use PublicInbox::Inbox;
use PublicInbox::LeiCurl;
use PublicInbox::OnDestroy;
-use Digest::SHA qw(sha256_hex);
+use Digest::SHA qw(sha256_hex sha1_hex);
our $LIVE; # pid => callback
-my $update_ref_stdin = $ENV{GIT_CAN_UPDATE_REF_STDIN} // 1;
sub _wq_done_wait { # dwaitpid callback (via wq_eof)
my ($arg, $pid) = @_;
$ret;
}
-sub start_clone {
+sub start_cmd {
my ($self, $cmd, $opt, $fini) = @_;
do_reap($self);
$self->{lei}->qerr("# @$cmd");
@cmd;
}
-sub fgrp_update_old ($) { # for git <1.8.5
- my ($fgrp) = @_;
- my $cmd = [ @{$fgrp->{-torsocks}}, 'git', "--git-dir=$fgrp->{cur_dst}",
- fetch_args($fgrp->{lei}, my $opt = {}) ];
- $fgrp->{lei}->qerr("# @$cmd");
- do_reap($fgrp);
- $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $fgrp, $cmd ];
-}
-
sub upr { # feed `git update-ref --stdin -z' verbosely
- my ($lei, $w, $op, $ref, $oid) = @_;
- $lei->qerr("# $op $ref $oid") if $lei->{opt}->{verbose};
- print $w "$op $ref\0$oid\0" or die "print(w): $!";
+ my ($lei, $w, $op, @rest) = @_; # ($ref, $oid) = @rest
+ $lei->qerr("# $op @rest") if $lei->{opt}->{verbose};
+ print $w "$op ", join("\0", @rest, '') or die "print(w): $!";
}
sub fgrp_update {
my $new = delete $src{$ref};
my $old = $dst{$ref};
if (defined $new) {
- upr($lei, $w, 'update', $ref, $new) if $new ne $old;
+ $new eq $old or
+ upr($lei, $w, 'update', $ref, $new, $old);
} else {
upr($lei, $w, 'delete', $ref, $old);
}
while (my ($ref, $oid) = each %src) {
upr($lei, $w, 'create', $ref, $oid);
}
- if (close($w)) { # git >= 1.8.5
- $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $cmd ];
- do_reap($fgrp);
- } else { # git <1.8.5 w/o update-ref --stdin
- warn "E: close(update-ref --stdin): $!\n";
- $update_ref_stdin = 0;
- waitpid($pid, 0) // die "waitpid(update-ref --stdin): $!";
- fgrp_update_old($fgrp);
- }
+ close($w) or warn "E: close(update-ref --stdin): $! (need git 1.8.5+)\n";
+ my $pack = PublicInbox::OnDestroy->new($$, \&pack_dst, $fgrp);
+ $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $cmd, $pack ];
+}
+
+sub pack_dst { # packs lightweight satellite repos
+ my ($fgrp) = @_;
+ pack_refs($fgrp, $fgrp->{cur_dst});
}
sub pack_refs {
do_reap($self);
my $cmd = [ 'git', "--git-dir=$git_dir", qw(pack-refs --all --prune) ];
$self->{lei}->qerr("# @$cmd");
+ return if $self->{dry_run};
my $opt = { 1 => $self->{lei}->{1}, 2 => $self->{lei}->{2} };
$LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $self, $cmd ];
}
-sub fgrp_fetched {
- my ($fgrp) = @_;
- return if $fgrp->{dry_run} || !$LIVE;
- my $rn = $fgrp->{-remote};
- my %opt = map { $_ => $fgrp->{lei}->{$_} } (0..2);
- pack_refs($fgrp, $fgrp->{-osdir}); # objstore refs always packed
-
- $update_ref_stdin or return fgrp_update_old($fgrp);
-
- my $update_ref = PublicInbox::OnDestroy->new($$, \&fgrp_update, $fgrp);
-
- my $src = [ 'git', "--git-dir=$fgrp->{-osdir}", 'for-each-ref',
- "--format=refs/%(refname:lstrip=3)%00%(objectname)",
- "refs/remotes/$rn/" ];
- do_reap($fgrp);
- open($fgrp->{srcfh}, '+>', undef) or die "open(src): $!";
- $fgrp->{lei}->qerr("# @$src >SRC");
- my $pid = spawn($src, undef, { %opt, 1 => $fgrp->{srcfh} });
- $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $src, $update_ref ];
