X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=21341efb99ab32d85f2a008767c974de4d3356b3;hb=4bc708478281771874bb23b88b9a04b70dddac78;hp=e6b3e32a1bacbe264bea6f86c7fe705109de9bc0;hpb=71d1ffb1bf3d435a6804a0d85340965548def00d;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index e6b3e32a..21341efb 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -3,14 +3,14 @@ # "lei add-external --mirror" support (also "public-inbox-clone"); package PublicInbox::LeiMirror; -use strict; -use v5.10.1; +use v5.12; 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 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; @@ -18,8 +18,10 @@ use PublicInbox::Config; use PublicInbox::Inbox; use PublicInbox::LeiCurl; use PublicInbox::OnDestroy; +use Digest::SHA qw(sha256_hex); -our %LIVE; # pid => callback +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, $pid) = @_; @@ -31,9 +33,9 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) warn("unlink($f): $!\n") unless $!{ENOENT}; } else { if (!$mrr->{dry_run} && $lei->{cmd} ne 'public-inbox-clone') { - # calls _finish_add_external - $lei->lazy_cb('add-external', '_finish_' - )->($lei, $mrr->{dst}); + require PublicInbox::LeiAddExternal; + PublicInbox::LeiAddExternal::_finish_add_external( + $lei, $mrr->{dst}); } $lei->qerr("# mirrored $mrr->{src} => $mrr->{dst}"); } @@ -42,20 +44,28 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) # for old installations without manifest.js.gz sub try_scrape { - my ($self) = @_; + my ($self, $fallback_manifest) = @_; my $uri = URI->new($self->{src}); my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $cmd = $curl->for_uri($lei, $uri, '--compressed'); + my $cmd = $curl->for_uri($lei, $uri, qw(-f --compressed)); my $opt = { 0 => $lei->{0}, 2 => $lei->{2} }; my $fh = popen_rd($cmd, undef, $opt); my $html = do { local $/; <$fh> } // die "read(curl $uri): $!"; close($fh) or return $lei->child_error($?, "@$cmd failed"); # we grep with URL below, we don't want Subject/From headers - # making us clone random URLs + # making us clone random URLs. This assumes remote instances + # prior to public-inbox 1.7.0 + # 5b96edcb1e0d8252 (www: move mirror instructions to /text/, 2021-08-28) my @html = split(/
/, $html); my @urls = ($html[-1] =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g); + if (!@urls && $fallback_manifest) { + warn <as_string; chop($url) eq '/' or die "BUG: $uri not canonicalized"; @@ -66,8 +76,9 @@ sub try_scrape { my ($n) = (m!/([0-9]+)\z!); $n => [ URI->new($_), '' ] } @v2_urls; # uniq - clone_v2($self, \%v2_epochs); - reap_live() while keys(%LIVE); + clone_v2_prep($self, \%v2_epochs); + delete local $lei->{opt}->{epoch}; + clone_all($self); return; } @@ -97,21 +108,36 @@ sub clone_cmd { ($lei->{opt}->{jobs} // 1) > 1; push @cmd, '-v' if $lei->{opt}->{verbose}; # XXX any other options to support? - # --reference is tricky with multiple epochs... + # --reference is tricky with multiple epochs, but handled + # automatically if using manifest.js.gz @cmd; } sub ft_rename ($$$) { my ($ft, $dst, $open_mode) = @_; - my $fn = $ft->filename; my @st = stat($dst); my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask); - chmod($mode, $ft) or croak "E: chmod $fn: $!"; + chmod($mode, $ft) or croak "E: chmod($ft): $!"; require File::Copy; - File::Copy::mv($fn, $dst) or croak "E: mv($fn => $ft): $!"; + File::Copy::mv($ft->filename, $dst) or croak "E: mv($ft => $dst): $!"; $ft->unlink_on_destroy(0); } +sub do_reap ($;$) { + my ($self, $jobs) = @_; + $jobs //= $self->{-jobs} //= $self->{lei}->{opt}->{jobs} // 1; + $jobs = 1 if $jobs < 1; + while (keys(%$LIVE) >= $jobs) { + my $pid = waitpid(-1, 0) // die "waitpid(-1): $!"; + if (my $x = delete $LIVE->{$pid}) { + my $cb = shift @$x; + $cb->(@$x) if $cb; + } else { + warn "reaped unknown PID=$pid ($?)