X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=e284f55deb6133cb25eaaf0113426ff7517434d6;hb=9b285533321b533a5257fd071e4200723c37aa8b;hp=4464b6b109b9bc1884c6a3d1a8cd73d29980927f;hpb=0b6098f90d269a57e04ba1c1d587891acdad4e3f;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index 4464b6b1..e284f55d 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -18,19 +18,24 @@ use PublicInbox::Config; use PublicInbox::Inbox; use PublicInbox::LeiCurl; use PublicInbox::OnDestroy; -use Digest::SHA qw(sha256_hex); +use Digest::SHA qw(sha256_hex sha1_hex); +use POSIX qw(strftime); our $LIVE; # pid => callback +our $FGRP_TODO; # objstore -> [ fgrp mirror objects ] +our $TODO; # reference => [ non-fgrp mirror objects ] + +sub keep_going ($) { + $LIVE && (!$_[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( @@ -47,7 +52,7 @@ sub try_scrape { 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, qw(-f --compressed)); + my $cmd = $curl->for_uri($lei, $uri, '--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): $!"; @@ -147,7 +152,7 @@ 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(-f --compressed -R -o), + my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o), $ft->filename); do_reap($self); $lei->qerr("# @$cmd"); @@ -196,22 +201,14 @@ sub _write_inbox_config { sub set_description ($) { my ($self) = @_; 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): $!"; - my $d = do { local $/; <$fh> } // die "read($f): $!"; - chomp(my $orig = $d); + chomp(my $orig = PublicInbox::Git::try_cat("$dst/description")); + my $d = $orig; while (defined($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}); - 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 $d, "\n" or die "print($f): $!"; - close $fh or die "close($f): $!"; + atomic_write($dst, 'description', $d."\n") if $d ne $orig; } sub index_cloned_inbox { @@ -244,7 +241,6 @@ sub index_cloned_inbox { PublicInbox::Admin::index_inbox($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 { @@ -256,7 +252,7 @@ sub run_reap { $ret; } -sub start_clone { +sub start_cmd { my ($self, $cmd, $opt, $fini) = @_; do_reap($self); $self->{lei}->qerr("# @$cmd"); @@ -275,17 +271,19 @@ sub fetch_args ($$) { push @cmd, '-q' if $lei->{opt}->{quiet} || ($lei->{opt}->{jobs} // 1) > 1; push @cmd, '-v' if $lei->{opt}->{verbose}; + push(@cmd, '-p') if $lei->{opt}->{prune}; @cmd; } sub upr { # feed `git update-ref --stdin -z' verbosely - my ($lei, $w, $op, $ref, $oid) = @_; - $lei->qerr("# $op $ref $oid") if $lei->{opt}->{verbose}; - print $w "$op $ref\0$oid\0" or die "print(w): $!"; + my ($lei, $w, $op, @rest) = @_; # ($ref, $oid) = @rest + $lei->qerr("# $op @rest") if $lei->{opt}->{verbose}; + print $w "$op ", join("\0", @rest, '') or die "print(w): $!"; } sub fgrp_update { my ($fgrp) = @_; + return if !keep_going($fgrp); my $srcfh = delete $fgrp->{srcfh} or return; my $dstfh = delete $fgrp->{dstfh} or return; seek($srcfh, SEEK_SET, 0) or die "seek(src): $!"; @@ -298,15 +296,16 @@ sub fgrp_update { my $cmd = [ 'git', "--git-dir=$fgrp->{cur_dst}", qw(update-ref --stdin -z) ]; my $lei = $fgrp->{lei}; - $lei->qerr("# @$cmd"); - my $opt = { 0 => $r, 1 => $lei->{1}, 2 => $lei->{2} }; - my $pid = spawn($cmd, undef, $opt); + my $pack = PublicInbox::OnDestroy->new($$, \&pack_dst, $fgrp); + start_cmd($fgrp, $cmd, { 0 => $r, 2 => $lei->{2} }, $pack); close $r or die "close(r): $!"; + return if $fgrp->{dry_run}; for my $ref (keys %dst) { 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, $old); } @@ -315,8 +314,6 @@ sub fgrp_update { upr($lei, $w, 'create', $ref, $oid); } close($w) or warn "E: close(update-ref --stdin): $! (need