mro UTF8 cleanup.

This patch also duplicates existing mro tests with copies that use
Unicode in identifiers, to test the mro code.

Since those tests trigger it, it also fixes a bug in the parsing
of *{...}: If the first character inside the braces is a non-ASCII
Unicode identifier character, the inside is now implicitly quoted
if it is just an identifier (just as it is with ASCII identifiers),
instead of being parsed as a bareword that would violate strict subs.

1 files changed, 14 insertions, 4 deletions

diff --git a/toke.c b/toke.c
index a85b698d5d..53c6759ed6 100644
--- a/toke.c
+++ b/toke.c
@@ -8705,9 +8705,19 @@ S_scan_ident(pTHX_ register char *s, register const char *send, char *dest, STRL
     }
     else if (ck_uni)
 	check_uni();
-    if (s < send)
-	*d = *s++;
-    d[1] = '\0';
+    if (s < send) {
+        if (UTF) {
+            const STRLEN skip = UTF8SKIP(s);
+            STRLEN i;
+            d[skip] = '\0';
+            for ( i = 0; i < skip; i++ )
+                d[i] = *s++;
+        }
+        else {
+            *d = *s++;
+            d[1] = '\0';
+        }
+    }
     if (*d == '^' && *s && isCONTROLVAR(*s)) {
 	*d = toCTRL(*s);
 	s++;
@@ -8723,7 +8733,7 @@ S_scan_ident(pTHX_ register char *s, register const char *send, char *dest, STRL
 	    }
 	}
 	if (isIDFIRST_lazy_if(d,UTF)) {
-	    d++;
+	    d += UTF8SKIP(d);
 	    if (UTF) {
 		char *end = s;
 		while ((end < send && isALNUM_lazy_if(end,UTF)) || *end == ':') {