-# Copyright (C) 2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# "lei add-external --mirror" support (also "public-inbox-clone");
use File::Temp ();
use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY);
use Carp qw(croak);
+our %LIVE;
sub _wq_done_wait { # dwaitpid callback (via wq_eof)
my ($arg, $pid) = @_;
warn("unlink($f): $!\n") unless $!{ENOENT};
} else {
if ($lei->{cmd} ne 'public-inbox-clone') {
+ # calls _finish_add_external
$lei->lazy_cb('add-external', '_finish_'
)->($lei, $mrr->{dst});
}
if (my @v2_urls = grep(m!\A\Q$url\E/[0-9]+\z!, @urls)) {
my %v2_epochs = map {
my ($n) = (m!/([0-9]+)\z!);
- $n => URI->new($_)
+ $n => [ URI->new($_), '' ]
} @v2_urls; # uniq
- return clone_v2($self, \%v2_epochs);
+ clone_v2($self, \%v2_epochs);
+ reap_live() while keys(%LIVE);
+ return;
}
# filter out common URLs served by WWW (e.g /$MSGID/T/)
$ft->unlink_on_destroy(0);
}
-sub _get_txt { # non-fatal
+sub _get_txt_start { # non-fatal
my ($self, $endpoint, $file, $mode) = @_;
- my $uri = URI->new($self->{src});
+ 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 $ft = File::Temp->new(TEMPLATE => "$file-XXXX", DIR => $self->{dst});
+ my $dst = $self->{cur_dst} // $self->{dst};
+ my $ft = File::Temp->new(TEMPLATE => "$file-XXXX", DIR => $dst);
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);
- my $cerr = run_reap($lei, $cmd, $opt);
+ $self->{-get_txt} = [ $ft, $cmd, $uri, $file, $mode ];
+ $lei->qerr("# @$cmd");
+ spawn($cmd, undef, $opt);
+}
+
+sub _get_txt_done {
+ my ($self) = @_;
+ my ($ft, $cmd, $uri, $file, $mode) = @{delete $self->{-get_txt}};
+ my $cerr = $?;
+ $? = 0;
return "$uri missing" if ($cerr >> 8) == 22;
return "# @$cmd failed (non-fatal)" if $cerr;
- ft_rename($ft, "$self->{dst}/$file", $mode);
+ my $dst = $self->{cur_dst} // $self->{dst};
+ ft_rename($ft, "$dst/$file", $mode);
undef; # success
}
# tries the relatively new /$INBOX/_/text/config/raw endpoint
-sub _try_config {
+sub _try_config_start {
my ($self) = @_;
- my $dst = $self->{dst};
+ 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";
}
- my $err = _get_txt($self,
- qw(_/text/config/raw inbox.config.example), 0444);
+ _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 $f = "$self->{dst}/inbox.config.example";
+ my $dst = $self->{cur_dst} // $self->{dst};
+ my $f = "$dst/inbox.config.example";
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 $f = "$self->{dst}/description";
+ 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): $!");
$d =~ /^Unnamed repository/ || $d !~ /\S/) {
seek($fh, 0, SEEK_SET) or die "seek($f): $!";
truncate($fh, 0) or die "truncate($f): $!";
- print $fh "mirror of $self->{src}\n" or die "print($f): $!";
+ my $src = $self->{cur_src} // $self->{src};
+ print $fh "mirror of $src\n" or die "print($f): $!";
close $fh or die "close($f): $!";
}
}
address => [ 'lei@example.com' ],
version => $iv,
};
- $ibx->{inboxdir} = $self->{dst};
+ $ibx->{inboxdir} = $self->{cur_dst} // $self->{dst};
PublicInbox::Inbox->new($ibx);
PublicInbox::InboxWritable->new($ibx);
my $opt = {};
PublicInbox::Admin::progress_prepare($opt, $lei->{2});
PublicInbox::Admin::index_inbox($ibx, undef, $opt);
}
+ return if defined $self->{cur_dst};
open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait
}
my ($self) = @_;
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
- my $uri = URI->new($self->{src});
+ my $uri = URI->new($self->{cur_src} // $self->{src});
defined($lei->{opt}->{epoch}) and
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, $self->{dst} ];
+ $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($self->{dst}, 1);
+ write_makefile($dst, 1);
index_cloned_inbox($self, 1);
}
sub parse_epochs ($$) {
- my ($opt_epochs, $v2_epochs) = @_; # $epcohs "LOW..HIGH"
+ my ($opt_epochs, $v2_epochs) = @_; # $epochs "LOW..HIGH"
$opt_epochs // return; # undef => all epochs
my ($lo, $dotdot, $hi, @extra) = split(/(\.\.)/, $opt_epochs);
undef($lo) if ($lo // '') eq '';
close $fh or die "close:($f): $!";
}
+sub reap_clone { # async, called via SIGCHLD
+ my ($lei, $cmd) = @_;
+ my $cerr = $?;
+ $? = 0; # don't let it influence normal exit
+ if ($cerr) {
+ kill('TERM', keys %LIVE);
+ $lei->child_error($cerr, "@$cmd failed");
+ }
+}
+
+sub v2_done { # called via OnDestroy
+ my ($self) = @_;
+ require PublicInbox::MultiGit;
