script/public-inbox-extindex

#!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 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...]

  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
  --dedupe[=MSGID]    fix prior deduplication errors (may be repeated)
  --reindex           index previously indexed inboxes
  --fast              only reindex unseen/stale messages
  --verbose | -v      increase verbosity (may be repeated)
  --dry-run | -n      dry-run on --dedupe

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 $opt = { quiet => -1, compact => 0, fsync => 1, scan => 1 };
GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i
		fsync|sync! fast dangerous
		indexlevel|index-level|L=s max_size|max-size=s
		batch_size|batch-size=s
		dedupe:s@ gc commit-interval=i watch scan! dry-run|n
		multi-pack-index! all C=s@ 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
require PublicInbox::Admin;
PublicInbox::Admin::do_chdir(delete $opt->{C});
my $cfg = PublicInbox::Config->new;
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;
	for my $sw (qw(all watch dry-run dedupe)) {
		die "E: --$sw is not compatible with --gc\n" if $opt->{$sw};
	}
} else {
	@ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
}
$opt->{'dry-run'} && !$opt->{dedupe} and
	die "E: --dry-run only affects --dedupe\n";
$opt->{fast} && !$opt->{reindex} and
	die "E: --fast only affects --reindex\n";

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, $opt);
if ($opt->{gc}) {
	$eidx->attach_config($cfg);
	$eidx->eidx_gc($opt);
} else {
	if ($opt->{all}) {
		$eidx->attach_config($cfg);
	} else {
		$eidx->attach_config($cfg, \@ibxs);
	}
	if ($opt->{watch}) {
		$cfg = undef; # save memory only after SIGHUP
		$eidx->eidx_watch($opt);
	} else {
		$eidx->eidx_sync($opt);
	}
}