#!perl -w
-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# Basic tool to create a Xapian search index for a public-inbox.
use strict;
use v5.10.1;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
-usage: public-inbox-extindex [options] EXTINDEX_DIR [INBOX_DIR]
+usage: public-inbox-extindex [options] [EXTINDEX_DIR] [INBOX_DIR...]
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)
See public-inbox-extindex(1) man page for full documentation.
EOF
-my $opt = { quiet => -1, compact => 0, max_size => undef, fsync => 1 };
+my $opt = { quiet => -1, compact => 0, fsync => 1, scan => 1 };
GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i
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 scan!
+ 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);
+local $SIG{USR1} = 'IGNORE'; # to be overridden in eidx_sync
# require lazily to speed up --help
-my $eidx_dir = shift(@ARGV) // die "E: $help";
require PublicInbox::Admin;
my $cfg = PublicInbox::Config->new;
-my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
+my $eidx_dir = shift(@ARGV);
+unless (defined $eidx_dir) {
+ if ($opt->{all} && $cfg->ALL) {
+ $eidx_dir = $cfg->ALL->{topdir};
+ } else {
+ die "E: $help";
+ }
+}
+my @ibxs;
+if ($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);
+ }
+}