diff options
Diffstat (limited to 'lib/PublicInbox/LeiMirror.pm')
-rw-r--r-- | lib/PublicInbox/LeiMirror.pm | 510 |
1 files changed, 317 insertions, 193 deletions
diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index 33cf55ab..e7c265bd 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -7,32 +7,37 @@ 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 PublicInbox::Spawn qw(spawn run_wait run_die run_qx); +use PublicInbox::IO qw(write_file); 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; -use PublicInbox::Config; +use PublicInbox::Config qw(glob2re); use PublicInbox::Inbox; use PublicInbox::LeiCurl; use PublicInbox::OnDestroy; -use Digest::SHA qw(sha256_hex sha1_hex); +use PublicInbox::SHA qw(sha256_hex sha_all); use POSIX qw(strftime); +use PublicInbox::Admin qw(fmt_localtime); +use autodie qw(chdir chmod close open pipe readlink + seek symlink sysopen sysseek truncate unlink); +use PublicInbox::Git qw(git_exe); our $LIVE; # pid => callback -our $FGRP_TODO; # objstore -> [ fgrp mirror objects ] +our $FGRP_TODO; # objstore -> [[ to resume ], [ to clone ]] our $TODO; # reference => [ non-fgrp mirror objects ] +our @PUH; # post-update hooks sub keep_going ($) { $LIVE && (!$_[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; +sub _wq_done_wait { # awaitpid cb (via wq_eof) + my ($pid, $mrr, $lei) = @_; if ($?) { $lei->child_error($?); } elsif (!$lei->{child_error}) { @@ -54,9 +59,8 @@ sub try_scrape { my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; 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): $!"; - close($fh) or return $lei->child_error($?, "@$cmd failed"); + my $html = run_qx($cmd, undef, $opt); + return $lei->child_error($?, "@$cmd failed") if $?; # we grep with URL below, we don't want Subject/From headers # making us clone random URLs. This assumes remote instances @@ -102,7 +106,7 @@ E: confused by scraping <$uri>, got ambiguous results: sub clone_cmd { my ($lei, $opt) = @_; - my @cmd = qw(git); + my @cmd = (git_exe); $opt->{$_} = $lei->{$_} 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 @@ -121,7 +125,7 @@ sub ft_rename ($$$;$) { my ($ft, $dst, $open_mode, $fh) = @_; my @st = stat($fh // $dst); my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask); - chmod($mode, $ft) or croak "E: chmod($ft): $!"; + chmod($mode, $ft); require File::Copy; File::Copy::mv($ft->filename, $dst) or croak "E: mv($ft => $dst): $!"; $ft->unlink_on_destroy(0); @@ -169,10 +173,9 @@ sub _get_txt_done { # returns true on error (non-fatal), undef on success $? = 0; # don't influence normal lei exit return warn("$uri missing\n") if ($cerr >> 8) == 22; return warn("# @$cmd failed (non-fatal)\n") if $cerr; - seek($fh, SEEK_SET, 0) or die "seek: $!"; + seek($fh, 0, SEEK_SET); $self->{"mtime.$endpoint"} = (stat($fh))[9]; - local $/; - $self->{"txt.$endpoint"} = <$fh>; + $self->{"txt.$endpoint"} = PublicInbox::IO::read_all $fh, -s _; undef; # success } @@ -182,9 +185,9 @@ sub _write_inbox_config { my $dst = $self->{cur_dst} // $self->{dst}; my $f = "$dst/inbox.config.example"; my $mtime = delete $self->{'mtime._/text/config/raw'}; - 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): $!"; + if (CORE::sysopen(my $fh, $f, O_CREAT|O_EXCL|O_WRONLY)) { + print $fh $buf; + chmod(0444 & ~umask, $fh); $fh->flush or die "flush($f): $!"; if (defined $mtime) { utime($mtime, $mtime, $fh) or die "utime($f): $!"; @@ -192,8 +195,9 @@ sub _write_inbox_config { } elsif (!$!{EEXIST}) { die "open($f): $!"; } - my $cfg = PublicInbox::Config->git_config_dump($f, $self->{lei}->{2}); - my $ibx = $self->{ibx} = {}; + my $cfg = PublicInbox::Config->git_config_dump($f, + { 2 => $self->{lei}->{2} }); + my $ibx = $self->{ibx} = {}; # for indexing for my $sec (grep(/\Apublicinbox\./, @{$cfg->{-section_order}})) { for (qw(address newsgroup nntpmirror)) { $ibx->{$_} = $cfg->{"$sec.