X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-extindex;h=bee824b1878611691344af7f725063a47fd6b421;hb=4eee5af6011cc8cdefb66c9729952c7eff5c0b0b;hp=20a0737c2e5768f2d5d612640fe4343ea6d9217c;hpb=9224adfd92cfeff1c00d6b971e653ca4ed5a98d2;p=public-inbox.git

diff --git a/script/public-inbox-extindex b/script/public-inbox-extindex
old mode 100644
new mode 100755
index 20a0737c..bee824b1
--- a/script/public-inbox-extindex
+++ b/script/public-inbox-extindex
@@ -1,42 +1,71 @@
 #!perl -w
-# Copyright (C) 2020 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>
-# 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
+  --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, 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
-		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);
@@ -44,5 +73,19 @@ 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);
+	}
+}