From d211f49249fd9a52ccdd305313d28aa9194dbcd0 Mon Sep 17 00:00:00 2001
From: Alex Vandiver <alex@chmrr.net>
Date: Sun, 22 Mar 2015 22:39:23 -0400
Subject: Make check for multi-dimensional arrays be UTF8-aware

During parsing, toke.c checks if the user is attempting provide multiple
indexes to an array index:

    $a[ $foo, $bar ];

However, while checking for word characters in variable names is aware
of multi-byte characters if "use utf8" is enabled, the loop is only
advanced one byte at a time, not one character at a time.  As such,
multibyte variables in array indexes incorrectly yield warnings:

    Passing malformed UTF-8 to "XPosixWord" is deprecated
    Malformed UTF-8 character (unexpected continuation byte 0x9d, with
      no preceding start byte)

Switch the loop to advance character-by-character if UTF-8 semantics are
in use.

(cherry picked from commit b3089e964c0afaf7eb8d54aa5a912e4eb2e6c176)

Bug: https://rt.perl.org/Ticket/Display.html?id=124113
Bug-Debian: https://bugs.debian.org/822336
Patch-Name: fixes/5.20.3/multidimensional_arrays_utf8.diff
---
 t/lib/warnings/toke | 10 ++++++++++
 toke.c              |  2 +-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/t/lib/warnings/toke b/t/lib/warnings/toke
index 92e94adf83..6764ae619c 100644
--- a/t/lib/warnings/toke
+++ b/t/lib/warnings/toke
@@ -1510,3 +1510,13 @@ Use of literal control characters in variable names is deprecated at (eval 2) li
 -a;
 ;-a;
 EXPECT
+########
+# toke.c
+# [perl #124113] Compile-time warning with UTF8 variable in array index
+use warnings;
+use utf8;
+my $𝛃 = 0;
+my @array = (0);
+my $v = $array[ 0 + $𝛃 ];
+   $v = $array[ $𝛃 + 0 ];
+EXPECT
diff --git a/toke.c b/toke.c
index 906d56c100..b112cde5b9 100644
--- a/toke.c
+++ b/toke.c
@@ -6621,7 +6621,7 @@ Perl_yylex(pTHX)
 			char *t = s+1;
 
 			while (isSPACE(*t) || isWORDCHAR_lazy_if(t,UTF) || *t == '$')
-			    t++;
+			    t += UTF ? UTF8SKIP(t) : 1;
 			if (*t++ == ',') {
 			    PL_bufptr = PEEKSPACE(PL_bufptr); /* XXX can realloc */
 			    while (t < PL_bufend && *t != ']')