use PublicInbox::Inbox;
use PublicInbox::LeiCurl;
use PublicInbox::OnDestroy;
-use Digest::SHA qw(sha256_hex);
+use Digest::SHA qw(sha256_hex sha1_hex);
our $LIVE; # pid => callback
+sub keep_going ($) {
+ $LIVE && (!$_[0]->{lei}->{child_error} ||
+ $_[0]->{lei}->{opt}->{'keep-going'});
+}
+
sub _wq_done_wait { # dwaitpid callback (via wq_eof)
my ($arg, $pid) = @_;
my ($mrr, $lei) = @$arg;
- my $f = "$mrr->{dst}/mirror.done";
if ($?) {
$lei->child_error($?);
- } elsif (!$mrr->{dry_run} && !unlink($f)) {
- warn("unlink($f): $!\n") unless $!{ENOENT};
- } else {
+ } elsif (!$lei->{child_error}) {
if (!$mrr->{dry_run} && $lei->{cmd} ne 'public-inbox-clone') {
require PublicInbox::LeiAddExternal;
PublicInbox::LeiAddExternal::_finish_add_external(
PublicInbox::Admin::index_inbox($ibx, undef, $opt);
}
return if defined $self->{cur_dst}; # one of many repos to clone
- open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait
}
sub run_reap {
push @cmd, '-q' if $lei->{opt}->{quiet} ||
($lei->{opt}->{jobs} // 1) > 1;
push @cmd, '-v' if $lei->{opt}->{verbose};
+ push(@cmd, '-p') if $lei->{opt}->{prune};
@cmd;
}
sub fgrp_update {
my ($fgrp) = @_;
+ return if !keep_going($fgrp);
my $srcfh = delete $fgrp->{srcfh} or return;
my $dstfh = delete $fgrp->{dstfh} or return;
seek($srcfh, SEEK_SET, 0) or die "seek(src): $!";
qw(update-ref --stdin -z) ];
my $lei = $fgrp->{lei};
$lei->qerr("# @$cmd");
- my $opt = { 0 => $r, 1 => $lei->{1}, 2 => $lei->{2} };
+ my $opt = { 0 => $r, 2 => $lei->{2} };
my $pid = spawn($cmd, undef, $opt);
close $r or die "close(r): $!";
for my $ref (keys %dst) {
sub pack_refs {
my ($self, $git_dir) = @_;
do_reap($self);
+ return if !keep_going($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} };
+ my $opt = { 2 => $self->{lei}->{2} };
$LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $self, $cmd ];
}
return if !$LIVE;
my $pid;
my $first = $fgrpv->[0] // die 'BUG: no fgrpv->[0]';
+ return if !keep_going($first);
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 %opt = ( 2 => $fgrp->{lei}->{2} );
my $update_ref = $fgrp->{dry_run} ? undef :
PublicInbox::OnDestroy->new($$, \&fgrp_update, $fgrp);
$f, '--unset-all', "remotes.$grp"];
$self->{lei}->qerr("# @$cmd");
if (!$self->{dry_run}) {
- $pid = spawn($cmd);
+ $pid = spawn($cmd, undef, { 2 => $self->{lei}->{2} });
waitpid($pid, 0) // die "waitpid: $!";
die "E: @$cmd: \$?=$?" if ($? && ($? >> 8) != 5);
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 && !$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 $rn = substr(sha256_hex($key), 0, 16);
- unless ($self->{dry_run}) {
- # --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);
- }
- }
if (!-d $self->{cur_dst} && !$self->{dry_run}) {
my $alt = File::Spec->rel2abs("$dir/objects");
PublicInbox::Import::init_bare($self->{cur_dst});
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) = @_;
+ return if !keep_going($self);
+ 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($$, \&resume_fetch, @_);
+ cmp_fp_fetch($self, $go_fetch) if $self->{-ent} &&
+ defined($self->{-ent}->{fingerprint});
}
sub resume_fetch {
my ($self, $uri, $fini) = @_;
+ return if !keep_going($self);
my $dst = $self->{cur_dst} // $self->{dst};
my @git = ('git', "--git-dir=$dst");
- my $opt = +{ map { $_ => $self->{lei}->{$_} } (0..2) };
+ my $opt = { 2 => $self->{lei}->{2} };
my $rn = 'origin'; # configurable?