\n"; + } + } +} + sub _get_txt_start { # non-fatal my ($self, $endpoint, $fini) = @_; my $uri = URI->new($self->{cur_src} // $self->{src}); @@ -122,14 +148,13 @@ sub _get_txt_start { # non-fatal 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), + my $cmd = $self->{curl}->for_uri($lei, $uri, qw(-f --compressed -R -o), $ft->filename); - my $jobs = $lei->{opt}->{jobs} // 1; - reap_live() while keys(%LIVE) >= $jobs; + do_reap($self); $lei->qerr("# @$cmd"); return if $self->{dry_run}; $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; - $LIVE{spawn($cmd, undef, $opt)} = + $LIVE->{spawn($cmd, undef, $opt)} = [ \&_get_txt_done, $self, $endpoint, $fini ]; } @@ -176,24 +201,23 @@ sub set_description ($) { open my $fh, '+>>', $f or die "open($f): $!"; seek($fh, 0, SEEK_SET) or die "seek($f): $!"; my $d = do { local $/; <$fh> } // die "read($f): $!"; - my $orig = $d; + chomp(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"; + $d //= 'mirror of '.($self->{cur_src} // $self->{src}); + chomp $d; 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): $!"; + print $fh $d, "\n" or die "print($f): $!"; close $fh or die "close($f): $!"; } sub index_cloned_inbox { my ($self, $iv) = @_; my $lei = $self->{lei}; - eval { set_description($self) }; - warn $@ if $@; # n.b. public-inbox-clone works w/o (SQLite || Xapian) # lei is useless without Xapian + SQLite @@ -220,7 +244,7 @@ sub index_cloned_inbox { PublicInbox::Admin::progress_prepare($opt, $lei->{2}); PublicInbox::Admin::index_inbox($ibx, undef, $opt); } - return if defined $self->{cur_dst}; + return if defined $self->{cur_dst}; # one of many repos to clone open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } @@ -235,11 +259,178 @@ sub run_reap { sub start_clone { my ($self, $cmd, $opt, $fini) = @_; - my $jobs = $self->{lei}->{opt}->{jobs} // 1; - reap_live() while keys(%LIVE) >= $jobs; + do_reap($self); $self->{lei}->qerr("# @$cmd"); return if $self->{dry_run}; - $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ]; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $self, $cmd, $fini ] +} + +sub fetch_args ($$) { + my ($lei, $opt) = @_; + my @cmd; # (git --git-dir=...) to be added by caller + $opt->{$_} = $lei->{$_} for (0..2); + # we support "-c $key=$val" for arbitrary git config options + # e.g.: git -c http.proxy=socks5h://127.0.0.1:9050 + push(@cmd, '-c', $_) for @{$lei->{opt}->{c} // []}; + push @cmd, 'fetch'; + push @cmd, '-q' if $lei->{opt}->{quiet} || + ($lei->{opt}->{jobs} // 1) > 1; + push @cmd, '-v' if $lei->{opt}->{verbose}; + @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 ($fgrp, $w, $op, $ref, $oid) = @_; + $fgrp->{lei}->qerr("# $op $ref $oid"); + print $w "$op $ref\0$oid\0" or die "print(w): $!"; +} + +sub fgrp_update { + my ($fgrp) = @_; + my $srcfh = delete $fgrp->{srcfh} or return; + my $dstfh = delete $fgrp->{dstfh} or return; + seek($srcfh, SEEK_SET, 0) or die "seek(src): $!"; + seek($dstfh, SEEK_SET, 0) or die "seek(dst): $!"; + my %src = map { chomp; split(/\0/) } (<$srcfh>); + close $srcfh; + my %dst = map { chomp; split(/\0/) } (<$dstfh>); + close $dstfh; + pipe(my ($r, $w)) or die "pipe: $!"; + my $cmd = [ 'git', "--git-dir=$fgrp->{cur_dst}", + qw(update-ref --stdin -z) ]; + $fgrp->{lei}->qerr("# @$cmd"); + my $opt = { 0 => $r, 1 => $fgrp->{lei}->{1}, 2 => $fgrp->{lei}->{2} }; + my $pid = spawn($cmd, undef, $opt); + close $r or die "close(r): $!"; + for my $ref (keys %dst) { + my $new = delete $src{$ref}; + my $old = $dst{$ref}; + if (defined $new) { + upr($fgrp, $w, 'update', $ref, $new) if $new ne $old; + } else { + upr($fgrp, $w, 'delete', $ref, $old); + } + } + while (my ($ref, $oid) = each %src) { + upr($fgrp, $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); + } +} + +sub pack_refs { + my ($self, $git_dir) = @_; + do_reap($self); + my $cmd = [ 'git', "--git-dir=$git_dir", qw(pack-refs --all --prune) ]; + $self->{lei}->qerr("# @$cmd"); + 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 = {}), + $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 ]; +} + +# keep this idempotent for future use by public-inbox-fetch +sub forkgroup_prep { + my ($self, $uri) = @_; + $self->{-ent} // return; + 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) { + PublicInbox::Import::init_bare($dir); + 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); + for ("url=$uri", "fetch=+refs/*:refs/remotes/$rn/*") { + 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 $alt = File::Spec->rel2abs("$dir/objects"); + PublicInbox::Import::init_bare($self->{cur_dst}); + my $o = "$self->{cur_dst}/objects"; + my $f = "$o/info/alternates"; + my $l = File::Spec->abs2rel($alt, File::Spec->rel2abs($o)); + open my $fh, '+>>', $f or die "open($f): $!"; + seek($fh, SEEK_SET, 0) or die "seek($f): $!"; + chomp(my @cur = <$fh>); + if (!grep(/\A\Q$l\E\z/, @cur)) { + 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); + } + bless { %$self, -osdir => $dir, -remote => $rn }, __PACKAGE__; } sub clone_v1 { @@ -249,18 +440,32 @@ sub clone_v1 { 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; + $self->{-torsocks} //= $curl->torsocks($lei, $uri) or return; my $dst = $self->{cur_dst} // $self->{dst}; my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self); - my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ]; - start_clone($self, $cmd, $opt, $fini); + 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"; + } + } + $fgrp ? fgrp_fetch($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', $fini); + } - _get_txt_start($self, '_/text/config/raw', $fini); my $d = $self->{-ent} ? $self->{-ent}->{description} : undef; - defined($d) ? ($self->{'txt.description'} = $d) : + $self->{'txt.description'} = $d if defined $d; + (!defined($d) && !$nohang) and _get_txt_start($self, 'description', $fini); - reap_live() until ($nohang || !keys(%LIVE)); # for non-manifest clone + $nohang or do_reap($self, 1); # for non-manifest clone } sub parse_epochs ($$) { @@ -328,79 +533,94 @@ EOM 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): $!"; + my %map = (head => 'HEAD', description => undef); + while (my ($key, $fn) = each %map) { + my $val = $ent->{$key} // next; + $fn //= $key; + $fn = "$edst/$fn"; + open $fh, '>', $fn or die "open($fn): $!"; + print $fh $val, "\n" or die "print($fn): $!"; + close $fh or die "close($fn): $!"; } } -sub reap_clone { # async, called via SIGCHLD +sub reap_cmd { # async, called via SIGCHLD my ($self, $cmd) = @_; 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}; + 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")) { + my $base = File::Spec->rel2abs($o); + chomp(my @l = <$fh>); + for (@l) { + $_ = File::Spec->abs2rel($_, $base) if m!\A/!; + $_ .= "\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); + } + pack_refs($self, $dst) if delete $self->{-do_pack_refs}; + eval { set_description($self) }; + warn $@ if $@; + return if ($self->{-is_epoch} || + $self->{lei}->{opt}->{'inbox-config'} ne 'always'); write_makefile($dst, 1); index_cloned_inbox($self, 1); } sub v2_done { # called via OnDestroy my ($self) = @_; - return if $self->{dry_run}; + return if $self->{dry_run} || !