xcpdb: preserve indexlevel for extindex

This likely fixes indexlevel preservation for some v2 on some
systems, too, since (apparently) we need to sort shards
numerically to get Xapian metadata working properly on a
combined (multi-shard) Xapian DB.

diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index c87baa7bbe74f7c067e7b442a55b2992c6520459..3a4c5622ea150cbbe61e2903716b6bc0c0183332 100644 (file)
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -219,7 +219,7 @@ sub prepare_run {
                my @old_shards;
                while (defined(my $dn = readdir($dh))) {
                        if ($dn =~ /\A[0-9]+\z/) {
-                               push @old_shards, $dn;
+                               push(@old_shards, $dn + 0);
                        } elsif ($dn eq '.' || $dn eq '..') {
                        } elsif ($dn =~ /\Aover\.sqlite3/) {
                        } elsif ($dn eq 'misc' && $misc_ok) {
@@ -228,7 +228,7 @@ sub prepare_run {
                        }
                }
                die "No Xapian shards found in $old\n" unless @old_shards;
-
+               @old_shards = sort { $a <=> $b } @old_shards;
                my ($src, $max_shard);
                if (!defined($reshard) || $reshard == scalar(@old_shards)) {
                        # 1:1 copy
@@ -464,11 +464,10 @@ sub cpdb ($$) { # cb_spawn callback
                        $dst->set_metadata('last_commit', $lc) if $lc;
 
                        # only the first xapian shard (0) gets 'indexlevel'
-                       if ($new =~ m!(?:xapian[0-9]+|xap[0-9]+/0)\b!) {
+                       if ($new =~ m!/(?:xapian[0-9]+|(?:ei|xap)[0-9]+/0)\b!) {
                                my $l = $src->get_metadata('indexlevel');
-                               if ($l eq 'medium') {
+                               $l eq 'medium' and
                                        $dst->set_metadata('indexlevel', $l);
-                               }
                        }
                        if ($pr_data) {
                                my $tot = $src->get_doccount;

diff --git a/t/extsearch.t b/t/extsearch.t
index 03bcad95ee5b162bcddb922bb640d6565a49f46c..8cbd26f07a3f451d73a9913de9b834ef2965c0da 100644 (file)
--- a/t/extsearch.t
+++ b/t/extsearch.t
@@ -1,8 +1,7 @@
 #!perl -w
 # Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-use strict;
-use Test::More;
+use v5.12;
 use PublicInbox::TestCommon;
 use PublicInbox::Config;
 use PublicInbox::InboxWritable;
@@ -554,4 +553,32 @@ EOM
        is_deeply($x, $o, 'xref3 and over docids match');
 }
 
+{
+       my $d = "$home/eidx-med";
+       ok(run_script([qw(-extindex --dangerous --all -L medium -j3), $d]),
+               'extindex medium init');
+       my $es = PublicInbox::ExtSearch->new($d);
+       is($es->xdb->get_metadata('indexlevel'), 'medium',
+               'es indexlevel before');
+       my @xdb = $es->xdb_shards_flat;
+       is($xdb[0]->get_metadata('indexlevel'), 'medium',
+               '0 indexlevel before');
+       shift @xdb;
+       for (@xdb) {
+               ok(!$_->get_metadata('indexlevel'), 'no indexlevel in >0 shard')
+       }
+       is($es->xdb->get_metadata('indexlevel'), 'medium', 'indexlevel before');
+       ok(run_script([qw(-xcpdb -R5), $d]), 'xcpdb R5');
+       $es = PublicInbox::ExtSearch->new($d);
+       is($es->xdb->get_metadata('indexlevel'), 'medium',
+               '0 indexlevel after');
+       @xdb = $es->xdb_shards_flat;
+       is(scalar(@xdb), 5, 'got 5 shards');
+       is($xdb[0]->get_metadata('indexlevel'), 'medium', '0 indexlevel after');
+       shift @xdb;
+       for (@xdb) {
+               ok(!$_->get_metadata('indexlevel'), 'no indexlevel in >0 shard')
+       }
+}
+
 done_testing;