+ die "No Xapian shards found in $old\n" unless @old_shards;
+
+ my ($src, $max_shard);
+ if (!defined($reshard) || $reshard == scalar(@old_shards)) {
+ # 1:1 copy
+ $max_shard = scalar(@old_shards) - 1;
+ } else {
+ # M:N copy
+ $max_shard = $reshard - 1;
+ $src = [ map { "$old/$_" } @old_shards ];
+ }
+ foreach my $dn (0..$max_shard) {
+ my $wip = File::Temp->newdir("$dn-XXXX", DIR => $old);
+ same_fs_or_die($old, $wip->dirname);
+ my $cur = "$old/$dn";
+ push @queue, [ $src // $cur , $wip ];
+ nodatacow_dir($wip->dirname);
+ $tmp->{$cur} = $wip;
+ }
+ # mark old shards to be unlinked
+ if ($src) {
+ $tmp->{$_} ||= undef for @$src;
+ }
+ }
+ ($tmp, \@queue);
+}
+
+sub check_compact () { runnable_or_die($XAPIAN_COMPACT) }
+
+sub _run { # with_umask callback
+ my ($ibx, $cb, $opt) = @_;
+ my $im = $ibx->can('importer') ? $ibx->importer(0) : undef;
+ ($im // $ibx)->lock_acquire;
+ my ($tmp, $queue) = prepare_run($ibx, $opt);
+
+ # fine-grained locking if we prepare for reindex
+ if (!$opt->{-coarse_lock}) {
+ prepare_reindex($ibx, $opt);
+ ($im // $ibx)->lock_release;
+ }
+
+ $ibx->cleanup if $ibx->can('cleanup');
+ process_queue($queue, $cb, $opt);
+ ($im // $ibx)->lock_acquire if !$opt->{-coarse_lock};
+ commit_changes($ibx, $im, $tmp, $opt);
+}
+
+sub run {
+ my ($ibx, $task, $opt) = @_; # task = 'cpdb' or 'compact'
+ my $cb = \&$task;
+ PublicInbox::Admin::progress_prepare($opt ||= {});
+ my $dir;
+ for my $fld (qw(inboxdir topdir)) {
+ my $d = $ibx->{$fld} // next;
+ -d $d or die "$fld=$d does not exist\n";
+ $dir = $d;
+ last;
+ }
+ check_compact() if $opt->{compact} && $ibx->search;
+
+ if (!$ibx->can('eidx_sync') && !$opt->{-coarse_lock}) {
+ # per-epoch ranges for v2
+ # v1:{ from => $OID }, v2:{ from => [ $OID, $OID, $OID ] } }
+ $opt->{reindex} = { from => $ibx->version == 1 ? '' : [] };
+ PublicInbox::SearchIdx::load_xapian_writable();
+ }
+
+ local @SIG{keys %SIG} = values %SIG;
+ setup_signals();
+ $ibx->with_umask(\&_run, $ibx, $cb, $opt);
+}
+
+sub cpdb_retryable ($$) {
+ my ($src, $pfx) = @_;
+ if (ref($@) =~ /\bDatabaseModifiedError\b/) {
+ warn "$pfx Xapian DB modified, reopening and retrying\n";
+ $src->reopen;
+ return 1;
+ }
+ if ($@) {
+ warn "$pfx E: ", ref($@), "\n";
+ die;
+ }
+ 0;
+}
+
+sub progress_pfx ($) {
+ my ($wip) = @_; # tempdir v2: ([0-9])+-XXXX
+ my @p = split('/', $wip);
+
+ # return "xap15/0" for v2, or "xapian15" for v1:
+ ($p[-1] =~ /\A([0-9]+)/) ? "$p[-2]/$1" : $p[-1];
+}
+
+sub kill_compact { # setup_signals callback
+ my ($sig, $pidref) = @_;
+ kill($sig, $$pidref) if defined($$pidref);
+}
+
+# xapian-compact wrapper
+sub compact ($$) { # cb_spawn callback
+ my ($args, $opt) = @_;
+ my ($src, $newdir) = @$args;
+ my $dst = ref($newdir) ? $newdir->dirname : $newdir;
+ my $pfx = $opt->{-progress_pfx} ||= progress_pfx($src);
+ my $pr = $opt->{-progress};
+ my $rdr = {};
+
+ foreach my $fd (0..2) {
+ defined(my $dfd = $opt->{$fd}) or next;
+ $rdr->{$fd} = $dfd;
+ }
+
+ # we rely on --no-renumber to keep docids synched to NNTP
+ my $cmd = [ $XAPIAN_COMPACT, '--no-renumber' ];
+ for my $sw (qw(no-full fuller)) {
+ push @$cmd, "--$sw" if $opt->{$sw};
+ }
+ for my $sw (qw(blocksize)) {
+ defined(my $v = $opt->{$sw}) or next;
+ push @$cmd, "--$sw", $v;
+ }
+ $pr->("$pfx `".join(' ', @$cmd)."'\n") if $pr;
+ push @$cmd, $src, $dst;
+ my ($rd, $pid);
+ local @SIG{keys %SIG} = values %SIG;
+ setup_signals(\&kill_compact, \$pid);
+ ($rd, $pid) = popen_rd($cmd, undef, $rdr);
+ while (<$rd>) {
+ if ($pr) {
+ s/\r/\r$pfx /g;
+ $pr->("$pfx $_");
+ }
+ }
+ waitpid($pid, 0);
+ die "@$cmd failed: \$?=$?\n" if $?;
+}
+
+sub cpdb_loop ($$$;$$) {
+ my ($src, $dst, $pr_data, $cur_shard, $reshard) = @_;
+ my ($pr, $fmt, $nr, $pfx);
+ if ($pr_data) {
+ $pr = $pr_data->{pr};
+ $fmt = $pr_data->{fmt};
+ $nr = \($pr_data->{nr});
+ $pfx = $pr_data->{pfx};
+ }
+
+ my ($it, $end);
+ do {
+ eval {
+ $it = $src->postlist_begin('');
+ $end = $src->postlist_end('');
+ };
+ } while (cpdb_retryable($src, $pfx));
+
+ do {
+ eval {
+ for (; $it != $end; $it++) {
+ my $docid = $it->get_docid;
+ if (defined $reshard) {
+ my $dst_shard = $docid % $reshard;
+ next if $dst_shard != $cur_shard;
+ }
+ my $doc = $src->get_document($docid);
+ $dst->replace_document($docid, $doc);
+ if ($pr_data && !(++$$nr & 1023)) {
+ $pr->(sprintf($fmt, $$nr));
+ }