+ my $dst = $self->{cur_dst} // $self->{dst};
+ my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
+ $mg->fill_alternates;
+ for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) }
+ for my $edst (@{delete($self->{-read_only}) // []}) {
+ my @st = stat($edst) or die "stat($edst): $!";
+ chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!";
+ }
+ write_makefile($dst, 2);
+ delete $self->{-locked} // die "BUG: $dst not locked"; # unlock
+ index_cloned_inbox($self, 2);
+}
+
+sub reap_live {
+ my $pid = waitpid(-1, 0) // die "waitpid(-1): $!";
+ if (my $x = delete $LIVE{$pid}) {
+ my $cb = shift @$x;
+ $cb->(@$x);
+ } else {
+ warn "reaped unknown PID=$pid ($?)\n";
+ }
+}
+
sub clone_v2 ($$;$) {
my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
- my $pfx = $curl->torsocks($lei, (values %$v2_epochs)[0]) or return;
- my $dst = $self->{dst};
+ my $first_uri = (map { $_->[0] } values %$v2_epochs)[0];
+ my $pfx = $curl->torsocks($lei, $first_uri) or return;
+ my $dst = $self->{cur_dst} // $self->{dst};
my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs);
- my (@src_edst, @read_only, @skip_nr);
+ my $task = $m ? bless { %$self }, __PACKAGE__ : $self;
+ my (@src_edst, @skip);
for my $nr (sort { $a <=> $b } keys %$v2_epochs) {
- my $uri = $v2_epochs->{$nr};
+ my ($uri, $key) = @{$v2_epochs->{$nr}};
my $src = $uri->as_string;
my $edst = $dst;
$src =~ m!/([0-9]+)(?:\.git)?\z! or die <<"";
push @src_edst, $src, $edst;
} else { # create a placeholder so users only need to chmod +w
init_placeholder($src, $edst);
- push @read_only, $edst;
- push @skip_nr, $nr;
+ push @{$task->{-read_only}}, $edst;
+ push @skip, $key;
}
}
- if (@skip_nr) { # filter out the epochs we skipped
- my $re = join('|', @skip_nr);
- my @del = grep(m!/git/$re\.git\z!, keys %$m);
- delete @$m{@del};
- $self->{-culled_manifest} = 1;
- }
+ # filter out the epochs we skipped
+ $self->{-culled_manifest} = 1 if delete(@$m{@skip});
my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
- _try_config($self);
- my $on_destroy = $lk->lock_for_scope($$);
+ my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
+ $LIVE{_try_config_start($task)} = [ \&_try_config_done, $task, $fini ];
+ $task->{-locked} = $lk->lock_for_scope($$);
my @cmd = clone_cmd($lei, my $opt = {});
- while (my ($src, $edst) = splice(@src_edst, 0, 2)) {
- my $cmd = [ @$pfx, @cmd, $src, $edst ];
- my $cerr = run_reap($lei, $cmd, $opt);
- return $lei->child_error($cerr, "@$cmd failed") if $cerr;
- }
- require PublicInbox::MultiGit;
- my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
- $mg->fill_alternates;
- for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) }
- for my $edst (@read_only) {
- my @st = stat($edst) or die "stat($edst): $!";
- chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!";
- }
- write_makefile($self->{dst}, 2);
- undef $on_destroy; # unlock
- index_cloned_inbox($self, 2);
-}
-
-# PSGI mount prefixes and manifest.js.gz prefixes don't always align...
-sub deduce_epochs ($$) {
- my ($m, $path) = @_;
- my ($v1_ent, @v2_epochs);
- my $path_pfx = '';
- $path =~ s!/+\z!!;
+ my $jobs = $self->{lei}->{opt}->{jobs} // 2;
do {
- $v1_ent = $m->{$path};
- @v2_epochs = grep(m!\A\Q$path\E/git/[0-9]+\.git\z!, keys %$m);
- } while (!defined($v1_ent) && !@v2_epochs &&
- $path =~ s!\A(/[^/]+)/!/! and $path_pfx .= $1);
- ($path_pfx, $v1_ent ? $path : undef, @v2_epochs);
+ 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});
}
sub decode_manifest ($$$) {
$m;
}
+sub multi_inbox ($$$) {
+ my ($self, $path, $m) = @_;
+ my $incl = $self->{lei}->{opt}->{include};
+ my $excl = $self->{lei}->{opt}->{exclude};
+
+ # assuming everything not v2 is v1, for now
+ my @v1 = sort grep(!m!.+/git/[0-9]+\.git\z!, keys %$m);
+ my @v2_epochs = sort grep(m!.+/git/[0-9]+\.git\z!, keys %$m);
+ my $v2 = {};
+
+ for (@v2_epochs) {
+ m!\A(/.+)/git/[0-9]+\.git\z! or die "BUG: $_";
+ push @{$v2->{$1}}, $_;
+ }
+ 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 @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 @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);
+ }
+ my $ret; # { v1 => [ ... ], v2 => { "/$inbox_name" => [ epochs ] }}
+ $ret->{v1} = \@v1 if @v1;
+ $ret->{v2} = $v2 if keys %$v2;
+ $ret //= @orig ? "Nothing to clone, available repositories:\n\t".