$_"}; @@ -204,7 +208,7 @@ sub _write_inbox_config { sub set_description ($) { my ($self) = @_; my $dst = $self->{cur_dst} // $self->{dst}; - chomp(my $orig = PublicInbox::Git::try_cat("$dst/description")); + chomp(my $orig = PublicInbox::IO::try_cat("$dst/description")); my $d = $orig; while (defined($d) && ($d =~ m!^\(\$INBOX_DIR/description missing\)! || $d =~ /^Unnamed repository/ || $d !~ /\S/)) { @@ -235,9 +239,9 @@ sub index_cloned_inbox { my ($k) = ($sw =~ /\A([\w-]+)/); $opt->{$k} = $lei->{opt}->{$k}; } - # force synchronous dwaitpid for v2: + # force synchronous awaitpid for v2: local $PublicInbox::DS::in_loop = 0; - my $cfg = PublicInbox::Config->new(undef, $lei->{2}); + my $cfg = PublicInbox::Config->new(undef, { 2 => $lei->{2} }); my $env = PublicInbox::Admin::index_prepare($opt, $cfg); local %ENV = (%ENV, %$env) if $env; PublicInbox::Admin::progress_prepare($opt, $lei->{2}); @@ -249,8 +253,7 @@ sub index_cloned_inbox { sub run_reap { my ($lei, $cmd, $opt) = @_; $lei->qerr("# @$cmd"); - waitpid(spawn($cmd, undef, $opt), 0) // die "waitpid: $!"; - my $ret = $?; + my $ret = run_wait($cmd, undef, $opt); $? = 0; # don't let it influence normal exit $ret; } @@ -275,6 +278,8 @@ sub fetch_args ($$) { ($lei->{opt}->{jobs} // 1) > 1; push @cmd, '-v' if $lei->{opt}->{verbose}; push(@cmd, '-p') if $lei->{opt}->{prune}; + PublicInbox::Git::git_version() ge v2.29.0 and + push(@cmd, '--no-write-fetch-head'); @cmd; } @@ -284,25 +289,32 @@ sub upr { # feed `git update-ref --stdin -z' verbosely print $w "$op ", join("\0", @rest, '') or die "print(w): $!"; } +sub start_update_ref { + my ($fgrp) = @_; + pipe(my $r, my $w); + my $cmd = [ git_exe, "--git-dir=$fgrp->{cur_dst}", + qw(update-ref --stdin -z) ]; + my $pack = on_destroy \&satellite_done, $fgrp; + start_cmd($fgrp, $cmd, { 0 => $r, 2 => $fgrp->{lei}->{2} }, $pack); + close $r; + $fgrp->{dry_run} ? undef : $w; +} + +sub upref_warn { warn "E: close(update-ref --stdin): $! (need git 1.8.5+)\n" } + sub fgrp_update { my ($fgrp) = @_; return if !keep_going($fgrp); my $srcfh = delete $fgrp->{srcfh} or return; my $dstfh = delete $fgrp->{dstfh} or return; - seek($srcfh, SEEK_SET, 0) or die "seek(src): $!"; - seek($dstfh, SEEK_SET, 0) or die "seek(dst): $!"; - my %src = map { chomp; split(/\0/) } (<$srcfh>); - close $srcfh; - my %dst = map { chomp; split(/\0/) } (<$dstfh>); - close $dstfh; - pipe(my ($r, $w)) or die "pipe: $!"; - my $cmd = [ 'git', "--git-dir=$fgrp->{cur_dst}", - qw(update-ref --stdin -z) ]; + seek($srcfh, 0, SEEK_SET); + seek($dstfh, 0, SEEK_SET); + my %src = map { chomp; split /\0/ } PublicInbox::IO::read_all $srcfh; + my %dst = map { chomp; split /\0/ } PublicInbox::IO::read_all $dstfh; + $srcfh = $dstfh = undef; + my $w = start_update_ref($fgrp) or return; my $lei = $fgrp->{lei}; - my $pack = PublicInbox::OnDestroy->new($$, \&pack_dst, $fgrp); - start_cmd($fgrp, $cmd, { 0 => $r, 2 => $lei->{2} }, $pack); - close $r or die "close(r): $!"; - return if $fgrp->{dry_run}; + my $ndel; for my $ref (keys %dst) { my $new = delete $src{$ref}; my $old = $dst{$ref}; @@ -311,47 +323,68 @@ sub fgrp_update { upr($lei, $w, 'update', $ref, $new, $old); } else { upr($lei, $w, 'delete', $ref, $old); + ++$ndel; } } - while (my ($ref, $oid) = each %src) { - upr($lei, $w, 'create', $ref, $oid); + # git's ref files backend doesn't allow directory/file conflicts + # between `delete' and `create' ops: + if ($ndel && scalar(keys %src)) { + $fgrp->{-create_refs} = \%src; + } else { + while (my ($ref, $oid) = each %src) { + upr($lei, $w, 'create', $ref, $oid); + } } - close($w) or warn "E: close(update-ref --stdin): $! (need git 1.8.5+)\n"; + $w->close or upref_warn(); } -sub pack_dst { # packs lightweight satellite repos +sub satellite_done { my ($fgrp) = @_; - pack_refs($fgrp, $fgrp->{cur_dst}); + if (my $create = delete $fgrp->{-create_refs}) { + my $w = start_update_ref($fgrp) or return; + while (my ($ref, $oid) = each %$create) { + upr($fgrp->{lei}, $w, 'create', $ref, $oid); + } + $w->close or upref_warn(); + } else { + pack_refs($fgrp, $fgrp->{cur_dst}); + run_puh($fgrp); + } } sub pack_refs { my ($self, $git_dir) = @_; - my $cmd = [ 'git', "--git-dir=$git_dir", qw(pack-refs --all --prune) ]; + my $cmd = [git_exe, "--git-dir=$git_dir", qw(pack-refs --all --prune)]; start_cmd($self, $cmd, { 2 => $self->{lei}->{2} }); } +sub unlink_fetch_head ($) { + my ($git_dir) = @_; + return if CORE::unlink("$git_dir/FETCH_HEAD") || $!