X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=33cf55aba2536dfc0f3d298cea9a8849e42a0a06;hb=eb22c4833d455b655b42b492dfad7f2abfc83203;hp=fc5bc88d86acba0edff1f3c68c13ed9caf93a0a6;hpb=3f36a5060302417a24a1fbacd8860a620298485c;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index fc5bc88d..33cf55ab 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -19,8 +19,11 @@ use PublicInbox::Inbox; use PublicInbox::LeiCurl; use PublicInbox::OnDestroy; 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} || @@ -49,7 +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): $!"; @@ -149,7 +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"); @@ -178,13 +181,16 @@ sub _write_inbox_config { my $buf = delete($self->{'txt._/text/config/raw'}) // return; my $dst = $self->{cur_dst} // $self->{dst}; my $f = "$dst/inbox.config.example"; - open my $fh, '>', $f or die "open($f): $!"; - print $fh $buf or die "print: $!"; - chmod(0444 & ~umask, $fh) or die "chmod($f): $!"; my $mtime = delete $self->{'mtime._/text/config/raw'}; - $fh->flush or die "flush($f): $!"; - if (defined $mtime) { - utime($mtime, $mtime, $fh) or die "utime($f): $!"; + if (sysopen(my $fh, $f, O_CREAT|O_EXCL|O_WRONLY)) { + print $fh $buf or die "print: $!"; + chmod(0444 & ~umask, $fh) or die "chmod($f): $!"; + $fh->flush or die "flush($f): $!"; + if (defined $mtime) { + utime($mtime, $mtime, $fh) or die "utime($f): $!"; + } + } elsif (!$!{EEXIST}) { + die "open($f): $!"; } my $cfg = PublicInbox::Config->git_config_dump($f, $self->{lei}->{2}); my $ibx = $self->{ibx} = {}; @@ -198,22 +204,14 @@ sub _write_inbox_config { sub set_description ($) { 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 $orig; } sub index_cloned_inbox { @@ -324,7 +322,6 @@ sub fgrp_update { sub pack_dst { # packs lightweight satellite repos my ($fgrp) = @_; pack_refs($fgrp, $fgrp->{cur_dst}); - delete($fgrp->{-fini}) // die 'BUG: no {-fini}'; # call v1_done } sub pack_refs { @@ -362,7 +359,8 @@ sub fgrpv_done { 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 @@ -381,6 +379,7 @@ sub fgrp_fetch_all { push(@fetch, "-j$j") if $j; while (my ($osdir, $fgrpv) = each %$todo) { my $f = "$osdir/config"; + return if !keep_going($self); # clobber group from previous run atomically my $cmd = ['git', "--git-dir=$osdir", qw(config -f), @@ -429,20 +428,9 @@ sub forkgroup_prep { my $key = $self->{-key} // die 'BUG: no -key'; 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"; - 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): $!"; - $f = "$self->{cur_dst}/config"; - open $fh, '+>>', $f or die "open:($f): $!"; + my $f = "$self->{cur_dst}/config"; + open my $fh, '+>>', $f or die "open:($f): $!"; print $fh <{dry_run}) { + my $alt = File::Spec->rel2abs("$dir/objects"); + 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): $!"; + } bless { %$self, -osdir => $dir, -remote => $rn, -uri => $uri }, __PACKAGE__; @@ -510,7 +511,7 @@ sub resume_fetch { } sub fgrp_enqueue { - my ($fgrp) = @_; + 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 @@ -523,15 +524,16 @@ sub fgrp_enqueue { $fgrp->{dry_run} ? $fgrp->{lei}->qerr("# @cmd @kv") : run_die([@cmd, @kv], undef, $opt); } - $fgrp->{fgrp_todo} // die 'BUG: no fgrp_todo'; - push @{$fgrp->{fgrp_todo}->{$fgrp->{-osdir}}}, $fgrp; + push @{$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; @@ -540,7 +542,8 @@ sub clone_v1 { my $resume = -d $dst; if (my $fgrp = forkgroup_prep($self, $uri)) { $fgrp->{-fini} = $fini; - $resume ? cmp_fp_do($fgrp, \&fgrp_enqueue) : fgrp_enqueue($fgrp) + $resume ? cmp_fp_do($fgrp, \&fgrp_enqueue, $end) + : fgrp_enqueue($fgrp, $end); } elsif ($resume) { cmp_fp_do($self, \&resume_fetch, $uri, $fini); } else { # normal clone @@ -562,10 +565,10 @@ 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 ($$) { @@ -664,6 +667,15 @@ sub up_fp_done { push @{$self->{chg}->{fp_mismatch}}, $self->{-key}; } +sub atomic_write ($$$) { + 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'; @@ -678,7 +690,6 @@ sub update_ent { my $done = PublicInbox::OnDestroy->new($$, \&up_fp_done, $self); start_cmd($self, $cmd, $opt, $done); } - $new = $self->{-ent}->{head}; $cur = $self->{-local_manifest}->{$key}->{head} // "\0"; if (defined($new) && $new ne $cur) { @@ -694,6 +705,33 @@ sub update_ent { } start_cmd($self, $cmd, { 2 => $self->{lei}->{2} }) if $cmd; } + if (my $symlinks = $self->{-ent}->{symlinks}) { + my $top = File::Spec->rel2abs($self->{dst}); + for my $p (@$symlinks) { + my $ln = "$top/$p"; + $ln =~ tr!