+ join("\n\t", sort @orig)
+ : "Nothing available to clone\n";
+ my $path_pfx = '';
+
+ # PSGI mount prefixes and manifest.js.gz prefixes don't always align...
+ if (@v2_epochs) {
+ until (grep(m!\A\Q$$path\E/git/[0-9]+\.git\z!,
+ @v2_epochs) == @v2_epochs) {
+ $$path =~ s!\A(/[^/]+)/!/! or last;
+ $path_pfx .= $1;
+ }
+ } elsif (@v1) {
+ while (!defined($m->{$$path}) && $$path =~ s!\A(/[^/]+)/!/!) {
+ $path_pfx .= $1;
+ }
+ }
+ ($path_pfx, $n, $ret);
+}
+
+# FIXME: this gets confused by single inbox instance w/ global manifest.js.gz
sub try_manifest {
my ($self) = @_;
my $uri = URI->new($self->{src});
my $opt = { -C => $pdir };
$opt->{$_} = $lei->{$_} for (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");
warn $@;
return try_scrape($self);
}
- my ($path_pfx, $v1_path, @v2_epochs) = deduce_epochs($m, $path);
- if (@v2_epochs) {
- # It may be possible to have v1 + v2 in parallel someday:
- warn(<<EOM) if defined $v1_path;
-# `$v1_path' appears to be a v1 inbox while v2 epochs exist:
-# @v2_epochs
-# ignoring $v1_path (use --inbox-version=1 to force v1 instead)
+ my ($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};
+ my %v2_epochs = map {
+ $uri->path($n > 1 ? $path_pfx.$path.$_
+ : $path_pfx.$_);
+ my ($e) = ("$uri" =~ m!/([0-9]+)\.git\z!);
+ $e // die "no [0-9]+\.git in `$uri'";
+ $e => [ $uri->clone, $_ ];
+ } @$epochs;
+ ("$uri" =~ m!\A(.+/)git/[0-9]+\.git\z!) or
+ die "BUG: `$uri' !~ m!/git/[0-9]+.git!";
+ local $self->{cur_src} = $1;
+ local $self->{cur_dst} = $self->{dst};
+ if ($n > 1 && $uri->path =~ m!\A\Q$path_pfx$path\E/(.+)/
+ git/[0-9]+\.git\z!x) {
+ $self->{cur_dst} .= "/$1";
+ }
+ index($self->{cur_dst}, "\n") >= 0 and die <<EOM;
+E: `$self->{cur_dst}' must not contain newline
EOM
- my %v2_epochs = map {
- $uri->path($path_pfx.$_);
- my ($n) = ("$uri" =~ m!/([0-9]+)\.git\z!);
- $n => $uri->clone
- } @v2_epochs;
- clone_v2($self, \%v2_epochs, $m);
- } elsif (defined $v1_path) {
- clone_v1($self);
- } else {
- die "E: confused by <$uri>, possible matches:\n\t",
- join(', ', sort keys %$m), "\n";
+ clone_v2($self, \%v2_epochs, $m);
+ reap_live() while keys(%LIVE) >= $jobs;
+ return if $self->{lei}->{child_error};
+ }
}
- if (delete $self->{-culled_manifest}) { # set by clone_v2
+ if (my $v1 = delete $multi->{v1}) {
+ my $p = $path_pfx.$path;
+ chop($p) if substr($p, -1, 1) eq '/';
+ $uri->path($p);
+ for my $name (@$v1) {
+ local $self->{cur_src} = "$uri";
+ local $self->{cur_dst} = $self->{dst};
+ if ($n > 1) {
+ $self->{cur_dst} .= $name;
+ $self->{cur_src} .= $name;
+ }
+ index($self->{cur_dst}, "\n") >= 0 and die <<EOM;
+E: `$self->{cur_dst}' must not contain newline
+EOM
+ $self->{cur_src} .= '/';
+ clone_v1($self, 1);
+ }
+ }
+ reap_live() while keys(%LIVE);
+ 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
# epoch they no longer want to skip
my $json = PublicInbox::Config->json->encode($m);
+ my $mtime = (stat($fn))[9];
gzip(\$json => $fn) or die "gzip: $GzipError";
+ utime($mtime, $mtime, $fn) or die "utime(..., $fn): $!";
}
ft_rename($ft, "$self->{dst}/manifest.js.gz", 0666);
+ open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait
}
sub start_clone_url {
eval {
my $iv = $lei->{opt}->{'inbox-version'};
if (defined $iv) {
+ local %LIVE;
return clone_v1($self) if $iv == 1;
return try_scrape($self) if $iv == 2;
die "bad --inbox-version=$iv\n";