{ENOENT}; + warn "W: unlink($git_dir/FETCH_HEAD): $!"; +} + sub fgrpv_done { my ($fgrpv) = @_; return if !$LIVE; my $first = $fgrpv->[0] // die 'BUG: no fgrpv->[0]'; return if !keep_going($first); + unlink_fetch_head($first->{-osdir}) if !$first->{dry_run}; pack_refs($first, $first->{-osdir}); # objstore refs always packed for my $fgrp (@$fgrpv) { my $rn = $fgrp->{-remote}; my %opt = ( 2 => $fgrp->{lei}->{2} ); - - my $update_ref = PublicInbox::OnDestroy->new($$, - \&fgrp_update, $fgrp); - - my $src = [ 'git', "--git-dir=$fgrp->{-osdir}", 'for-each-ref', + my $update_ref = on_destroy \&fgrp_update, $fgrp; + my $src = [ git_exe, "--git-dir=$fgrp->{-osdir}", + 'for-each-ref', "--format=refs/%(refname:lstrip=3)%00%(objectname)", "refs/remotes/$rn/" ]; - open(my $sfh, '+>', undef) or die "open(src): $!"; + open(my $sfh, '+>', undef); $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)' ]; - open(my $dfh, '+>', undef) or die "open(dst): $!"; + my $dst = [ git_exe, "--git-dir=$fgrp->{cur_dst}", + 'for-each-ref', '--format=%(refname)%00%(objectname)' ]; + open(my $dfh, '+>', undef); $fgrp->{dstfh} = $dfh; start_cmd($fgrp, $dst, { %opt, 1 => $dfh }, $update_ref); } @@ -368,43 +401,72 @@ sub fgrp_fetch_all { # system argv limits: my $grp = 'fgrptmp'; - my @git = (@{$self->{-torsocks}}, 'git'); + my @git = (@{$self->{-torsocks}}, git_exe); my $j = $self->{lei}->{opt}->{jobs}; my $opt = {}; my @fetch = do { local $self->{lei}->{opt}->{jobs} = 1; - (fetch_args($self->{lei}, $opt), - qw(--no-tags --multiple)); + (fetch_args($self->{lei}, $opt), qw(--no-tags --multiple)); }; push(@fetch, "-j$j") if $j; - while (my ($osdir, $fgrpv) = each %$todo) { + while (my ($osdir, $fgrp_old_new) = each %$todo) { my $f = "$osdir/config"; return if !keep_going($self); + my ($old, $new) = @$fgrp_old_new; + @$old = sort { $b->{-sort} <=> $a->{-sort} } @$old; + # $new is ordered by {references} + my $cmd = [ git_exe, "--git-dir=$osdir", qw(config -f), $f ]; + + # clobber settings from previous run atomically + for ("remotes.$grp", 'fetch.hideRefs') { + my $c = [ @$cmd, '--unset-all', $_ ]; + $self->{lei}->qerr("# @$c"); + next if $self->{dry_run}; + run_wait($c, undef, $opt); + die "E: @$c \$?=$?" if ($? && ($? >> 8) != 5); + } - # clobber group from previous run atomically - my $cmd = ['git', "--git-dir=$osdir", qw(config -f), - $f, '--unset-all', "remotes.$grp"]; - $self->{lei}->qerr("# @$cmd"); - if (!$self->{dry_run}) { - my $pid = spawn($cmd, undef, { 2 => $self->{lei}->{2} }); - waitpid($pid, 0) // die "waitpid: $!"; - die "E: @$cmd: \$?=$?" if ($? && ($? >> 8) != 5); + # permanent configs: + my $cfg = PublicInbox::Config->git_config_dump($f); + for my $fgrp (@$old, @$new) { + my $u = $fgrp->{-uri} // die 'BUG: no {-uri}'; + my $rn = $fgrp->{-remote} // die 'BUG: no {-remote}'; + for ("url=$u", "fetch=+refs/*:refs/remotes/$rn/*", + 'tagopt=--no-tags') { + my ($k, $v) = split(/=/, $_, 2); + $k = "remote.$rn.$k"; + next if ($cfg->{$k} // '') eq $v; + my $c = [@$cmd, $k, $v]; + $fgrp->{lei}->qerr("# @$c"); + next if $fgrp->{dry_run}; + run_die($c, undef, $opt); + } + } + if (!$self->{dry_run}) { # update the config atomically via O_APPEND while # respecting git-config locking - sysopen(my $lk, "$f.lock", O_CREAT|O_EXCL|O_WRONLY) - or die "open($f.lock): $!"; - open my $fh, '>>', $f or die "open(>>$f): $!"; + sysopen(my $lk, "$f.lock", O_CREAT|O_EXCL|O_WRONLY); + open my $fh, '>>', $f; $fh->autoflush(1); - my $buf = join('', "[remotes]\n", - map { "\t$grp = $_->{-remote}\n" } @$fgrpv); + my $buf = ''; + if (@$old) { + $buf = "[fetch]\n\thideRefs = refs\n"; + $buf .= join('', map { + "\thideRefs = !refs/remotes/" . + "$_->{-remote}/\n"; + } @$old); + } + $buf .