X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-extindex;h=bee824b1878611691344af7f725063a47fd6b421;hb=60848de2194f0c518bd660860e9458dd765d0a3e;hp=5d56e2c31ff5e8ac13e7de5eae9c19640832c352;hpb=df8e4a0612545d53672036641e9f076efc94c2f6;p=public-inbox.git
diff --git a/script/public-inbox-extindex b/script/public-inbox-extindex
old mode 100644
new mode 100755
index 5d56e2c3..bee824b1
--- a/script/public-inbox-extindex
+++ b/script/public-inbox-extindex
@@ -1,47 +1,91 @@
#!perl -w
-# Copyright (C) 2020 all contributors
+# Copyright (C) all contributors
# License: AGPL-3.0+
-# 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 = < -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!
+ fsync|sync! fast dangerous
indexlevel|index-level|L=s max_size|max-size=s
batch_size|batch-size=s
- skip-docdata all help|h))
+ dedupe:s@ gc commit-interval=i watch scan! dry-run|n
+ 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 lazily to speed up --help
-my $eidx_dir = shift(@ARGV) // die "E: $help";
+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 @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;
+ 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, $opt);
-$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 {
+ $eidx->attach_config($cfg, \@ibxs);
+ }
+ if ($opt->{watch}) {
+ $cfg = undef; # save memory only after SIGHUP
+ $eidx->eidx_watch($opt);
+ } else {
+ $eidx->eidx_sync($opt);
+ }
+}