-
- my $dst = [ 'git', "--git-dir=$fgrp->{cur_dst}", 'for-each-ref',
- '--format=%(refname)%00%(objectname)' ];
- do_reap($fgrp);
- open($fgrp->{dstfh}, '+>', undef) or die "open(dst): $!";
- $fgrp->{lei}->qerr("# @$dst >DST");
- $pid = spawn($dst, undef, { %opt, 1 => $fgrp->{dstfh} });
- $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $dst, $update_ref ];
-}
-
-sub fgrp_fetch {
- my ($fgrp, $fini) = @_;
- my $cmd = [ @{$fgrp->{-torsocks}}, 'git', "--git-dir=$fgrp->{-osdir}",
- fetch_args($fgrp->{lei}, my $opt = {}), '--no-tags',
- $fgrp->{-remote} ];
- $fgrp->{-fini} = $fini;
- do_reap($fgrp);
- $fgrp->{lei}->qerr("# @$cmd");
- return if $fgrp->{dry_run};
- my $fgrp_fini = PublicInbox::OnDestroy->new($$, \&fgrp_fetched, $fgrp);
- my $pid = spawn($cmd, undef, $opt);
- $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $cmd, $fgrp_fini ];
+sub fgrpv_done {
+ my ($fgrpv) = @_;
+ return if !$LIVE;
+ my $pid;
+ my $first = $fgrpv->[0] // die 'BUG: no fgrpv->[0]';
+ pack_refs($first, $first->{-osdir}); # objstore refs always packed
+ for my $fgrp (@$fgrpv) {
+ my $rn = $fgrp->{-remote};
+ my %opt = map { $_ => $fgrp->{lei}->{$_} } (0..2);
+
+ my $update_ref = $fgrp->{dry_run} ? undef :
+ PublicInbox::OnDestroy->new($$, \&fgrp_update, $fgrp);
+
+ my $src = [ 'git', "--git-dir=$fgrp->{-osdir}", 'for-each-ref',
+ "--format=refs/%(refname:lstrip=3)%00%(objectname)",
+ "refs/remotes/$rn/" ];
+ do_reap($fgrp);
+ $fgrp->{lei}->qerr("# @$src >SRC");
+ if ($update_ref) {
+ open(my $fh, '+>', undef) or die "open(src): $!";
+ $pid = spawn($src, undef, { %opt, 1 => $fh });
+ $fgrp->{srcfh} = $fh;
+ $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $src, $update_ref ]
+ }
+ my $dst = [ 'git', "--git-dir=$fgrp->{cur_dst}", 'for-each-ref',
+ '--format=%(refname)%00%(objectname)' ];
+ do_reap($fgrp);
+ $fgrp->{lei}->qerr("# @$dst >DST");
+ if ($update_ref) {
+ open(my $fh, '+>', undef) or die "open(dst): $!";
+ $pid = spawn($dst, undef, { %opt, 1 => $fh });
+ $fgrp->{dstfh} = $fh;
+ $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $dst, $update_ref ]
+ }
+ }
+}
+
+sub fgrp_fetch_all {
+ my ($self) = @_;
+ my $todo = delete $self->{fgrp_todo} or return;
+ keys(%$todo) or return;
+
+ # Rely on the fgrptmp remote groups in the config file rather
+ # than listing all remotes since the remote name list may exceed
+ # system argv limits:
+ my $grp = 'fgrptmp';
+
+ my @git = (@{$self->{-torsocks}}, 'git');
+ my $j = $self->{lei}->{opt}->{jobs};
+ my $opt = {};
+ my @fetch = do {
+ local $self->{lei}->{opt}->{jobs} = 1;
+ (fetch_args($self->{lei}, $opt),
+ qw(--no-tags --multiple));
+ };
+ push(@fetch, "-j$j") if $j;
+ my $pid;
+ while (my ($osdir, $fgrpv) = each %$todo) {
+ my $f = "$osdir/config";
+
+ # clobber group from previous run atomically
+ my $cmd = ['git', "--git-dir=$osdir", qw(config -f),
+ $f, '--unset-all', "remotes.$grp"];
+ $self->{lei}->qerr("# @$cmd");
+ if (!$self->{dry_run}) {
+ $pid = spawn($cmd);
+ waitpid($pid, 0) // die "waitpid: $!";
+ die "E: @$cmd: \$?=$?" if ($? && ($? >> 8) != 5);
+
+ # update the config atomically via O_APPEND while
+ # respecting git-config locking