= join('', "[remotes]\n", + (map { "\t$grp = $_->{-remote}\n" } @$old), + (map { "\t$grp = $_->{-remote}\n" } @$new)); print $fh $buf or die "print($f): $!"; - close $fh or die "close($f): $!"; - unlink("$f.lock") or die "unlink($f.lock): $!"; + close $fh; + unlink("$f.lock"); } - - $cmd = [ @git, "--git-dir=$osdir", @fetch, $grp ]; - my $end = PublicInbox::OnDestroy->new($$, \&fgrpv_done, $fgrpv); + $cmd = [ @git, "--git-dir=$osdir", @fetch, $grp ]; + push @$old, @$new; + my $end = on_destroy \&fgrpv_done, $old; start_cmd($self, $cmd, $opt, $end); } } @@ -418,20 +480,18 @@ sub forkgroup_prep { my $dir = "$os/$fg.git"; 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, $opt); - } + write_file '+>>', "$dir/config", <<EOM; +[repack] + useDeltaIslands = true +[pack] + island = refs/remotes/([^/]+)/ +EOM } my $key = $self->{-key} // die 'BUG: no -key'; my $rn = substr(sha256_hex($key), 0, 16); if (!-d $self->{cur_dst} && !$self->{dry_run}) { PublicInbox::Import::init_bare($self->{cur_dst}); - my $f = "$self->{cur_dst}/config"; - open my $fh, '+>>', $f or die "open:($f): $!"; - print $fh <<EOM or die "print($f): $!"; + write_file '+>>', "$self->{cur_dst}/config", <<EOM; ; rely on the "$rn" remote in the ; $fg fork group for fetches ; only uncomment the following iff you detach from fork groups @@ -440,20 +500,16 @@ sub forkgroup_prep { ; fetch = +refs/*:refs/* ; mirror = true EOM - close $fh or die "close($f): $!"; } if (!$self->{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): $!"; + open my $fh, '+>>', my $f = "$o/info/alternates"; + seek($fh, 0, SEEK_SET); # Perl did SEEK_END when it saw '>>' + my $seen = grep /\A\Q$l\E\n/, PublicInbox::IO::read_all $fh; + print $fh "$l\n" if !$seen; + close $fh; } bless { %$self, -osdir => $dir, -remote => $rn, -uri => $uri @@ -461,13 +517,17 @@ EOM } sub fp_done { - my ($self, $cb, @arg) = @_; + my ($self, $cmd, $cb, @arg) = @_; + if ($?) { + $self->{lei}->err("@$cmd failed (\$?=$?) (non-fatal)"); + $? = 0; # don't let it influence normal exit + } return if !keep_going($self); my $fh = delete $self->{-show_ref} // die 'BUG: no show-ref output'; - seek($fh, SEEK_SET, 0) or die "seek(show_ref): $!"; + sysseek($fh, 0, SEEK_SET); $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): $!")); + my $B = sha_all(1, $fh)->hexdigest; return $cb->($self, @arg) if $A ne $B; $self->{lei}->qerr("# $self->{-key} up-to-date"); } @@ -483,48 +543,40 @@ sub cmp_fp_do { return if $cur_ent->{fingerprint} eq $new; } my $dst = $self->{cur_dst} // $self->{dst}; - my $cmd = ['git', "--git-dir=$dst", 'show-ref']; + my $cmd = [git_exe, "--git-dir=$dst", 'show-ref']; my $opt = { 2 => $self->{lei}->{2} }; - open($opt->{1}, '+>', undef) or die "open(tmp): $!"; + open($opt->{1}, '+>', undef); $self->{-show_ref} = $opt->{1}; - my $done = PublicInbox::OnDestroy->new($$, \&fp_done, $self, $cb, @arg); - start_cmd($self, $cmd, $opt, $done); + do_reap($self); + $self->{lei}->qerr("# @$cmd"); + $LIVE->{spawn($cmd, undef, $opt)} = [ \&fp_done, $self, $cmd, + $cb, @arg ]; } 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 @git = (git_exe, "--git-dir=$dst"); my $opt = { 2 => $self->{lei}->{2} }; - my $rn = 'origin'; # configurable? + my $rn = 'random'.int(rand(1 << 30)); 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); + push @git, '-c', "remote.$rn.$_"; } 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); + my $run_puh = on_destroy \&run_puh, $self, $fini; + ++$self->{chg}->{nr_chg}; + start_cmd($self, $cmd, $opt, $run_puh); } 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; + ++$fgrp->{chg}->{nr_chg}; + my $dst = $FGRP_TODO->{$fgrp->{-osdir}} //= [ [], [] ]; # [ old, new ] + push @{$dst->[defined($fgrp->{-sort} ? 0 : 1)]}, $fgrp; } sub clone_v1 { @@ -538,12 +590,23 @@ sub clone_v1 { 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 $dst; + if ($resume) { # respect read-only cloned w/ --epoch= + my @st = stat(_); # for root + if (!-w _ || !