X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=a04be9fcb4f18456777f3eb0e0295c9cd283ce96;hp=87893ef15bc66fdb049cc1ad7160cd250557c237;hb=refs%2Fheads%2Fmaster;hpb=4af931f9ad100b0eca5729e2b1c56b844cf1a1c8

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 87893ef1..a04be9fc 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,5 +1,5 @@
 #!perl -w
-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2021 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.
 # Usage with libeatmydata <https://www.flamingspork.com/projects/libeatmydata/>
@@ -25,6 +25,8 @@ options:
   --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
   --reindex           index previously indexed data (if upgrading)
+  --since=DATE        limit --reindex to changes after DATE
+  --until=DATE        limit --reindex to changes before DATE
   --rethread          regenerate thread IDs (if upgrading, use sparingly)
   --prune             prune git storage on discontiguous history
   --verbose | -v      increase verbosity (may be repeated)
@@ -37,12 +39,13 @@ my $opt = {
 	'update-extindex' => [], # ":s@" optional arg sets '' if no arg given
 };
 GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
-		fsync|sync! xapian_only|xapian-only
+		fsync|sync! xapian_only|xapian-only dangerous
 		indexlevel|index-level|L=s max_size|max-size=s
 		batch_size|batch-size=s
-		sequential_shard|seq-shard|sequential-shard
+		since|after=s until|before=s
+		sequential-shard|seq-shard
 		no-update-extindex update-extindex|E=s@
-		fast-noop|F skip-docdata all help|h))
+		fast-noop|F skip-docdata 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} && $opt->{jobs} < 0;
@@ -56,6 +59,7 @@ if ($opt->{reindex} && delete($opt->{'fast-noop'})) {
 # require lazily to speed up --help
 require PublicInbox::Admin;
 PublicInbox::Admin::require_or_die('-index');
+PublicInbox::Admin::do_chdir(delete $opt->{C});
 
 my $cfg = PublicInbox::Config->new; # Config is loaded by Admin
 $opt->{-use_cwd} = 1;
@@ -63,7 +67,7 @@ my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
 PublicInbox::Admin::require_or_die('-index');
 unless (@ibxs) { print STDERR $help; exit 1 }
 
-my (@eidx_dir, %eidx_seen);
+my (@eidx, %eidx_seen);
 my $update_extindex = $opt->{'update-extindex'};
 if (!scalar(@$update_extindex) && (my $ALL = $cfg->ALL)) {
 	# extindex and normal inboxes may have different owners
@@ -84,7 +88,10 @@ for my $ei_name (@$update_extindex) {
 	} else {
 		die "extindex `$ei_name' not configured or found\n";
 	}
-	$eidx_seen{$topdir} //= push(@eidx_dir, $topdir);
+	my $o = { %$opt };
+	delete $o->{indexlevel} if ($o->{indexlevel}//'') eq 'basic';
+	$eidx_seen{$topdir} //=
+		push(@eidx, PublicInbox::ExtSearchIdx->new($topdir, $o));
 }
 my $mods = {};
 my @eidx_unconfigured;
@@ -95,7 +102,7 @@ foreach my $ibx (@ibxs) {
 	$ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ?
 			'full' : $detected);
 	PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
-	if (@eidx_dir && $ibx->{-unconfigured}) {
+	if (@eidx && $ibx->{-unconfigured}) {
 		push @eidx_unconfigured, "  $ibx->{inboxdir}\n";
 	}
 }
@@ -119,6 +126,7 @@ for my $ibx (@ibxs) {
 		PublicInbox::Xapcmd::run($ibx, 'compact', $opt->{compact_opt});
 	}
 	$ibx->{-no_fsync} = 1 if !$opt->{fsync};
+	$ibx->{-dangerous} = 1 if $opt->{dangerous};
 	$ibx->{-skip_docdata} //= $opt->{'skip-docdata'};
 
 	my $ibx_opt = $opt;
@@ -126,20 +134,23 @@ for my $ibx (@ibxs) {
 		defined(my $v = $cfg->git_bool($s)) or die <<EOL;
 publicInbox.$ibx->{name}.indexSequentialShard not boolean
 EOL
-		$ibx_opt = { %$opt, sequential_shard => $v };
+		$ibx_opt = { %$opt, 'sequential-shard' => $v };
 	}
-	PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
+	my $nidx = PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
 	last if $ibx_opt->{quit};
 	if (my $copt = $opt->{compact_opt}) {
-		local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard};
+		local $copt->{jobs} = 0 if $ibx_opt->{'sequential-shard'};
 		PublicInbox::Xapcmd::run($ibx, 'compact', $copt);
 	}
-	next if $ibx->{-unconfigured};
 	last if $ibx_opt->{quit};
-	for my $dir (@eidx_dir) {
-		my $eidx = PublicInbox::ExtSearchIdx->new($dir);
+	next if $ibx->{-unconfigured} || !$nidx;
+	for my $eidx (@eidx) {
 		$eidx->attach_inbox($ibx);
-		$eidx->eidx_sync($ibx_opt);
-		last if $ibx_opt->{quit};
 	}
 }
+my $pr = $opt->{-progress};
+for my $eidx (@eidx) {
+	$pr->("indexing $eidx->{topdir} ...\n") if $pr;
+	$eidx->eidx_sync($opt);
+	last if $opt->{quit};
+}