X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-extindex;h=bee824b1878611691344af7f725063a47fd6b421;hb=4eee5af6011cc8cdefb66c9729952c7eff5c0b0b;hp=771486c425b315bae70fd8a82d62ab0331e0a827;hpb=f1921e46e16cabb6f705236581564b8fe901a76e;p=public-inbox.git

diff --git a/script/public-inbox-extindex b/script/public-inbox-extindex
index 771486c4..bee824b1 100755
--- a/script/public-inbox-extindex
+++ b/script/public-inbox-extindex
@@ -1,5 +1,5 @@
 #!perl -w
-# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
+# 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;
@@ -17,18 +17,22 @@ usage: public-inbox-extindex [options] [EXTINDEX_DIR] [INBOX_DIR...]
   --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!
+		fsync|sync! fast dangerous
 		indexlevel|index-level|L=s max_size|max-size=s
 		batch_size|batch-size=s
-		gc commit-interval=i watch scan!
-		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;
@@ -38,6 +42,7 @@ 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) {
@@ -50,11 +55,17 @@ unless (defined $eidx_dir) {
 my @ibxs;
 if ($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};
+	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);
@@ -69,7 +80,7 @@ if ($opt->{gc}) {
 	if ($opt->{all}) {
 		$eidx->attach_config($cfg);
 	} else {
-		$eidx->attach_inbox($_) for @ibxs;
+		$eidx->attach_config($cfg, \@ibxs);
 	}
 	if ($opt->{watch}) {
 		$cfg = undef; # save memory only after SIGHUP