Make the UTF-8 decoding stricter and more verbose when

malformation happens.  This involved adding an argument
to utf8_to_uv_chk(), which involved changing its prototype,
and prefer STRLEN over I32 for the UTF-8 length, which as
a domino effect necessitated changing the prototypes of
scan_bin(), scan_oct(), scan_hex(), and reg_uni().
The stricter UTF-8 decoding checking uses Markus Kuhn's
UTF-8 Decode Stress Tester from
http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt

p4raw-id: //depot/perl@7416

1 files changed, 4 insertions, 4 deletions

diff --git a/sv.c b/sv.c
index 1fac1620aa..2790cfd859 100644
--- a/sv.c
+++ b/sv.c
@@ -6358,13 +6358,13 @@ Perl_sv_vcatpvfn(pTHX_ SV *sv, const char *pat, STRLEN patlen, va_list *args, SV
 	case 'd':
 	case 'i':
 	    if (vectorize) {
-		I32 ulen;
+		STRLEN ulen;
 		if (!veclen) {
 		    vectorize = FALSE;
 		    break;
 		}
 		if (utf)
-		    iv = (IV)utf8_to_uv_chk(vecstr, &ulen, 0);
+		    iv = (IV)utf8_to_uv_chk(vecstr, veclen, &ulen, 0);
 		else {
 		    iv = *vecstr;
 		    ulen = 1;
@@ -6440,14 +6440,14 @@ Perl_sv_vcatpvfn(pTHX_ SV *sv, const char *pat, STRLEN patlen, va_list *args, SV
 
 	uns_integer:
 	    if (vectorize) {
-		I32 ulen;
+		STRLEN ulen;
 	vector:
 		if (!veclen) {
 		    vectorize = FALSE;
 		    break;
 		}
 		if (utf)
-		    uv = utf8_to_uv_chk(vecstr, &ulen, 0);
+		    uv = utf8_to_uv_chk(vecstr, veclen, &ulen, 0);
 		else {
 		    uv = *vecstr;
 		    ulen = 1;