utf8.c: Don't invert beyond-Unicode code points

The Unicode properties are defined only on Unicode code points.  In the
past, this meant all property matches would fail for non-Unicode code
points.  However, starting with 5.15.1 some properties do succeed.  This
restores the previous behavior.

1 files changed, 15 insertions, 1 deletions

diff --git a/t/re/pat.t b/t/re/pat.t
index 4ef9663b5e..988c23e01d 100644
--- a/t/re/pat.t
+++ b/t/re/pat.t
@@ -21,7 +21,7 @@ BEGIN {
     require './test.pl';
 }
 
-plan tests => 451;  # Update this when adding/deleting tests.
+plan tests => 455;  # Update this when adding/deleting tests.
 
 run_tests() unless caller;
 
@@ -1167,6 +1167,20 @@ sub run_tests {
         is($got,$want,'RT #84294: check that "ab" =~ /((\w+)(?{ push @got, $2 })){2}/ leaves @got in the correct state');
     }
 
+    {
+        # Suppress warnings, as the non-unicode one comes out even if turn off
+        # warnings here (because the execution is done in another scope).
+        local $SIG{__WARN__} = sub {};
+        my $str = "\x{110000}";
+
+        # No non-unicode code points match any Unicode property, even inverse
+        # ones
+        unlike($str, qr/\p{ASCII_Hex_Digit=True}/, "Non-Unicode doesn't match \\p{}");
+        unlike($str, qr/\p{ASCII_Hex_Digit=False}/, "Non-Unicode doesn't match \\p{}");
+        like($str, qr/\P{ASCII_Hex_Digit=True}/, "Non-Unicode matches \\P{}");
+        like($str, qr/\P{ASCII_Hex_Digit=False}/, "Non-Unicode matches \\P{}");
+    }
+
 } # End of sub run_tests
 
 1;