Create and update external (detached) search indices
--no-fsync speed up indexing, risk corruption on power outage
+ --watch run persistently and watch for inbox updates
-L LEVEL `medium', or `full' (default: full)
--all index all configured inboxes
--jobs=NUM set or disable parallelization (NUM=0)
--batch-size=BYTES flush changes to OS after a given number of bytes
--max-size=BYTES do not index messages larger than the given size
+ --gc perform garbage collection instead of indexing
--verbose | -v increase verbosity (may be repeated)
BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes)
fsync|sync!
indexlevel|index-level|L=s max_size|max-size=s
batch_size|batch-size=s
- skip-docdata all help|h))
+ gc commit-interval=i watch
+ all help|h))
or die $help;
if ($opt->{help}) { print $help; exit 0 };
die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
-
+require IO::Handle;
+STDOUT->autoflush(1);
+STDERR->autoflush(1);
# require lazily to speed up --help
my $eidx_dir = shift(@ARGV) // die "E: $help";
local $SIG{USR1} = 'IGNORE'; # to be overridden in eidx_sync
require PublicInbox::Admin;
my $cfg = PublicInbox::Config->new;
-my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
+my @ibxs;
+if ($opt->{gc}) {
+ die "E: inbox paths must not be specified with --gc\n" if @ARGV;
+ die "E: --all not compatible with --gc\n" if $opt->{all};
+ die "E: --watch is not compatible with --gc\n" if $opt->{watch};
+} else {
+ @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
+}
PublicInbox::Admin::require_or_die(qw(-search));
+PublicInbox::Config::json() or die "Cpanel::JSON::XS or similar missing\n";
PublicInbox::Admin::progress_prepare($opt);
+my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
+local %ENV = (%ENV, %$env) if $env;
require PublicInbox::ExtSearchIdx;
my $eidx = PublicInbox::ExtSearchIdx->new($eidx_dir, $opt);
-$eidx->attach_inbox($_) for @ibxs;
-$eidx->eidx_sync($opt);
+if ($opt->{gc}) {
+ $eidx->attach_config($cfg);
+ $eidx->eidx_gc($opt);
+} else {
+ if ($opt->{all}) {
+ $eidx->attach_config($cfg);
+ } else {
+ $eidx->attach_inbox($_) for @ibxs;
+ }
+ if ($opt->{watch}) {
+ $cfg = undef; # save memory only after SIGHUP
+ $eidx->eidx_watch($opt);
+ } else {
+ $eidx->eidx_sync($opt);
+ }
+}