+ sysopen(my $lk, "$f.lock", O_CREAT|O_EXCL|O_WRONLY)
+ or die "open($f.lock): $!";
+ open my $fh, '>>', $f or die "open(>>$f): $!";
+ $fh->autoflush(1);
+ my $buf = join('', "[remotes]\n",
+ map { "\t$grp = $_->{-remote}\n" } @$fgrpv);
+ print $fh $buf or die "print($f): $!";
+ close $fh or die "close($f): $!";
+ unlink("$f.lock") or die "unlink($f.lock): $!";
+ }
+
+ $cmd = [ @git, "--git-dir=$osdir", @fetch, $grp ];
+ do_reap($self);
+ $self->{lei}->qerr("# @$cmd");
+ my $end = PublicInbox::OnDestroy->new($$, \&fgrpv_done, $fgrpv);
+ return if $self->{dry_run};
+ $pid = spawn($cmd, undef, $opt);
+ $LIVE->{$pid} = [ \&reap_cmd, $self, $cmd, $end ];
+ }
}
# keep this idempotent for future use by public-inbox-fetch
my $os = $self->{-objstore} // return;
my $fg = $self->{-ent}->{forkgroup} // return;
my $dir = "$os/$fg.git";
- my @cmd = ('git', "--git-dir=$dir", 'config');
- my $opt = +{ map { $_ => $self->{lei}->{$_} } (0..2) };
- if (!-d $dir) {
+ if (!-d $dir && !$self->{dry_run}) {
PublicInbox::Import::init_bare($dir);
+ my @cmd = ('git', "--git-dir=$dir", 'config');
+ my $opt = { 2 => $self->{lei}->{2} };
for ('repack.useDeltaIslands=true',
'pack.island=refs/remotes/([^/]+)/') {
run_die([@cmd, split(/=/, $_, 2)], undef, $opt);
}
}
my $key = $self->{-key} // die 'BUG: no -key';
- my ($bn) = ($key =~ m{/([a-z0-9_,;=!\+\{\}\|][^/]*)(?:\.git)?\z}i);
- my $rn = "$bn-".substr(sha256_hex($key), 0, 16);
- # --no-tags is required to avoid conflicts
- for ("url=$uri", "fetch=+refs/*:refs/remotes/$rn/*",
- 'tagopt=--no-tags') {
- my @kv = split(/=/, $_, 2);
- $kv[0] = "remote.$rn.$kv[0]";
- run_die([@cmd, @kv], undef, $opt);
- }
- $self->{-do_pack_refs} = 1; # likely coderepo
- if (!-d $self->{cur_dst}) {
+ my $rn = substr(sha256_hex($key), 0, 16);
+ if (!-d $self->{cur_dst} && !$self->{dry_run}) {
my $alt = File::Spec->rel2abs("$dir/objects");
PublicInbox::Import::init_bare($self->{cur_dst});
my $o = "$self->{cur_dst}/objects";
say $fh $l or die "say($f): $!";
}
close $fh or die "close($f): $!";
- @cmd = ('git', "--git-dir=$self->{cur_dst}",
- qw(remote add --mirror=fetch origin), "$uri");
- my $pid = spawn(\@cmd, undef, $opt);
- waitpid($pid, 0) // die "waitpid(@cmd): $!";
- die "E: @cmd: \$?=$?" if ($? && ($? >> 8) != 3);
+ $f = "$self->{cur_dst}/config";
+ open $fh, '+>>', $f or die "open:($f): $!";
+ print $fh <<EOM or die "print($f): $!";
+; rely on the "$rn" remote in the
+; $fg fork group for fetches
+; only uncomment the following iff you detach from fork groups
+; [remote "origin"]
+; url = $uri
+; fetch = +refs/*:refs/*
+; mirror = true
+EOM
+ close $fh or die "close($f): $!";
}
- bless { %$self, -osdir => $dir, -remote => $rn }, __PACKAGE__;
+ bless {
+ %$self, -osdir => $dir, -remote => $rn, -uri => $uri
+ }, __PACKAGE__;
+}
+
+sub fp_done {
+ my ($self, $go_fetch) = @_;
+ my $fh = delete $self->{-show_ref} // die 'BUG: no show-ref output';
+ seek($fh, SEEK_SET, 0) or die "seek(show_ref): $!";
+ $self->{-ent} // die 'BUG: no -ent';
+ my $A = $self->{-ent}->{fingerprint} // die 'BUG: no fingerprint';
+ my $B = sha1_hex(do { local $/; <$fh> } // die("read(show_ref): $!"));
+ return if $A ne $B; # $go_fetch->DESTROY fires
+ $go_fetch->cancel;