for ("url=$uri", "fetch=+refs/*:refs/*", 'mirror=true') {
my @kv = split(/=/, $_, 2);
}
my $cmd = [ @{$self->{-torsocks}}, @git,
fetch_args($self->{lei}, $opt), $rn ];
+ push @$cmd, '-P' if $self->{lei}->{prune}; # --prune-tags implied
start_cmd($self, $cmd, $opt, $fini);
}
+sub fgrp_enqueue_maybe {
+ my ($self, $fgrp) = @_;
+ my $enq = PublicInbox::OnDestroy->new($$, \&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, $fgrp) = @_;
+ return if !keep_going($self);
+ 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}}}, $fgrp;
+}
+
sub clone_v1 {
my ($self, $nohang) = @_;
my $lei = $self->{lei};
$self->{-torsocks} //= $curl->torsocks($lei, $uri) or return;
my $dst = $self->{cur_dst} // $self->{dst};
my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self);
+ my $resume = -d $dst;
if (my $fgrp = forkgroup_prep($self, $uri)) {
$fgrp->{-fini} = $fini;
- push @{$self->{fgrp_todo}->{$fgrp->{-osdir}}}, $fgrp;
- } elsif (-d $dst) {
- resume_fetch($self, $uri, $fini);
+ $resume ? fgrp_enqueue_maybe($self, $fgrp) :
+ fgrp_enqueue($self, $fgrp);
+ } elsif ($resume) {
+ resume_fetch_maybe($self, $uri, $fini);
} else { # normal clone
my $cmd = [ @{$self->{-torsocks}},
clone_cmd($lei, my $opt = {}), "$uri", $dst ];
my ($self, $cmd) = @_;
my $cerr = $?;
$? = 0; # don't let it influence normal exit
- if ($cerr) {
- kill('TERM', keys %$LIVE);
- $self->{lei}->child_error($cerr, "@$cmd failed (\$?=$cerr)");
+ $self->{lei}->child_error($cerr, "@$cmd failed (\$?=$cerr)") if $cerr;
+}
+
+sub up_fp_done {
+ my ($self) = @_;
+ return if !keep_going($self);
+ my $fh = delete $self->{-show_ref_up} // die 'BUG: no show-ref output';
+ seek($fh, SEEK_SET, 0) or die "seek(show_ref): $!";
+ $self->{-ent} // die 'BUG: no -ent';
+ my $A = $self->{-ent}->{fingerprint} // die 'BUG: no fingerprint';
+ my $B = sha1_hex(do { local $/; <$fh> } // die("read(show_ref): $!"));
+ return if $A eq $B;
+ $self->{-ent}->{fingerprint} = $B;
+ push @{$self->{chg}->{fp_mismatch}}, $self->{-key};
+}
+
+sub update_ent {
+ my ($self) = @_;
+ my $key = $self->{-key} // die 'BUG: no -key';
+ my $new = $self->{-ent}->{fingerprint};
+ my $cur = $self->{-local_manifest}->{$key}->{fingerprint} // "\0";
+ my $dst = $self->{cur_dst} // $self->{dst};
+ if (defined($new) && $new ne $cur) {
+ my $cmd = ['git', "--git-dir=$dst", 'show-ref'];
+ my $opt = { 2 => $self->{lei}->{2} };
+ open($opt->{1}, '+>', undef) or die "open(tmp): $!";
+ $self->{-show_ref_up} = $opt->{1};
+ my $done = PublicInbox::OnDestroy->new($$, \&up_fp_done, $self);
+ start_cmd($self, $cmd, $opt, $done);
}
+ $new = $self->{-ent}->{owner} // return;
+ $cur = $self->{-local_manifest}->{$key}->{owner} // "\0";
+ return if $cur eq $new;
+ my $cmd = [ qw(git config -f), "$dst/config", 'gitweb.owner', $new ];
+ start_cmd($self, $cmd, { 2 => $self->{lei}->{2} });
}
sub v1_done { # called via OnDestroy
my ($self) = @_;
- return if $self->{dry_run} || !$LIVE;
+ return if $self->{dry_run} || !keep_going($self);
_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', $o]);
- }
+ update_ent($self) if $self->{-ent};
my $o = "$dst/objects";
if (open(my $fh, '<', my $fn = "$o/info/alternates")) {;
my $base = File::Spec->rel2abs($o);
sub v2_done { # called via OnDestroy
my ($self) = @_;
- return if $self->{dry_run} || !$LIVE;
+ return if $self->{dry_run} || !keep_going($self);
my $dst = $self->{cur_dst} // $self->{dst};
require PublicInbox::Lock;
my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
}
}
# filter out the epochs we skipped
- $self->{-culled_manifest} = 1 if $m && delete(@$m{@skip});
+ $self->{chg}->{manifest} = 1 if $m && delete(@$m{@skip});
(!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst);
$m;
}
+sub load_current_manifest ($) {
+ 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): $!\n" if !$self->{-initial_clone};
+ undef;
+ } else {
+ die "open($fn): $!\n";
