[PATCH 12/28] cindex: implement --exclude= like -clone

[Eric Wong <e@80x24.org>]

This is to ensure we can exclude certain repos which are
expensive-to-index (e.g. `**/deps.git', `**/transparency-logs/**').
---
 lib/PublicInbox/CodeSearchIdx.pm | 10 +++++++++-
 script/public-inbox-cindex       |  2 +-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/lib/PublicInbox/CodeSearchIdx.pm b/lib/PublicInbox/CodeSearchIdx.pm
index 587f0b81..97c563bd 100644
--- a/lib/PublicInbox/CodeSearchIdx.pm
+++ b/lib/PublicInbox/CodeSearchIdx.pm
@@ -27,7 +27,7 @@ use File::Spec ();
 use PublicInbox::SHA qw(sha256_hex);
 use PublicInbox::Search qw(xap_terms);
 use PublicInbox::SearchIdx qw(add_val);
-use PublicInbox::Config;
+use PublicInbox::Config qw(glob2re);
 use PublicInbox::Spawn qw(spawn popen_rd);
 use PublicInbox::OnDestroy;
 use Socket qw(MSG_EOR);
@@ -566,6 +566,14 @@ sub cidx_run { # main entry point
 		}
 		warn "E: canonicalized and attempting to continue\n";
 	}
+	if (defined(my $excl = $self->{-opt}->{exclude})) {
+		my $re = '(?:'.join('\\z|', map {
+				glob2re($_) // qr/\A\Q$_\E/
+			} @$excl).'\\z)';
+		@{$self->{git_dirs}} = grep {
+			$_ =~ /$re/ ? (warn("# excluding $_\n"), 0) : 1;
+		} @{$self->{git_dirs}};
+	}
 	local $self->{nchange} = 0;
 	local $LIVE_JOBS = $self->{-opt}->{jobs} ||
 			PublicInbox::IPC::detect_nproc() || 2;
diff --git a/script/public-inbox-cindex b/script/public-inbox-cindex
index 166c8261..420ef4de 100755
--- a/script/public-inbox-cindex
+++ b/script/public-inbox-cindex
@@ -26,7 +26,7 @@ EOF
 my $opt = { fsync => 1, scan => 1 }; # --no-scan is hidden
 GetOptions($opt, qw(quiet|q verbose|v+ reindex jobs|j=i fsync|sync! dangerous
 		indexlevel|index-level|L=s batch_size|batch-size=s
-		project-list=s
+		project-list=s exclude=s@
 		d=s update|u scan! prune dry-run|n C=s@ help|h))
 	or die $help;
 if ($opt->{help}) { print $help; exit 0 };