+ $self->{lei}->qerr("# $self->{-key} up-to-date");
+}
+
+sub cmp_fp_fetch {
+ my ($self, $go_fetch) = @_;
+ # $go_fetch is either resume_fetch or fgrp_enqueue
+ my $new = $self->{-ent}->{fingerprint} // die 'BUG: no fingerprint';
+ my $key = $self->{-key} // die 'BUG: no -key';
+ if (my $cur_ent = $self->{-local_manifest}->{$key}) {
+ # runs go_fetch->DESTROY run if eq
+ return $go_fetch->cancel if $cur_ent->{fingerprint} eq $new;
+ }
+ my $dst = $self->{cur_dst} // $self->{dst};
+ my $cmd = ['git', "--git-dir=$dst", 'show-ref'];
+ my $opt = { 2 => $self->{lei}->{2} };
+ open($opt->{1}, '+>', undef) or die "open(tmp): $!";
+ $self->{-show_ref} = $opt->{1};
+ my $done = PublicInbox::OnDestroy->new($$, \&fp_done, $self, $go_fetch);
+ start_cmd($self, $cmd, $opt, $done);
+}
+
+sub resume_fetch_maybe {
+ my ($self, $uri, $fini) = @_;
+ my $go_fetch = PublicInbox::OnDestroy->new($$, \&resume_fetch, @_);
+ cmp_fp_fetch($self, $go_fetch) if $self->{-ent} &&
+ defined($self->{-ent}->{fingerprint});
+}
+
+sub resume_fetch {
+ my ($self, $uri, $fini) = @_;
+ my $dst = $self->{cur_dst} // $self->{dst};
+ my @git = ('git', "--git-dir=$dst");
+ my $opt = +{ map { $_ => $self->{lei}->{$_} } (0..2) };
+ my $rn = 'origin'; # configurable?
+ for ("url=$uri", "fetch=+refs/*:refs/*", 'mirror=true') {
+ my @kv = split(/=/, $_, 2);
+ $kv[0] = "remote.$rn.$kv[0]";
+ next if $self->{dry_run};
+ run_die([@git, 'config', @kv], undef, $opt);
+ }
+ my $cmd = [ @{$self->{-torsocks}}, @git,
+ fetch_args($self->{lei}, $opt), $rn ];
+ start_cmd($self, $cmd, $opt, $fini);
+}
+
+sub fgrp_enqueue_maybe {
+ my ($self, $fgrp) = @_;
+ my $enq = PublicInbox::OnDestroy->new($$, \&fgrp_enqueue, $self, $fgrp);
+ cmp_fp_fetch($self, $enq) if $self->{-ent} &&
+ defined($self->{-ent}->{fingerprint});
+ # $enq->DESTROY calls fgrp_enqueue otherwise
+}
+
+sub fgrp_enqueue {
+ my ($self, $fgrp) = @_;
+ my $opt = { 2 => $self->{lei}->{2} };
+ # --no-tags is required to avoid conflicts
+ my $u = $fgrp->{-uri} // die 'BUG: no {-uri}';
+ my $rn = $fgrp->{-remote} // die 'BUG: no {-remote}';
+ my @cmd = ('git', "--git-dir=$fgrp->{-osdir}", 'config');
+ for ("url=$u", "fetch=+refs/*:refs/remotes/$rn/*", 'tagopt=--no-tags') {
+ my @kv = split(/=/, $_, 2);
+ $kv[0] = "remote.$rn.$kv[0]";
+ $self->{dry_run} ? $self->{lei}->qerr("# @cmd @kv") :
+ run_die([@cmd, @kv], undef, $opt);
+ }
+ push @{$self->{fgrp_todo}->{$fgrp->{-osdir}}}, $fgrp;
}
sub clone_v1 {
$self->{-torsocks} //= $curl->torsocks($lei, $uri) or return;
my $dst = $self->{cur_dst} // $self->{dst};
my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self);
- my $cmd = [ @{$self->{-torsocks}}, clone_cmd($lei, my $opt = {}),
- "$uri", $dst ];
- my $fgrp = forkgroup_prep($self, $uri);
- if (!defined($fgrp) && defined($self->{-ent})) {
- if (defined(my $ref = $self->{-ent}->{reference})) {
- -e "$self->{dst}$ref" and
- push @$cmd, '--reference', "$self->{dst}$ref";
+ my $resume = -d $dst;
+ if (my $fgrp = forkgroup_prep($self, $uri)) {
+ $fgrp->{-fini} = $fini;
+ $resume ? fgrp_enqueue_maybe($self, $fgrp) :
+ fgrp_enqueue($self, $fgrp);
+ } elsif ($resume) {
+ resume_fetch_maybe($self, $uri, $fini);
+ } else { # normal clone