($st[2] & 0222)) { + warn "# skipping $dst, not writable\n"; + return; + } + } + my $fini = on_destroy \&v1_done, $self; if (my $fgrp = forkgroup_prep($self, $uri)) { $fgrp->{-fini} = $fini; - $resume ? cmp_fp_do($fgrp, \&fgrp_enqueue, $end) - : fgrp_enqueue($fgrp, $end); + if ($resume) { + $fgrp->{-sort} = $fgrp->{-ent}->{modified}; + cmp_fp_do($fgrp, \&fgrp_enqueue, $end); + } else { # new repo, save for last + fgrp_enqueue($fgrp, $end); + } } elsif ($resume) { cmp_fp_do($self, \&resume_fetch, $uri, $fini); } else { # normal clone @@ -556,15 +619,18 @@ sub clone_v1 { "$self->{dst}$ref"; } } - start_cmd($self, $cmd, $opt, $fini); + ++$self->{chg}->{nr_chg}; + start_cmd($self, $cmd, $opt, + on_destroy(\&run_puh, $self, $fini)); } if (!$self->{-is_epoch} && $lei->{opt}->{'inbox-config'} =~ - /\A(?:always|v1)\z/s) { + /\A(?:always|v1)\z/s && + !-f "$dst/inbox.config.example") { _get_txt_start($self, '_/text/config/raw', $fini); } my $d = $self->{-ent} ? $self->{-ent}->{description} : undef; - $self->{'txt.description'} = $d if defined $d; + utf8::encode($self->{'txt.description'} = $d) if defined $d; (!defined($d) && !$end) and _get_txt_start($self, 'description', $fini); @@ -617,9 +683,11 @@ EOM sub init_placeholder ($$$) { my ($src, $edst, $ent) = @_; PublicInbox::Import::init_bare($edst); - my $f = "$edst/config"; - open my $fh, '>>', $f or die "open($f): $!"; - print $fh <<EOM or die "print($f): $!"; + my @owner = defined($ent->{owner}) ? (<<EOM) : (); +[gitweb] + owner = $ent->{owner} +EOM + write_file '>>', "$edst/config", <<EOM, @owner; [remote "origin"] url = $src fetch = +refs/*:refs/* @@ -629,21 +697,11 @@ sub init_placeholder ($$$) { ; will not fetch updates for it unless write permission is added. ; Hint: chmod +w $edst EOM - if (defined($ent->{owner})) { - print $fh <<EOM or die "print($f): $!"; -[gitweb] - owner = $ent->{owner} -EOM - } - 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): $!"; + write_file '>', "$edst/$fn", $val; } } @@ -658,10 +716,10 @@ sub up_fp_done { my ($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): $!"; + sysseek($fh, 0, SEEK_SET); $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): $!")); + my $B = sha_all(1, $fh)->hexdigest; return if $A eq $B; $self->{-ent}->{fingerprint} = $B; push @{$self->{chg}->{fp_mismatch}}, $self->{-key}; @@ -670,11 +728,27 @@ sub up_fp_done { sub atomic_write ($$$) { my ($dn, $bn, $raw) = @_; my $ft = File::Temp->new(DIR => $dn, TEMPLATE => "$bn-XXXX"); - print $ft $raw or die "print($ft): $!"; + print $ft $raw; $ft->flush or die "flush($ft): $!"; ft_rename($ft, "$dn/$bn", 0666); } +sub run_next_puh { + my ($self) = @_; + my $puh = shift @{$self->{-puh_todo}} // return delete($self->{-fini}); + my $fini = on_destroy \&run_next_puh, $self; + my $cmd = [ @$puh, ($self->{cur_dst} // $self->{dst}) ]; + my $opt = +{ map { $_ => $self->{lei}->{$_} } (0..2) }; + start_cmd($self, $cmd, undef, $opt, $fini); +} + +sub run_puh { + my ($self, $fini) = @_; + $self->{-fini} = $fini; + @{$self->{-puh_todo}} = @PUH; + run_next_puh($self); +} + # modifies the to-be-written manifest entry, and sets values from it, too sub update_ent { my ($self) = @_; @@ -683,18 +757,18 @@ sub update_ent { my $cur = $self->{-local_manifest}->{$key}->{fingerprint} // "\0"; my $dst = $self->{cur_dst} // $self->{dst}; if (defined($new) && $new ne $cur) { - my $cmd = ['git', "--git-dir=$dst", 'show-ref']; + my $cmd = [git_exe, "--git-dir=$dst", 'show-ref']; my $opt = { 2 => $self->{lei}->{2} }; - open($opt->{1}, '+>', undef) or die "open(tmp): $!"; + open($opt->{1}, '+>', undef); $self->{-show_ref_up} = $opt->{1}; - my $done = PublicInbox::OnDestroy->new($$, \&up_fp_done, $self); + my $done = on_destroy \&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" ]; + my $cmd = [ git_exe, "--git-dir=$dst" ]; if ($new =~ s/\Aref: //) { push @$cmd, qw(symbolic-ref HEAD), $new; } elsif ($new =~ /\A[a-f0-9]{40,}\z/) { @@ -707,6 +781,7 @@ sub update_ent { } if (my $symlinks = $self->{-ent}->{symlinks}) { my $top = File::Spec->rel2abs($self->{dst}); + push @{$self->{-new_symlinks}}, @$symlinks; for my $p (@$symlinks) { my $ln = "$top/$p"; $ln =~ tr!