+ }
+}
+
sub multi_inbox ($$$) {
my ($self, $path, $m) = @_;
my $incl = $self->{lei}->{opt}->{include};
$self->{lei}->glob2re($_) // 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 $self->{-culled_manifest} = 1;
+ delete @$m{map { @$_ } @gone} and $self->{chg}->{manifest} = 1;
+ delete @$m{grep(!/$re/, @v1)} and $self->{chg}->{manifest} = 1;
@v1 = grep(/$re/, @v1);
}
if (defined $excl) {
$self->{lei}->glob2re($_) // 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 $self->{-culled_manifest} = 1;
+ delete @$m{map { @$_ } @gone} and $self->{chg}->{manifest} = 1;
+ delete @$m{grep(/$re/, @v1)} and $self->{chg}->{manifest} = 1;
@v1 = grep(!/$re/, @v1);
}
my $ret; # { v1 => [ ... ], v2 => { "/$inbox_name" => [ epochs ] }}
# handle no-dependency repos, first
for (@$nodep) {
clone_v1($_, 1);
- return if $self->{lei}->{child_error};
+ return if !keep_going($self);
}
# resolve references, deepest, first:
while (scalar keys %$todo) {
my $y = delete $todo->{$x} // next; # already done
for (@$y) {
clone_v1($_, 1);
- return if $self->{lei}->{child_error};
+ return if !keep_going($self);
}
last; # restart %$todo iteration
}
}
+ do_reap($self, 1); # finish all fingerprint checks
fgrp_fetch_all($self);
do_reap($self, 1);
}
my $path = $uri->path;
chop($path) eq '/' or die "BUG: $uri not canonicalized";
$uri->path($path . '/manifest.js.gz');
- my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX',
- UNLINK => 1, TMPDIR => 1, SUFFIX => '.tmp');
+ my $manifest = $self->{-manifest} // "$self->{dst}/manifest.js.gz";
+ my %opt = (UNLINK => 1, SUFFIX => '.tmp', TMPDIR => 1);
+ if (!$self->{dry_run} && $manifest =~ m!\A(.+?)/[^/]+\z! and -d $1) {
+ $opt{DIR} = $1; # allows fast rename(2) w/o EXDEV
+ delete $opt{TMPDIR};
+ }
+ my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX', %opt);
my $cmd = $curl->for_uri($lei, $uri, qw(-f -R -o), $ft->filename);
- my %opt = map { $_ => $lei->{$_} } (0..2);
+ my $mf_url = "$uri";
+ %opt = map { $_ => $lei->{$_} } (0..2);
my $cerr = run_reap($lei, $cmd, \%opt);
if ($cerr) {
return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing
warn $@;
return try_scrape($self);
}
+ local $self->{chg} = {};
+ 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 $multi->{v2};
E: `$self->{cur_dst}' must not contain newline
EOM
clone_v2_prep($self, \%v2_epochs, $m);
- return if $self->{lei}->{child_error};
+ return if !keep_going($self);
}
}
if (my $v1 = delete $multi->{v1}) {
}
delete local $lei->{opt}->{epoch} if defined($v2);
clone_all($self, $m);
- return if $self->{lei}->{child_error} || $self->{dry_run};
+ return if $self->{dry_run} || !keep_going($self);
# set by clone_v2_prep/-I/--exclude
- dump_manifest($m => $ft) if delete $self->{-culled_manifest};
- ft_rename($ft, "$self->{dst}/manifest.js.gz", 0666);
- open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait
+ my $mis = delete $self->{chg}->{fp_mismatch};
+ if ($mis) {
+ my $t = (stat($ft))[9];
+ require POSIX;
+ $t = POSIX::strftime('%Y-%m-%d %k:%M:%S %z', localtime($t));
+ warn <<EOM;
+W: Fingerprints for the following repositories do not match
+W: $mf_url @ $t:
+W: These repositories may have updated since $t:
+EOM
+ warn "\t", $_, "\n" for @$mis;
+ warn <<EOM if !$self->{lei}->{opt}->{prune};
+W: The above fingerprints may never match without --prune
+EOM
+ }
+ dump_manifest($m => $ft) if delete($self->{chg}->{manifest}) || $mis;
+ ft_rename($ft, $manifest, 0666);
}
sub start_clone_url {
my $lei = $self->{lei};
$self->{dry_run} = 1 if $lei->{opt}->{'dry-run'};
umask($lei->{client_umask}) if defined $lei->{client_umask};
+ $self->{-initial_clone} = 1 if !-d $self->{dst};
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\.{0,2}/!;
+ $self->{"-$k"} = $v;
}
- local $LIVE;
+ local $LIVE = {};
my $iv = $lei->{opt}->{'inbox-version'} //
return start_clone_url($self);
return clone_v1($self) if $iv == 1;