%$LIVE) >= $jobs;
+ $self->{lei}->qerr("# @$cmd");
+ return if $self->{dry_run};
+ $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ]
+}
+
sub clone_v1 {
my ($self, $nohang) = @_;
my $lei = $self->{lei};
my $pfx = $curl->torsocks($lei, $uri) or return;
my $dst = $self->{cur_dst} // $self->{dst};
my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self);
- my $jobs = $self->{lei}->{opt}->{jobs} // 1;
my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ];
- $lei->qerr("# @$cmd");
- $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $lei, $cmd, $fini ];
- reap_live() while keys(%LIVE) >= $jobs;
-
- # wait for `git clone' to mkdir $dst (TODO: inotify/kevent?)
- select(undef, undef, undef, 0.011) until -d $dst;
- $LIVE{_try_config_start($self)} = [ \&_try_config_done, $self, $fini ];
- reap_live() until ($nohang || !keys(%LIVE));
+ my $ref = $self->{-ent} ? $self->{-ent}->{reference} : undef;
+ defined($ref) && -e "$self->{dst}$ref" and
+ push @$cmd, '--reference', "$self->{dst}$ref";
+ start_clone($self, $cmd, $opt, $fini);
+
+ $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v1)\z/s and
+ _get_txt_start($self, '_/text/config/raw', $fini);
+ my $d = $self->{-ent} ? $self->{-ent}->{description} : undef;
+ defined($d) ? ($self->{'txt.description'} = $d) :
+ _get_txt_start($self, 'description', $fini);
+
+ reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone
}
sub parse_epochs ($$) {
$want
}
-sub init_placeholder ($$) {
- my ($src, $edst) = @_;
+sub init_placeholder ($$$) {
+ my ($src, $edst, $ent) = @_;
PublicInbox::Import::init_bare($edst);
my $f = "$edst/config";
open my $fh, '>>', $f or die "open($f): $!";
; 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 $edst
+EOM
+ if (defined($ent->{owner})) {
+ print $fh <<EOM or die "print($f): $!";
+[gitweb]
+ owner = $ent->{owner}
EOM
- close $fh or die "close:($f): $!";
+ }
+ 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): $!";
+ }
}
sub reap_clone { # async, called via SIGCHLD
- my ($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, "@$cmd failed");
+ kill('TERM', keys %$LIVE);
+ $self->{lei}->child_error($cerr, "@$cmd failed");
}
}
sub v1_done { # called via OnDestroy
my ($self) = @_;
+ 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 $self->{dry_run} || !$LIVE;
+ _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];
+ }
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): $!";
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 {
$1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr";
$edst .= "/git/$nr.git";
+ $m->{$key} // die "BUG: `$key' not in manifest.js.gz";
if (!$want || $want->{$nr}) {
push @src_edst, $src, $edst;
+ my $o = $m->{$key}->{owner};
+ push(@{$task->{-owner}}, $edst, $o) if defined($o);
} else { # create a placeholder so users only need to chmod +w
- init_placeholder($src, $edst);
+ init_placeholder($src, $edst, $m->{$key});
push @{$task->{-read_only}}, $edst;
push @skip, $key;
}
# 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): $!\n";
- }
+ (!$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($$, \&v2_done, $task);
- $LIVE{_try_config_start($task)} = [ \&_try_config_done, $task, $fini ];
- $task->{-locked} = $lk->lock_for_scope($$);
+
+ $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and
+ _get_txt_start($task, '_/text/config/raw', $fini);
+
+ _get_txt_start($task, 'description', $fini);
+
+ $task->{-locked} = $lk->lock_for_scope($$) if !$self->{dry_run};
my @cmd = clone_cmd($lei, my $opt = {});
- my $jobs = $self->{lei}->{opt}->{jobs} // 1;
- do {
- reap_live() while keys(%LIVE) >= $jobs;
- while (keys(%LIVE) < $jobs && @src_edst &&
- !$lei->{child_error}) {
- my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
- $lei->qerr("# @$cmd");
- $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone,
- $lei, $cmd, $fini ];
- }
- } while (@src_edst && !$lei->{child_error});
+ while (@src_edst && !$lei->{child_error}) {
+ my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
+ start_clone($self, $cmd, $opt, $fini);
+ }
}
sub decode_manifest ($$$) {
($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) {
+ # resolve multi-level references
+ while (defined($m->{$x}->{reference})) {
+ $x = $m->{$x}->{reference};
+ }
+ 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 $path = $uri->path;
chop($path) eq '/' or die "BUG: $uri not canonicalized";
$uri->path($path . '/manifest.js.gz');
- my $pdir = $lei->rel2abs($self->{dst});
- $pdir =~ s!/[^/]+/?\z!!;
- my $ft = File::Temp->new(TEMPLATE => 'm-XXXX',
- UNLINK => 1, DIR => $pdir, SUFFIX => '.tmp');
+ my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX',
+ UNLINK => 1, TMPDIR => 1, SUFFIX => '.tmp');
my $fn = $ft->filename;
- my ($bn) = ($fn =~ m!/([^/]+)\z!);
- my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $bn);
- my $opt = { -C => $pdir };
- $opt->{$_} = $lei->{$_} for (0..2);
- my $cerr = run_reap($lei, $cmd, $opt);
- local %LIVE;
+ my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn);
+ my %opt = map { $_ => $lei->{$_} } (0..2);
+ my $cerr = run_reap($lei, $cmd, \%opt);
+ local $LIVE;
if ($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);
- my $jobs = $self->{lei}->{opt}->{jobs} // 1;
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};
}
}
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) {
- 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) {
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);
- return if $self->{lei}->{child_error};
+ reap_live() while keys(%$LIVE);
+ return if $self->{lei}->{child_error} || $self->{dry_run};
if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude
# write the smaller manifest if epochs were skipped so
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";
sub start {
my ($cls, $lei, $src, $dst) = @_;
my $self = bless { src => $src, dst => $dst }, $cls;
- if ($src =~ m!https?://!) {
- require URI;
- require PublicInbox::LeiCurl;
- }
- require PublicInbox::Lock;
- require PublicInbox::Inbox;
- require PublicInbox::Admin;
- require PublicInbox::InboxWritable;
$lei->request_umask;
my ($op_c, $ops) = $lei->workers_start($self, 1);
$lei->{wq1} = $self;