+ my $cmd = [ @{$self->{-torsocks}},
+ clone_cmd($lei, my $opt = {}), "$uri", $dst ];
+ if (defined($self->{-ent})) {
+ if (defined(my $ref = $self->{-ent}->{reference})) {
+ -e "$self->{dst}$ref" and
+ push @$cmd, '--reference',
+ "$self->{dst}$ref";
+ }
}
+ start_cmd($self, $cmd, $opt, $fini);
}
- $fgrp ? fgrp_fetch($fgrp, $fini) :
- start_clone($self, $cmd, $opt, $fini);
-
if (!$self->{-is_epoch} && $lei->{opt}->{'inbox-config'} =~
/\A(?:always|v1)\z/s) {
_get_txt_start($self, '_/text/config/raw', $fini);
$? = 0; # don't let it influence normal exit
if ($cerr) {
kill('TERM', keys %$LIVE);
- $self->{lei}->child_error($cerr, "@$cmd failed");
+ $self->{lei}->child_error($cerr, "@$cmd failed (\$?=$cerr)");
}
}
_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 $key = $self->{-key} // die 'BUG: no -key';
+ my $cur = $self->{-local_manifest}->{$key}->{owner} // "\0";
+ $cur eq $o or run_die([qw(git config -f),
+ "$dst/config", 'gitweb.owner', $o]);
}
my $o = "$dst/objects";
if (open(my $fh, '<', my $fn = "$o/info/alternates")) {;
ft_rename($ft, $fn, 0666, $fh);
}
}
- pack_refs($self, $dst) if delete $self->{-do_pack_refs};
eval { set_description($self) };
warn $@ if $@;
return if ($self->{-is_epoch} ||
$m;
}
+sub load_current_manifest ($) {
+ my ($self) = @_;
+ my $fn = $self->{-manifest} // return;
+ if (open(my $fh, '<', $fn)) {
+ decode_manifest($fh, $fn, $fn);
+ } elsif ($!{ENOENT}) { # non-fatal, we can just do it slowly
+ warn "open($fn): $!\n";
+ undef;
+ } else {
+ die "open($fn): $!\n";
+ }
+}
+
sub multi_inbox ($$$) {
my ($self, $path, $m) = @_;
my $incl = $self->{lei}->{opt}->{include};
last; # restart %$todo iteration
}
}
+ do_reap($self, 1); # finish all fingerprint checks
+ fgrp_fetch_all($self);
do_reap($self, 1);
}
my $uri = URI->new($self->{src});
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
+ $self->{-torsocks} //= $curl->torsocks($lei, $uri) or return;
my $path = $uri->path;
chop($path) eq '/' or die "BUG: $uri not canonicalized";
$uri->path($path . '/manifest.js.gz');
warn $@;
return try_scrape($self);
}
+ local $self->{-local_manifest} = load_current_manifest($self);
my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m);
return $lei->child_error(1, $multi) if !ref($multi);
my $v2 = delete $multi->{v2};
local $self->{todo} = {};
+ local $self->{fgrp_todo} = {}; # { objstore_dir => [fgrp, ...] }
if ($v2) {
for my $name (sort keys %$v2) {
my $epochs = delete $v2->{$name};
sub do_mirror { # via wq_io_do or public-inbox-clone
my ($self) = @_;
my $lei = $self->{lei};
+ $self->{dry_run} = 1 if $lei->{opt}->{'dry-run'};
umask($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'
- if (defined(my $os = $lei->{opt}->{objstore})) {
- $os = 'objstore' if $os eq ''; # --objstore w/o args
- $os = "$self->{dst}/$os" if $os !~ m!\A/!;
- $self->{-objstore} = $os;
+ # we support --objstore= and --manifest= with '' (empty string)
+ for my $default (qw(objstore manifest.js.gz)) {
+ my ($k) = (split(/\./, $default))[0];
+ my $v = $lei->{opt}->{$k} // next;
+ $v = $default if $v eq '';
+ $v = "$self->{dst}/$v" if $v !~ m!\A/!;
+ $self->{"-$k"} = $v;
}
local $LIVE;
my $iv = $lei->{opt}->{'inbox-version'} //