git 1.8.5+)\n"; - my $pack = PublicInbox::OnDestroy->new($$, \&pack_dst, $fgrp); - $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $cmd, $pack ]; } sub pack_dst { # packs lightweight satellite repos @@ -326,54 +323,41 @@ sub pack_dst { # packs lightweight satellite repos sub pack_refs { my ($self, $git_dir) = @_; - do_reap($self); my $cmd = [ 'git', "--git-dir=$git_dir", qw(pack-refs --all --prune) ]; - $self->{lei}->qerr("# @$cmd"); - return if $self->{dry_run}; - my $opt = { 1 => $self->{lei}->{1}, 2 => $self->{lei}->{2} }; - $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $self, $cmd ]; + start_cmd($self, $cmd, { 2 => $self->{lei}->{2} }); } sub fgrpv_done { my ($fgrpv) = @_; return if !$LIVE; - my $pid; my $first = $fgrpv->[0] // die 'BUG: no fgrpv->[0]'; + return if !keep_going($first); pack_refs($first, $first->{-osdir}); # objstore refs always packed for my $fgrp (@$fgrpv) { my $rn = $fgrp->{-remote}; - my %opt = map { $_ => $fgrp->{lei}->{$_} } (0..2); + my %opt = ( 2 => $fgrp->{lei}->{2} ); - my $update_ref = $fgrp->{dry_run} ? undef : - PublicInbox::OnDestroy->new($$, \&fgrp_update, $fgrp); + my $update_ref = PublicInbox::OnDestroy->new($$, + \&fgrp_update, $fgrp); my $src = [ 'git', "--git-dir=$fgrp->{-osdir}", 'for-each-ref', "--format=refs/%(refname:lstrip=3)%00%(objectname)", "refs/remotes/$rn/" ]; - do_reap($fgrp); - $fgrp->{lei}->qerr("# @$src >SRC"); - if ($update_ref) { - open(my $fh, '+>', undef) or die "open(src): $!"; - $pid = spawn($src, undef, { %opt, 1 => $fh }); - $fgrp->{srcfh} = $fh; - $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $src, $update_ref ] - } + open(my $sfh, '+>', undef) or die "open(src): $!"; + $fgrp->{srcfh} = $sfh; + start_cmd($fgrp, $src, { %opt, 1 => $sfh }, $update_ref); my $dst = [ 'git', "--git-dir=$fgrp->{cur_dst}", 'for-each-ref', '--format=%(refname)%00%(objectname)' ]; - do_reap($fgrp); - $fgrp->{lei}->qerr("# @$dst >DST"); - if ($update_ref) { - open(my $fh, '+>', undef) or die "open(dst): $!"; - $pid = spawn($dst, undef, { %opt, 1 => $fh }); - $fgrp->{dstfh} = $fh; - $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $dst, $update_ref ] - } + open(my $dfh, '+>', undef) or die "open(dst): $!"; + $fgrp->{dstfh} = $dfh; + start_cmd($fgrp, $dst, { %opt, 1 => $dfh }, $update_ref); } } sub fgrp_fetch_all { my ($self) = @_; - my $todo = delete $self->{fgrp_todo} or return; + my $todo = $FGRP_TODO; + $FGRP_TODO = \'BUG on further use'; keys(%$todo) or return; # Rely on the fgrptmp remote groups in the config file rather @@ -390,7 +374,6 @@ sub fgrp_fetch_all { qw(--no-tags --multiple)); }; push(@fetch, "-j$j") if $j; - my $pid; while (my ($osdir, $fgrpv) = each %$todo) { my $f = "$osdir/config"; @@ -399,7 +382,7 @@ sub fgrp_fetch_all { $f, '--unset-all', "remotes.$grp"]; $self->{lei}->qerr("# @$cmd"); if (!$self->{dry_run}) { - $pid = spawn($cmd); + my $pid = spawn($cmd, undef, { 2 => $self->{lei}->{2} }); waitpid($pid, 0) // die "waitpid: $!"; die "E: @$cmd: \$?=$?" if ($? && ($? >> 8) != 5); @@ -417,12 +400,8 @@ sub fgrp_fetch_all { } $cmd = [ @git, "--git-dir=$osdir", @fetch, $grp ]; - do_reap($self); - $self->{lei}->qerr("# @$cmd"); my $end = PublicInbox::OnDestroy->new($$, \&fgrpv_done, $fgrpv); - return if $self->{dry_run}; - $pid = spawn($cmd, undef, $opt); - $LIVE->{$pid} = [ \&reap_cmd, $self, $cmd, $end ]; + start_cmd($self, $cmd, $opt, $end); } } @@ -433,10 +412,10 @@ sub forkgroup_prep { 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); @@ -444,15 +423,6 @@ sub forkgroup_prep { } 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}); @@ -479,23 +449,98 @@ sub forkgroup_prep { 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, $cb, @arg) = @_; + return if !keep_going($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 $cb->($self, @arg) if $A ne $B; + $self->{lei}->qerr("# $self->{-key} up-to-date"); +} + +sub cmp_fp_do { + my ($self, $cb, @arg) = @_; + # $cb is either resume_fetch or fgrp_enqueue + $self->{-ent} // return $cb->($self, @arg); + my $new = $self->{-ent}->{fingerprint} // return $cb->($self, @arg); + my $key = $self->{-key} // die 'BUG: no -key'; + if (my $cur_ent = $self->{-local_manifest}->{$key}) { + # runs go_fetch->DESTROY run if eq + return 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($$, \&fp_done, $self, $cb, @arg); + start_cmd($self, $cmd, $opt, $done); +} + +sub resume_fetch { + my ($self, $uri, $fini) = @_; + return if !keep_going($self); + my $dst = $self->{cur_dst} // $self->{dst}; + my @git = ('git', "--git-dir=$dst"); + my $opt = { 2 => $self->{lei}->{2} }; + my $rn = 'origin'; # configurable? + for ("url=$uri", "fetch=+refs/*:refs/*", 'mirror=true') { + my @kv = split(/=/, $_, 2); + $kv[0] = "remote.$rn.$kv[0]"; + next if $self->{dry_run}; + run_die([@git, 'config', @kv], undef, $opt); + } + my $cmd = [ @{$self->{-torsocks}}, @git, + fetch_args($self->{lei}, $opt), $rn ]; + push @$cmd, '-P' if $self->{lei}->{prune}; # --prune-tags implied + start_cmd($self, $cmd, $opt, $fini); +} + +sub fgrp_enqueue { + my ($fgrp, $end) = @_; # $end calls fgrp_fetch_all + return if !keep_going($fgrp); + my $opt = { 2 => $fgrp->{lei}->{2} }; + # --no-tags is required to avoid conflicts + my $u = $fgrp->{-uri} // die 'BUG: no {-uri}'; + my $rn = $fgrp->{-remote} // die 'BUG: no {-remote}'; + my @cmd = ('git', "--git-dir=$fgrp->{-osdir}", 'config'); + for ("url=$u", "fetch=+refs/*:refs/remotes/$rn/*", 'tagopt=--no-tags') { + my @kv = split(/=/, $_, 2); + $kv[0] = "remote.$rn.$kv[0]"; + $fgrp->{dry_run} ? $fgrp->{lei}->qerr("# @cmd @kv") : + run_die([@cmd, @kv], undef, $opt); + } + push @{$FGRP_TODO->{$fgrp->{-osdir}}}, $fgrp; } sub clone_v1 { - my ($self, $nohang) = @_; + my ($self, $end) = @_; my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; my $uri = URI->new($self->{cur_src} // $self->{src}); + my $path = $uri->path; + $path =~ s!/*\z!! and $uri->path($path); defined($lei->{opt}->{epoch}) and die "$uri is a v1 inbox, --epoch is not supported\n"; $self->{-torsocks} //= $curl->torsocks($lei, $uri) or return; my $dst = $self->{cur_dst} // $self->{dst}; my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self); + my $resume = -d $dst; if (my $fgrp = forkgroup_prep($self, $uri)) { $fgrp->{-fini} = $fini; - push @{$self->{fgrp_todo}->{$fgrp->{-osdir}}}, $fgrp; - } else { # normal fetch + $resume ? cmp_fp_do($fgrp, \&fgrp_enqueue, $end) + : fgrp_enqueue($fgrp, $end); + } elsif ($resume) { + cmp_fp_do($self, \&resume_fetch, $uri, $fini); + } else { # normal clone my $cmd = [ @{$self->{-torsocks}}, clone_cmd($lei, my $opt = {}), "$uri", $dst ]; if (defined($self->{-ent})) { @@ -505,7 +550,7 @@ sub clone_v1 { "$self->{dst}$ref"; } } - start_clone($self, $cmd, $opt, $fini); + start_cmd($self, $cmd, $opt, $fini); } if (!$self->{-is_epoch} && $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v1)\z/s) { @@ -514,10 +559,10 @@ sub clone_v1 { my $d = $self->{-ent} ? $self->{-ent}->{description} : undef; $self->{'txt.description'} = $d if defined $d; - (!defined($d) && !$nohang) and + (!defined($d) && !