X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=9c457fcab054c6a68bdceaea5dce3c803dd05d8b;hb=dfb7216697548f294259cb010c26416cdbbe0ff0;hp=d0bc7384f7286dff3620d325dfab254390384c17;hpb=c89fbee4be1ab3e3f5544cda2d88ec7472aaadb2;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index d0bc7384..9c457fca 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -8,9 +8,10 @@ use v5.10.1; use parent qw(PublicInbox::IPC); 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); use URI; @@ -19,7 +20,7 @@ use PublicInbox::Inbox; 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) = @_; @@ -27,10 +28,10 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) 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}); @@ -67,7 +68,7 @@ sub try_scrape { $n => [ URI->new($_), '' ] } @v2_urls; # uniq clone_v2($self, \%v2_epochs); - reap_live() while keys(%LIVE); + reap_live() while keys(%$LIVE); return; } @@ -107,7 +108,8 @@ sub ft_rename ($$$) { my @st = stat($dst); my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask); chmod($mode, $ft) or croak "E: chmod $fn: $!"; - rename($fn, $dst) or croak "E: rename($fn => $ft): $!"; + require File::Copy; + File::Copy::mv($fn, $dst) or croak "E: mv($fn => $ft): $!"; $ft->unlink_on_destroy(0); } @@ -123,11 +125,12 @@ sub _get_txt_start { # non-fatal my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} }; my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o), $ft->filename); - $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; my $jobs = $lei->{opt}->{jobs} // 1; - reap_live() while keys(%LIVE) >= $jobs; + reap_live() while keys(%$LIVE) >= $jobs; $lei->qerr("# @$cmd"); - $LIVE{spawn($cmd, undef, $opt)} = + return if $self->{dry_run}; + $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&_get_txt_done, $self, $endpoint, $fini ]; } @@ -234,9 +237,10 @@ sub run_reap { sub start_clone { my ($self, $cmd, $opt, $fini) = @_; my $jobs = $self->{lei}->{opt}->{jobs} // 1; - reap_live() while keys(%LIVE) >= $jobs; + reap_live() while keys(%$LIVE) >= $jobs; $self->{lei}->qerr("# @$cmd"); - $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ]; + return if $self->{dry_run}; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ] } sub clone_v1 { @@ -250,14 +254,18 @@ sub clone_v1 { my $dst = $self->{cur_dst} // $self->{dst}; my $fini = PublicInbox::OnDestroy->new($$, \&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'} = $d) : _get_txt_start($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 ($$) { @@ -303,8 +311,8 @@ EOM $want } -sub init_placeholder ($$) { - my ($src, $edst) = @_; +sub init_placeholder ($$$) { + my ($src, $edst, $ent) = @_; PublicInbox::Import::init_bare($edst); my $f = "$edst/config"; open my $fh, '>>', $f or die "open($f): $!"; @@ -318,7 +326,19 @@ sub init_placeholder ($$) { ; will not fetch updates for it unless write permission is added. ; Hint: chmod +w $edst EOM - close $fh or die "close:($f): $!"; + if (defined($ent->{owner})) { + print $fh <{owner} +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): $!"; + } } sub reap_clone { # async, called via SIGCHLD @@ -326,26 +346,48 @@ sub reap_clone { # async, called via SIGCHLD 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 $self->{dry_run} || !$LIVE; _write_inbox_config($self); - write_makefile($self->{cur_dst} // $self->{dst}, 1); + 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): $!"; @@ -357,7 +399,7 @@ sub v2_done { # called via OnDestroy 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 { @@ -384,10 +426,13 @@ failed to extract epoch number from $src $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; } @@ -395,15 +440,18 @@ failed to extract epoch number from $src # filter out the epochs we skipped $self->{-culled_manifest} = 1 if delete(@$m{@skip}); - -d $dst || File::Path::mkpath($dst); + (!$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($$, \&v2_done, $task); - _get_txt_start($task, '_/text/config/raw', $fini); - _get_txt_start($self, 'description', $fini); + $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and + _get_txt_start($task, '_/text/config/raw', $fini); - $task->{-locked} = $lk->lock_for_scope($$); + _get_txt_start($task, 'description', $fini); + + $task->{-locked} = $lk->lock_for_scope($$) if !$self->{dry_run}; my @cmd = clone_cmd($lei, my $opt = {}); while (@src_edst && !$lei->{child_error}) { my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ]; @@ -480,6 +528,30 @@ sub multi_inbox ($$$) { ($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) = @_; @@ -489,18 +561,13 @@ sub try_manifest { 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!!; - -d $pdir || File::Path::mkpath($pdir); - 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"); @@ -541,9 +608,9 @@ EOM 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 `$name' in manifest"); @@ -557,11 +624,14 @@ EOM E: `$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 @@ -582,14 +652,18 @@ sub start_clone_url { 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";