lei q: -I/--exclude/--only support globs and basenames

We can do basename matching when it's unambiguous.  Since '*?[]'
characters are rare in URLs and pathnames, we'll do glob
matching by default to support a (curl-inspired) --globoff/-g
option to disable globbing.

And fix --exclude while we're at it

1 files changed, 37 insertions, 1 deletions

diff --git a/lib/PublicInbox/LeiExternal.pm b/lib/PublicInbox/LeiExternal.pm
index 3853cfc1..6b4c7fb0 100644
--- a/lib/PublicInbox/LeiExternal.pm
+++ b/lib/PublicInbox/LeiExternal.pm
@@ -39,7 +39,7 @@ sub lei_ls_external {
 }
 
 sub ext_canonicalize {
-        my ($location) = $_[-1];
+        my ($location) = @_;
         if ($location !~ m!\Ahttps?://!) {
                 PublicInbox::Config::rel2abs_collapsed($location);
         } else {
@@ -52,6 +52,42 @@ sub ext_canonicalize {
         }
 }
 
+my %patmap = ('*' => '[^/]*?', '?' => '[^/]', '[' => '[', ']' => ']');
+sub glob2pat {
+        my ($glob) = @_;
+        $glob =~ s!(.)!$patmap{$1} || "\Q$1"!ge;
+        $glob;
+}
+
+sub get_externals {
+        my ($self, $loc, $exclude) = @_;
+        return (ext_canonicalize($loc)) if -e $loc;
+
+        my @m;
+        my @cur = externals_each($self);
+        my $do_glob = !$self->{opt}->{globoff}; # glob by default
+        if ($do_glob && ($loc =~ /[\*\?]/s || $loc =~ /\[.*\]/s)) {
+                my $re = glob2pat($loc);
+                @m = grep(m!$re!, @cur);
+                return @m if scalar(@m);
+        } elsif (index($loc, '/') < 0) { # exact basename match:
+                @m = grep(m!/\Q$loc\E/?\z!, @cur);
+                return @m if scalar(@m) == 1;
+        } elsif ($exclude) { # URL, maybe:
+                my $canon = ext_canonicalize($loc);
+                @m = grep(m!\A\Q$canon\E\z!, @cur);
+                return @m if scalar(@m) == 1;
+        } else { # URL:
+                return (ext_canonicalize($loc));
+        }
+        if (scalar(@m) == 0) {
+                $self->fail("`$loc' is unknown");
+        } else {
+                $self->fail("`$loc' is ambiguous:\n", map { "\t$_\n" } @m);
+        }
+        ();
+}
+
 sub lei_add_external {
         my ($self, $location) = @_;
         my $cfg = $self->_lei_cfg(1);