/!/!s; + my (undef, $dn, $bn) = File::Spec->splitpath($ln); + File::Path::mkpath($dn); + my $tgt = "$top/$key"; + $tgt = File::Spec->abs2rel($tgt, $dn); + if (lstat($ln)) { + if (-l _) { + next if readlink($ln) eq $tgt; + unlink($ln) or die "unlink($ln): $!"; + } else { + push @{$self->{chg}->{badlink}}, $p; + } + } + symlink($tgt, $ln) or die "symlink($tgt, $ln): $!"; + } + } + if (defined(my $t = $self->{-ent}->{modified})) { + my ($dn, $bn) = ("$dst/info/web", 'last-modified'); + my $orig = PublicInbox::Git::try_cat("$dn/$bn"); + $t = strftime('%F %T', gmtime($t))." +0000\n"; + File::Path::mkpath($dn); + atomic_write($dn, $bn, $t) if $orig ne $t; + } $new = $self->{-ent}->{owner} // return; $cur = $self->{-local_manifest}->{$key}->{owner} // "\0"; @@ -765,7 +803,6 @@ sub clone_v2_prep ($$;$) { 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($$, \&v2_done, $task); for my $nr (sort { $a <=> $b } keys %$v2_epochs) { @@ -793,7 +830,7 @@ failed to extract epoch number from $src $etask->{cur_dst} = $edst; $etask->{-is_epoch} = $fini; my $ref = $ent->{reference} // ''; - push @{$self->{todo}->{$ref}}, $etask; + push @{$TODO->{$ref}}, $etask; $self->{any_want}->{$key} = 1; } else { # create a placeholder so users only need to chmod +w init_placeholder($src, $edst, $ent); @@ -897,7 +934,9 @@ sub multi_inbox ($$$) { sub clone_all { my ($self, $m) = @_; - my $todo = delete $self->{todo}; + my $todo = $TODO; + $TODO = \'BUG on further use'; + my $end = PublicInbox::OnDestroy->new($$, \&fgrp_fetch_all, $self); { my $nodep = delete $todo->{''}; @@ -909,7 +948,7 @@ sub clone_all { # handle no-dependency repos, first for (@$nodep) { - clone_v1($_, 1); + clone_v1($_, $end); return if !keep_going($self); } } @@ -927,14 +966,16 @@ EOM } my $y = delete $todo->{$x} // next; # already done for (@$y) { - clone_v1($_, 1); + clone_v1($_, $end); return if !keep_going($self); } last; # restart %$todo iteration } } - do_reap($self, 1); # finish all fingerprint checks - fgrp_fetch_all($self); + + # $end->DESTROY will call fgrp_fetch_all once all references + # in $LIVE are gone, and do_reap will eventually drain $LIVE + $end = undef; do_reap($self, 1); } @@ -952,6 +993,34 @@ sub dump_manifest ($$) { utime($mtime, $mtime, "$ft") or die "utime(..., $ft): $!"; } +sub dump_project_list ($$) { + my ($self, $m) = @_; + my $f = $self->{'-project-list'} // return; + my $old = PublicInbox::Git::try_cat($f); + my %new; + + open my $dh, '<', '.' or die "open(.): $!"; + chdir($self->{dst}) or die "chdir($self->{dst}): $!"; + my @local = grep { -e $_ ? ($new{$_} = undef) : 1 } split(/\n/s, $old); + chdir($dh) or die "chdir(restore): $!"; + + $new{substr($_, 1)} = 1 for keys %$m; # drop leading '/' + my @list = sort keys %new; + my @remote = grep { !defined($new{$_}) } @list; + + warn <{src}: +EOM + warn "\t", $_, "\n" for @remote; + warn <splitpath($f); + atomic_write($dn, $bn, join("\n", @list, '')); +} + # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz sub try_manifest { my ($self) = @_; @@ -969,7 +1038,8 @@ sub try_manifest { 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 $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, $cmd, \%opt); @@ -977,6 +1047,10 @@ sub try_manifest { return try_scrape($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 $@; @@ -987,8 +1061,6 @@ sub try_manifest { my ($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}; @@ -1034,7 +1106,7 @@ 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; } } @@ -1046,8 +1118,7 @@ EOM 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)); + $t = strftime('%F %k:%M:%S %z', localtime($t)); warn < $ft) if delete($self->{chg}->{manifest}) || $mis; + my $bad = delete $self->{chg}->{badlink}; + warn(<{opt}->{$k} // next; $v = $default if $v eq ''; $v = "$self->{dst}/$v" if $v !~ m!\A\.{0,2}/!; $self->{"-$k"} = $v; } + 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;