$end) and _get_txt_start($self, 'description', $fini); - $nohang or do_reap($self, 1); # for non-manifest clone + $end or do_reap($self, 1); # for non-manifest clone } sub parse_epochs ($$) { @@ -600,20 +645,101 @@ sub reap_cmd { # async, called via SIGCHLD my ($self, $cmd) = @_; my $cerr = $?; $? = 0; # don't let it influence normal exit - if ($cerr) { - kill('TERM', keys %$LIVE); - $self->{lei}->child_error($cerr, "@$cmd failed"); + $self->{lei}->child_error($cerr, "@$cmd failed (\$?=$cerr)") if $cerr; +} + +sub up_fp_done { + my ($self) = @_; + return if !keep_going($self); + my $fh = delete $self->{-show_ref_up} // die 'BUG: no show-ref output'; + seek($fh, SEEK_SET, 0) or die "seek(show_ref): $!"; + $self->{-ent} // die 'BUG: no -ent'; + my $A = $self->{-ent}->{fingerprint} // die 'BUG: no fingerprint'; + my $B = sha1_hex(do { local $/; <$fh> } // die("read(show_ref): $!")); + return if $A eq $B; + $self->{-ent}->{fingerprint} = $B; + push @{$self->{chg}->{fp_mismatch}}, $self->{-key}; +} + +sub atomic_write ($$$) { + my ($dn, $bn, $raw) = @_; + my $ft = File::Temp->new(DIR => $dn, TEMPLATE => "$bn-XXXX"); + print $ft $raw or die "print($ft): $!"; + $ft->flush or die "flush($ft): $!"; + ft_rename($ft, "$dn/$bn", 0666); +} + +# modifies the to-be-written manifest entry, and sets values from it, too +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}->{head}; + $cur = $self->{-local_manifest}->{$key}->{head} // "\0"; + if (defined($new) && $new ne $cur) { + # n.b. grokmirror writes raw contents to $dst/HEAD w/o locking + my $cmd = [ 'git', "--git-dir=$dst" ]; + if ($new =~ s/\Aref: //) { + push @$cmd, qw(symbolic-ref HEAD), $new; + } elsif ($new =~ /\A[a-f0-9]{40,}\z/) { + push @$cmd, qw(update-ref --no-deref HEAD), $new; + } else { + undef $cmd; + warn "W: $key: {head} => `$new' not understood\n"; + } + start_cmd($self, $cmd, { 2 => $self->{lei}->{2} }) if $cmd; + } + if (my $symlinks = $self->{-ent}->{symlinks}) { + my $top = File::Spec->rel2abs($self->{dst}); + for my $p (@$symlinks) { + my $ln = "$top/$p"; + $ln =~ tr!/!/!s; + my (undef, $dn, $bn) = File::Spec->splitpath($ln); + File::Path::mkpath($dn); + my $tgt = "$top/$key"; + $tgt = File::Spec->abs2rel($tgt, $dn); + if (lstat($ln)) { + if (-l _) { + next if readlink($ln) eq $tgt; + unlink($ln) or die "unlink($ln): $!"; + } else { + push @{$self->{chg}->{badlink}}, $p; + } + } + symlink($tgt, $ln) or die "symlink($tgt, $ln): $!"; + } + } + if (defined(my $t = $self->{-ent}->{modified})) { + my ($dn, $bn) = ("$dst/info/web", 'last-modified'); + my $orig = PublicInbox::Git::try_cat("$dn/$bn"); + $t = strftime('%F %T', gmtime($t))." +0000\n"; + File::Path::mkpath($dn); + atomic_write($dn, $bn, $t) if $orig ne $t; + } + + $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); @@ -641,7 +767,7 @@ sub v1_done { # called via OnDestroy 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'; @@ -671,7 +797,6 @@ sub clone_v2_prep ($$;$) { my $dst = $self->{cur_dst} // $self->{dst}; my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); my $task = $m ? bless { %$self }, __PACKAGE__ : $self; - delete $task->{todo}; # $self->{todo} still exists my (@skip, $desc); my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); for my $nr (sort { $a <=> $b } keys %$v2_epochs) { @@ -699,7 +824,7 @@ failed to extract epoch number from $src $etask->{cur_dst} = $edst; $etask->{-is_epoch} = $fini; my $ref = $ent->{reference} // ''; - push @{$self->{todo}->{$ref}}, $etask; + push @{$TODO->{$ref}}, $etask; $self->{any_want}->{$key} = 1; } else { # create a placeholder so users only need to chmod +w init_placeholder($src, $edst, $ent); @@ -708,7 +833,7 @@ failed to extract epoch number from $src } } # filter out the epochs we skipped - $self->{-culled_manifest} = 1 if $m && delete(@$m{@skip}); + $self->{chg}->{manifest} = 1 if $m && delete(@$m{@skip}); (!