/!/!s; @@ -717,17 +792,18 @@ sub update_ent { if (lstat($ln)) { if (-l _) { next if readlink($ln) eq $tgt; - unlink($ln) or die "unlink($ln): $!"; + unlink($ln); } else { push @{$self->{chg}->{badlink}}, $p; } } - symlink($tgt, $ln) or die "symlink($tgt, $ln): $!"; + symlink($tgt, $ln); + ++$self->{chg}->{nr_chg}; } } if (defined(my $t = $self->{-ent}->{modified})) { my ($dn, $bn) = ("$dst/info/web", 'last-modified'); - my $orig = PublicInbox::Git::try_cat("$dn/$bn"); + my $orig = PublicInbox::IO::try_cat("$dn/$bn"); $t = strftime('%F %T', gmtime($t))." +0000\n"; File::Path::mkpath($dn); atomic_write($dn, $bn, $t) if $orig ne $t; @@ -736,7 +812,9 @@ sub update_ent { $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', $new ]; + utf8::encode($new); # to octets + my $cmd = [ git_exe, qw(config -f), "$dst/config", + 'gitweb.owner', $new ]; start_cmd($self, $cmd, { 2 => $self->{lei}->{2} }); } @@ -745,9 +823,10 @@ sub v1_done { # called via OnDestroy return if $self->{dry_run} || !keep_going($self); _write_inbox_config($self); my $dst = $self->{cur_dst} // $self->{dst}; + unlink_fetch_head($dst); update_ent($self) if $self->{-ent}; my $o = "$dst/objects"; - if (open(my $fh, '<', my $fn = "$o/info/alternates")) {; + if (CORE::open(my $fh, '<', my $fn = "$o/info/alternates")) {; my $base = File::Spec->rel2abs($o); my @l = <$fh>; my $ft; @@ -758,7 +837,7 @@ sub v1_done { # called via OnDestroy DIR => "$o/info"); } if ($ft) { - print $ft @l or die "print($ft): $!"; + print $ft @l; $ft->flush or die "flush($ft): $!"; ft_rename($ft, $fn, 0666, $fh); } @@ -776,8 +855,8 @@ sub v2_done { # called via OnDestroy 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'; - my $lck = $lk->lock_for_scope($$); + my $lk = PublicInbox::Lock->new("$dst/inbox.lock"); + my $lck = $lk->lock_for_scope; _write_inbox_config($self); require PublicInbox::MultiGit; my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git'); @@ -785,7 +864,7 @@ sub v2_done { # called via OnDestroy for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) } for my $edst (@{delete($self->{-read_only}) // []}) { my @st = stat($edst) or die "stat($edst): $!"; - chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; + chmod($st[2] & 0555, $edst); } write_makefile($dst, 2); undef $lck; # unlock @@ -804,7 +883,7 @@ sub clone_v2_prep ($$;$) { my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); my $task = $m ? bless { %$self }, __PACKAGE__ : $self; my (@skip, $desc); - my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); + my $fini = on_destroy \&v2_done, $task; for my $nr (sort { $a <=> $b } keys %$v2_epochs) { my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; @@ -841,10 +920,12 @@ failed to extract epoch number from $src # filter out the epochs we skipped $self->{chg}->{manifest} = 1 if $m && delete(@$m{@skip}); - (!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst); + $self->{dry_run} or File::Path::mkpath($dst); - $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and + if ($lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s && + !-f "$dst/inbox.config.example") { _get_txt_start($task, '_/text/config/raw', $fini); + } defined($desc) ? ($task->{'txt.description'} = $desc) : _get_txt_start($task, 'description', $fini); @@ -853,7 +934,7 @@ failed to extract epoch number from $src sub decode_manifest ($$$) { my ($fh, $fn, $uri) = @_; my $js; - my $gz = do { local $/; <$fh> } // die "slurp($fn): $!"; + my $gz = PublicInbox::IO::read_all $fh; gunzip(\$gz => \$js, MultiStream => 1) or die "gunzip($uri): $GunzipError\n"; my $m = eval { PublicInbox::Config->json->decode($js) }; @@ -865,13 +946,14 @@ sub decode_manifest ($$$) { sub load_current_manifest ($) { my ($self) = @_; my $fn = $self->{-manifest} // return; - if (open(my $fh, '<', $fn)) { + if (CORE::open(my $fh, '<', $fn)) { decode_manifest($fh, $fn, $fn); } elsif ($!{ENOENT}) { # non-fatal, we can just do it slowly - warn "open($fn): $!