$LIVE; + my $dst = $self->{cur_dst} // $self->{dst}; + require PublicInbox::Lock; + my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; + my $lck = $lk->lock_for_scope($$); _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): $!"; } write_makefile($dst, 2); - delete $self->{-locked} // die "BUG: $dst not locked"; # unlock + undef $lck; # unlock + eval { set_description($self) }; + warn $@ if $@; index_cloned_inbox($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 ($$;$) { +sub clone_v2_prep ($$;$) { my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; my $first_uri = (map { $_->[0] } values %$v2_epochs)[0]; - my $pfx = $curl->torsocks($lei, $first_uri) or return; + $self->{-torsocks} //= $curl->torsocks($lei, $first_uri) or return; my $dst = $self->{cur_dst} // $self->{dst}; my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); my $task = $m ? bless { %$self }, __PACKAGE__ : $self; - my (@src_edst, @skip); + delete $task->{todo}; # $self->{todo} still exists + my (@skip, $desc); + my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); for my $nr (sort { $a <=> $b } keys %$v2_epochs) { my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; @@ -410,35 +630,40 @@ 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"; + my $ent; + if ($m) { + $ent = $m->{$key} // + die("BUG: `$key' not in manifest.js.gz"); + if (defined(my $d = $ent->{description})) { + $d =~ s/ \[epoch [0-9]+\]\z//s; + $desc = $d; + } + } if (!$want || $want->{$nr}) { - push @src_edst, $src, $edst; - my $o = $m->{$key}->{owner}; - push(@{$task->{-owner}}, $edst, $o) if defined($o); + my $etask = bless { %$task, -key => $key }, __PACKAGE__; + $etask->{-ent} = $ent; # may have {reference} + $etask->{cur_src} = $src; + $etask->{cur_dst} = $edst; + $etask->{-is_epoch} = $fini; + my $ref = $ent->{reference} // ''; + push @{$self->{todo}->{$ref}}, $etask; + $self->{any_want}->{$key} = 1; } else { # create a placeholder so users only need to chmod +w - init_placeholder($src, $edst, $m->{$key}); + init_placeholder($src, $edst, $ent); push @{$task->{-read_only}}, $edst; push @skip, $key; } } # filter out the epochs we skipped - $self->{-culled_manifest} = 1 if delete(@$m{@skip}); + $self->{-culled_manifest} = 1 if $m && delete(@$m{@skip}); (!$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($$, \&v2_done, $task); - - _get_txt_start($task, '_/text/config/raw', $fini); - _get_txt_start($self, 'description', $fini); + $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and + _get_txt_start($task, '_/text/config/raw', $fini); - $task->{-locked} = $lk->lock_for_scope($$) 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) ]; - start_clone($self, $cmd, $opt, $fini); - } + defined($desc) ? ($task->{'txt.description'} = $desc) : + _get_txt_start($task, 'description', $fini); } sub decode_manifest ($$$) { @@ -470,18 +695,18 @@ sub multi_inbox ($$$) { 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 $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // 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 $self->{-culled_manifest} = 1; @v1 = grep(/$re/, @v1); } if (defined $excl) { - my $re = '(?:'.join('|', map { - $self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/ - } @$excl).')'; + my $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // 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; @@ -510,6 +735,59 @@ sub multi_inbox ($$$) { ($path_pfx, $n, $ret); } +sub clone_all { + my ($self, $m) = @_; + my $todo = delete $self->{todo}; + my $nodep = delete $todo->{''}; + + # do not download unwanted deps + my $any_want = delete $self->{any_want}; + my @unwanted = grep { !$any_want->{$_} } keys %$todo; + my @nodep = delete(@$todo{@unwanted}); + push(@$nodep, @$_) for @nodep; + + # handle no-dependency repos, first + for (@$nodep) { + clone_v1($_, 1); + return if $self->{lei}->{child_error}; + } + # resolve references, deepest, first: + while (scalar keys %$todo) { + for my $x (keys %$todo) { + my ($nr, $nxt); + # resolve multi-level references + while ($m && defined($nxt = $m->{$x}->{reference})) { + exists($todo->{$nxt}) or last; + die < 1000; +E: dependency loop detected (`$x' => `$nxt') +EOM + $x = $nxt; + } + my $y = delete $todo->{$x} // next; # already done + for (@$y) { + clone_v1($_, 1); + return if $self->{lei}->{child_error}; + } + last; # restart %$todo iteration + } + } + do_reap($self, 1); +} + +sub dump_manifest ($$) { + my ($m, $ft) = @_; + # 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 $mtime = (stat($ft))[9]; + seek($ft, SEEK_SET, 0) or die "seek($ft): $!"; + truncate($ft, 0) or die "truncate($ft): $!"; + gzip(\$json => $ft) or die "gzip($ft): $GzipError"; + $ft->flush or die "flush($ft): $!"; + utime($mtime, $mtime, "$ft") or die "utime(..., $ft): $!"; +} + # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz sub try_manifest { my ($self) = @_; @@ -521,23 +799,23 @@ sub try_manifest { $uri->path($path . '/manifest.js.gz'); my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX', UNLINK => 1, TMPDIR => 1, SUFFIX => '.tmp'); - my $fn = $ft->filename; - my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn); + my $cmd = $curl->for_uri($lei, $uri, qw(-f -R -o), $ft->filename); 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 $m = eval { decode_manifest($ft, $fn, $uri) }; + my $m = eval { decode_manifest($ft, $ft, $uri) }; if ($@) { warn $@; return try_scrape($self); } my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m); return $lei->child_error(1, $multi) if !ref($multi); - if (my $v2 = delete $multi->{v2}) { + my $v2 = delete $multi->{v2}; + local $self->{todo} = {}; + if ($v2) { for my $name (sort keys %$v2) { my $epochs = delete $v2->{$name}; my %v2_epochs = map { @@ -558,7 +836,7 @@ sub try_manifest { index($self->{cur_dst}, "\n") >= 0 and die <{cur_dst}' must not contain newline EOM - clone_v2($self, \%v2_epochs, $m); + clone_v2_prep($self, \%v2_epochs, $m); return if $self->{lei}->{child_error}; } } @@ -567,13 +845,12 @@ EOM chop($p) if substr($p, -1, 1) eq '/'; $uri->path($p); 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"); $task->{cur_src} = "$uri"; $task->{cur_dst} = $task->{dst}; + $task->{-key} = $name; if ($n > 1) { $task->{cur_dst} .= $name; $task->{cur_src} .= $name; @@ -582,21 +859,17 @@ EOM E: `$task->{cur_dst}' must not contain newline EOM $task->{cur_src} .= '/'; - clone_v1($task, 1); + my $dep = $task->{-ent}->{reference} // ''; + push @{$self->{todo}->{$dep}}, $task; # for clone_all + $self->{any_want}->{$name} = 1; } } - reap_live() while keys(%LIVE); + delete local $lei->{opt}->{epoch} if defined($v2); + clone_all($self, $m); 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 - # 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): $!"; - } + # set by clone_v2_prep/-I/--exclude + dump_manifest($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 } @@ -607,20 +880,29 @@ 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 $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"; + 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} = $os; } - return start_clone_url($self) if $self->{src} =~ m!://!; - die "TODO: cloning local directories not supported, yet"; + local $LIVE; + my $iv = $lei->{opt}->{'inbox-version'} // + return start_clone_url($self); + return clone_v1($self) if $iv == 1; + die "bad --inbox-version=$iv\n" if $iv != 2; + die <{src} !~ m!://!; +cloning local v2 inboxes not supported +EOM + try_scrape($self, 1); }; $lei->fail($@) if $@; } @@ -670,6 +952,7 @@ help : @echo Rarely needed targets: @echo ' make reindex - may be needed for new features/bugfixes' @echo ' make compact - rewrite Xapian storage to save space' + @echo ' make index - initial index after clone fetch : public-inbox-fetch @@ -686,12 +969,14 @@ update : echo 'public-inbox index not initialized'; \ echo 'see public-inbox-index(1) man page'; \ fi +index : + public-inbox-index reindex : public-inbox-index --reindex compact : public-inbox-compact -.PHONY : help fetch update reindex compact +.PHONY : help fetch update index reindex compact EOM close $fh or die "close($f): $!"; } else {