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst); @@ -731,6 +856,19 @@ sub decode_manifest ($$$) { $m; } +sub load_current_manifest ($) { + 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 ($$$) { my ($self, $path, $m) = @_; my $incl = $self->{lei}->{opt}->{include}; @@ -752,8 +890,8 @@ sub multi_inbox ($$$) { $self->{lei}->glob2re($_) // 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) { @@ -761,8 +899,8 @@ sub multi_inbox ($$$) { $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ } @$excl).'\\z)'; my @gone = delete @$v2{grep(/$re/, keys %$v2)}; - delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1; - delete @$m{grep(/$re/, @v1)} and $self->{-culled_manifest} = 1; + delete @$m{map { @$_ } @gone} and $self->{chg}->{manifest} = 1; + delete @$m{grep(/$re/, @v1)} and $self->{chg}->{manifest} = 1; @v1 = grep(!/$re/, @v1); } my $ret; # { v1 => [ ... ], v2 => { "/$inbox_name" => [ epochs ] }} @@ -790,19 +928,23 @@ sub multi_inbox ($$$) { 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}; + my $todo = $TODO; + $TODO = \'BUG on further use'; + my $end = PublicInbox::OnDestroy->new($$, \&fgrp_fetch_all, $self); + { + 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($_, $end); + return if !keep_going($self); + } } # resolve references, deepest, first: while (scalar keys %$todo) { @@ -818,13 +960,16 @@ EOM } my $y = delete $todo->{$x} // next; # already done for (@$y) { - clone_v1($_, 1); - return if $self->{lei}->{child_error}; + clone_v1($_, $end); + return if !keep_going($self); } last; # restart %$todo iteration } } - fgrp_fetch_all($self); + + # $end->DESTROY will call fgrp_fetch_all once all references + # in $LIVE are gone, and do_reap will eventually drain $LIVE + $end = undef; do_reap($self, 1); } @@ -852,25 +997,36 @@ sub try_manifest { 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 $cmd = $curl->for_uri($lei, $uri, qw(-f -R -o), $ft->filename); - my %opt = map { $_ => $lei->{$_} } (0..2); + 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(-R -o), $ft->filename); + push(@$cmd, '-z', $manifest) if -f $manifest; + 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 return $lei->child_error($cerr, "@$cmd failed"); } + + # bail out if curl -z/--timecond hit 304 Not Modified, $ft will be empty + return $lei->qerr("# $manifest unchanged") if -f $manifest && !-s $ft; + my $m = eval { decode_manifest($ft, $ft, $uri) }; if ($@) { 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}; - local $self->{todo} = {}; - local $self->{fgrp_todo} = {}; # { objstore_dir => [fgrp, ...] } if ($v2) { for my $name (sort keys %$v2) { my $epochs = delete $v2->{$name}; @@ -893,7 +1049,7 @@ sub try_manifest { 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 $multi->{v1}) { @@ -916,18 +1072,35 @@ E: `$task->{cur_dst}' must not contain newline EOM $task->{cur_src} .= '/'; my $dep = $task->{-ent}->{reference} // ''; - push @{$self->{todo}->{$dep}}, $task; # for clone_all + push @{$TODO->{$dep}}, $task; # for clone_all $self->{any_want}->{$name} = 1; } } 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]; + $t = strftime('%F %k:%M:%S %z', localtime($t)); + warn <{lei}->{opt}->{prune}; +W: The above fingerprints may never match without --prune +EOM + } + dump_manifest($m => $ft) if delete($self->{chg}->{manifest}) || $mis; + my $bad = delete $self->{chg}->{badlink}; + warn(<{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 = {}; + local $TODO = {}; + local $FGRP_TODO = {}; my $iv = $lei->{opt}->{'inbox-version'} // return start_clone_url($self); return clone_v1($self) if $iv == 1;