\n" if !$self->{-initial_clone}; + $self->{-initial_clone} or + warn "W: open($fn): $! (non-fatal)\n"; undef; } else { - die "open($fn): $!\n"; + die "E: open($fn): $!\n"; } } @@ -893,7 +975,7 @@ sub multi_inbox ($$$) { my @orig = defined($incl // $excl) ? (keys %$v2, @v1) : (); if (defined $incl) { my $re = '(?:'.join('\\z|', map { - $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + glob2re($_) // qr/\A\Q$_\E/ } @$incl).'\\z)'; my @gone = delete @$v2{grep(!/$re/, keys %$v2)}; delete @$m{map { @$_ } @gone} and $self->{chg}->{manifest} = 1; @@ -902,7 +984,7 @@ sub multi_inbox ($$$) { } if (defined $excl) { my $re = '(?:'.join('\\z|', map { - $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + glob2re($_) // qr/\A\Q$_\E/ } @$excl).'\\z)'; my @gone = delete @$v2{grep(/$re/, keys %$v2)}; delete @$m{map { @$_ } @gone} and $self->{chg}->{manifest} = 1; @@ -936,7 +1018,7 @@ sub clone_all { my ($self, $m) = @_; my $todo = $TODO; $TODO = \'BUG on further use'; - my $end = PublicInbox::OnDestroy->new($$, \&fgrp_fetch_all, $self); + my $end = on_destroy \&fgrp_fetch_all, $self; { my $nodep = delete $todo->{''}; @@ -959,9 +1041,13 @@ sub clone_all { # resolve multi-level references while ($m && defined($nxt = $m->{$x}->{reference})) { exists($todo->{$nxt}) or last; - die <<EOM if ++$nr > 1000; -E: dependency loop detected (`$x' => `$nxt') + if (++$nr > 1000) { + $m->{$x}->{reference} = undef; + $m->{$nxt}->{reference} = undef; + warn <<EOM +E: dependency loop detected (`$x' => `$nxt'), breaking EOM + } $x = $nxt; } my $y = delete $todo->{$x} // next; # already done @@ -986,8 +1072,8 @@ sub dump_manifest ($$) { # epoch they no longer want to skip my $json = PublicInbox::Config->json->encode($m); my $mtime = (stat($ft))[9]; - seek($ft, SEEK_SET, 0) or die "seek($ft): $!"; - truncate($ft, 0) or die "truncate($ft): $!"; + seek($ft, 0, SEEK_SET); + truncate($ft, 0); gzip(\$json => $ft) or die "gzip($ft): $GzipError"; $ft->flush or die "flush($ft): $!"; utime($mtime, $mtime, "$ft") or die "utime(..., $ft): $!"; @@ -995,30 +1081,50 @@ sub dump_manifest ($$) { sub dump_project_list ($$) { my ($self, $m) = @_; - my $f = $self->{'-project-list'} // return; - my $old = PublicInbox::Git::try_cat($f); + my $f = $self->{'-project-list'}; + my $old = defined($f) ? PublicInbox::IO::try_cat($f) : ''; my %new; - open my $dh, '<', '.' or die "open(.): $!"; - chdir($self->{dst}) or die "chdir($self->{dst}): $!"; + open my $dh, '<', '.'; + if (!$self->{dry_run} || -d $self->{dst}) { + chdir($self->{dst}); + } my @local = grep { -e $_ ? ($new{$_} = undef) : 1 } split(/\n/s, $old); - chdir($dh) or die "chdir(restore): $!"; + chdir($dh); $new{substr($_, 1)} = 1 for keys %$m; # drop leading '/' my @list = sort keys %new; my @remote = grep { !defined($new{$_}) } @list; + my %lnk = map { substr($_, 1) => undef } @{$self->{-new_symlinks}}; + @remote = grep { !exists($lnk{$_}) } @remote; - warn <<EOM if @remote; + if (@remote) { + warn <<EOM; The following local repositories are ignored/gone from $self->{src}: EOM - warn "\t", $_, "\n" for @remote; - warn <<EOM if @local; + warn "\t", $_, "\n" for @remote; + + if ($self->{lei}->{opt}->{purge} && !$self->{dry_run}) { + my $o = {}; + $o->{verbose} = 1 if $self->{lei}->{opt}->{verbose}; + my $dst = $self->{dst}; + File::Path::remove_tree(map { "$dst/$_" } @remote, $o); + my %rm = map { $_ => undef } @remote; + @list = grep { !exists($rm{$_}) } @list; + $self->{lei}->qerr('# purged '); + } + } + if (defined($f) && @local) { + warn <<EOM; The following repos in $f no longer exist on the filesystem: EOM - warn "\t", $_, "\n" for @local; - + warn "\t", $_, "\n" for @local; + } + $self->{chg}->{nr_chg} += scalar(@remote) + scalar(@local); + return if !defined($f) || $self->{dry_run}; my (undef, $dn, $bn) = File::Spec->splitpath($f); - atomic_write($dn, $bn, join("\n", @list, '')); + my $new = join("\n", @list, ''); + atomic_write($dn, $bn, $new) if $new ne $old; } # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz @@ -1030,7 +1136,13 @@ sub try_manifest { $self->{-torsocks} //= $curl->torsocks($lei, $uri) or return; my $path = $uri->path; chop($path) eq '/' or die "BUG: $uri not canonicalized"; - $uri->path($path . '/manifest.js.gz'); + my $rmf = $lei->{opt}->{'remote-manifest'} // '/manifest.js.gz'; + if ($rmf =~ m!