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} ||
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): $!";
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");
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 = $self->{ibx} = {};
sub set_description ($) {
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 $orig;
}
sub index_cloned_inbox {
sub pack_dst { # packs lightweight satellite repos
my ($fgrp) = @_;
pack_refs($fgrp, $fgrp->{cur_dst});
- delete($fgrp->{-fini}) // die 'BUG: no {-fini}'; # call v1_done
}
sub pack_refs {
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
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),
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 $fh <<EOM or die "print($f): $!";
; rely on the "$rn" remote in the
; $fg fork group for fetches
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): $!";
+ }
bless {
%$self, -osdir => $dir, -remote => $rn, -uri => $uri
}, __PACKAGE__;
}
sub fgrp_enqueue {
- my ($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
$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;
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
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 ($$) {
push @{$self->{chg}->{fp_mismatch}}, $self->{-key};
}
+sub atomic_write ($$$) {
+ 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 $done = PublicInbox::OnDestroy->new($$, \&up_fp_done, $self);
start_cmd($self, $cmd, $opt, $done);
}
-
$new = $self->{-ent}->{head};
$cur = $self->{-local_manifest}->{$key}->{head} // "\0";
if (defined($new) && $new ne $cur) {
}
start_cmd($self, $cmd, { 2 => $self->{lei}->{2} }) if $cmd;
}
+ if (my $symlinks = $self->{-ent}->{symlinks}) {
+ my $top = File::Spec->rel2abs($self->{dst});
+ push @{$self->{-new_symlinks}}, @$symlinks;
+ for my $p (@$symlinks) {
+ my $ln = "$top/$p";
+ $ln =~ tr!/!/!s;
+ my (undef, $dn, $bn) = File::Spec->splitpath($ln);
+ File::Path::mkpath($dn);
+ my $tgt = "$top/$key";
+ $tgt = File::Spec->abs2rel($tgt, $dn);
+ if (lstat($ln)) {
+ if (-l _) {
+ next if readlink($ln) eq $tgt;
+ unlink($ln) or die "unlink($ln): $!";
+ } else {
+ push @{$self->{chg}->{badlink}}, $p;
+ }
+ }
+ symlink($tgt, $ln) or die "symlink($tgt, $ln): $!";
+ }
+ }
+ if (defined(my $t = $self->{-ent}->{modified})) {
+ my ($dn, $bn) = ("$dst/info/web", 'last-modified');
+ my $orig = PublicInbox::Git::try_cat("$dn/$bn");
+ $t = strftime('%F %T', gmtime($t))." +0000\n";
+ File::Path::mkpath($dn);
+ atomic_write($dn, $bn, $t) if $orig ne $t;
+ }
$new = $self->{-ent}->{owner} // return;
$cur = $self->{-local_manifest}->{$key}->{owner} // "\0";
my $dst = $self->{cur_dst} // $self->{dst};
my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs);
my $task = $m ? bless { %$self }, __PACKAGE__ : $self;
- delete $task->{todo}; # $self->{todo} still exists
my (@skip, $desc);
my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
for my $nr (sort { $a <=> $b } keys %$v2_epochs) {
$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, $ent);
sub clone_all {
my ($self, $m) = @_;
- my $todo = delete $self->{todo};
+ my $todo = $TODO;
+ $TODO = \'BUG on further use';
+ my $end = PublicInbox::OnDestroy->new($$, \&fgrp_fetch_all, $self);
{
my $nodep = delete $todo->{''};
# handle no-dependency repos, first
for (@$nodep) {
- clone_v1($_, 1);
+ clone_v1($_, $end);
return if !keep_going($self);
}
}
# resolve multi-level references
while ($m && defined($nxt = $m->{$x}->{reference})) {
exists($todo->{$nxt}) or last;
- die <<EOM if ++$nr > 1000;
-E: dependency loop detected (`$x' => `$nxt')
+ if (++$nr > 1000) {
+ $m->{$x}->{reference} = undef;
+ $m->{$nxt}->{reference} = undef;
+ warn <<EOM
+E: dependency loop detected (`$x' => `$nxt'), breaking
EOM
+ }
$x = $nxt;
}
my $y = delete $todo->{$x} // next; # already done
for (@$y) {
- clone_v1($_, 1);
+ clone_v1($_, $end);
return if !keep_going($self);
}
last; # restart %$todo iteration
}
}
- do_reap($self, 1); # finish all fingerprint checks
- fgrp_fetch_all($self);
+
+ # $end->DESTROY will call fgrp_fetch_all once all references
+ # in $LIVE are gone, and do_reap will eventually drain $LIVE
+ $end = undef;
do_reap($self, 1);
}
utime($mtime, $mtime, "$ft") or die "utime(..., $ft): $!";
}
+sub dump_project_list ($$) {
+ 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{$_}) } @list;
+ my %lnk = map { substr($_, 1) => undef } @{$self->{-new_symlinks}};
+ @remote = grep { !exists($lnk{$_}) } @remote;
+
+ warn <<EOM if @remote;
+The following local repositories are ignored/gone from $self->{src}:
+EOM
+ warn "\t", $_, "\n" for @remote;
+ warn <<EOM if @local;
+The following repos in $f no longer exist on the filesystem:
+EOM
+ warn "\t", $_, "\n" for @local;
+
+ my (undef, $dn, $bn) = File::Spec->splitpath($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) = @_;
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, $cmd, \%opt);
return try_scrape($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 $@;
}
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);
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};
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;
}
}
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 <<EOM;
W: Fingerprints for the following repositories do not match
W: $mf_url @ $t:
EOM
}
dump_manifest($m => $ft) if delete($self->{chg}->{manifest}) || $mis;
+ 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);
}
$ic =~ /\A(?:v1|v2|always|never)\z/s or die <<"";
--inbox-config must be one of `always', `v2', `v1', or `never'
- # we support --objstore= and --manifest= with '' (empty string)
- for my $default (qw(objstore manifest.js.gz)) {
- my ($k) = (split(/\./, $default))[0];
+ # we support these switches with '' (empty string).
+ # defaults match example conf distributed with grokmirror
+ my @pairs = qw(objstore objstore manifest manifest.js.gz
+ project-list projects.list);
+ while (@pairs) {
+ my ($k, $default) = splice(@pairs, 0, 2);
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 $TODO = {};
+ local $FGRP_TODO = {};
my $iv = $lei->{opt}->{'inbox-version'} //
return start_clone_url($self);
return clone_v1($self) if $iv == 1;