\A[^/:]+://!) { + $uri = URI->new($rmf); + } else { + $rmf = "/$rmf" if index($rmf, '/') != 0; + $uri->path($path.$rmf); + } 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) { @@ -1049,7 +1161,10 @@ sub try_manifest { } # bail out if curl -z/--timecond hit 304 Not Modified, $ft will be empty - return $lei->qerr("# $manifest unchanged") if -f $manifest && !-s $ft; + if (-f $manifest && !-s $ft) { + $lei->child_error(127 << 8) if $lei->{opt}->{'exit-code'}; + return $lei->qerr("# $manifest unchanged"); + } my $m = eval { decode_manifest($ft, $ft, $uri) }; if ($@) { @@ -1058,8 +1173,9 @@ sub try_manifest { } local $self->{chg} = {}; local $self->{-local_manifest} = load_current_manifest($self); + local $self->{-new_symlinks} = []; my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m); - return $lei->child_error(1, $multi) if !ref($multi); + return $lei->child_error(0, $multi) if !ref($multi); my $v2 = delete $multi->{v2}; if ($v2) { for my $name (sort keys %$v2) { @@ -1112,13 +1228,12 @@ EOM } delete local $lei->{opt}->{epoch} if defined($v2); clone_all($self, $m); - return if $self->{dry_run} || !keep_going($self); + return if !keep_going($self); # set by clone_v2_prep/-I/--exclude my $mis = delete $self->{chg}->{fp_mismatch}; if ($mis) { - my $t = (stat($ft))[9]; - $t = strftime('%F %k:%M:%S %z', localtime($t)); + my $t = fmt_localtime((stat($ft))[9]); warn <<EOM; W: Fingerprints for the following repositories do not match W: $mf_url @ $t: @@ -1129,13 +1244,17 @@ EOM W: The above fingerprints may never match without --prune EOM } - dump_manifest($m => $ft) if delete($self->{chg}->{manifest}) || $mis; + if ((delete($self->{chg}->{manifest}) || $mis) && !$self->{dry_run}) { + dump_manifest($m => $ft); + } my $bad = delete $self->{chg}->{badlink}; warn(<<EOM, map { ("\t", $_, "\n") } @$bad) if $bad; W: The following exist and have not been converted to symlinks EOM dump_project_list($self, $m); - ft_rename($ft, $manifest, 0666); + ft_rename($ft, $manifest, 0666) if !$self->{dry_run}; + !$self->{chg}->{nr_chg} && $lei->{opt}->{'exit-code'} and + $lei->child_error(127 << 8); } sub start_clone_url { @@ -1150,6 +1269,11 @@ sub do_mirror { # via wq_io_do or public-inbox-clone $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}; + local @PUH; + if (defined(my $puh = $lei->{opt}->{'post-update-hook'})) { + require Text::ParseWords; + @PUH = map { [ Text::ParseWords::shellwords($_) ] } @$puh; + } eval { my $ic = $lei->{opt}->{'inbox-config'} //= 'always'; $ic =~ /\A(?:v1|v2|always|never)\z/s or die <<""; @@ -1202,8 +1326,8 @@ sub ipc_atfork_child { sub write_makefile { my ($dir, $ibx_ver) = @_; my $f = "$dir/Makefile"; - if (sysopen my $fh, $f, O_CREAT|O_EXCL|O_WRONLY) { - print $fh <<EOM or die "print($f) $!"; + if (CORE::sysopen my $fh, $f, O_CREAT|O_EXCL|O_WRONLY) { + print $fh <<EOM; # This is a v$ibx_ver public-inbox, see the public-inbox-v$ibx_ver-format(5) # manpage for more information on the format. This Makefile is # intended as a familiar wrapper for users unfamiliar with @@ -1217,7 +1341,7 @@ sub write_makefile { # so you may edit it freely with your own convenience targets # and notes. public-inbox-fetch will recreate it if removed. EOM - print $fh <<'EOM' or die "print($f): $!"; + print $fh <<'EOM'; # the default target: help : @echo Common targets: @@ -1227,7 +1351,7 @@ 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 + @echo ' make index - initial index after clone' fetch : public-inbox-fetch @@ -1253,7 +1377,7 @@ compact : .PHONY : help fetch update index reindex compact EOM - close $fh or die "close($f): $!"; + close $fh; } else { die "open($f): $!" unless $!{EEXIST}; } |