fix erroneous acceptance of f4 9x xx xx code sequences by utf-8 decoder

the DFA table controlling accepted ranges for the f4 prefix used an
incorrect upper bound of 0xa0 where it should have been 0x90, allowing
such sequences to be accepted and decoded as non-Unicode-scalar values
0x110000 through 0x11ffff.

diff --git a/src/multibyte/internal.c b/src/multibyte/internal.c
index 7e1b1c03409f0e6759d9b0a47cde82eb8bb8b5a3..2f5aaa914a1e19e694e5372442533c9cb09ef377 100644 (file)
--- a/src/multibyte/internal.c
+++ b/src/multibyte/internal.c
@@ -9,7 +9,7 @@
              | x )
 #define F(x) ( ( x>=5 ? 0 : \
                  x==0 ? R(0x90,0xc0) : \
-                 x==4 ? R(0x80,0xa0) : \
+                 x==4 ? R(0x80,0x90) : \
                  R(0x80,0xc0) ) \
              | ( R(0x80,0xc0) >> 6 ) \
              | ( R(0x80,0xc0) >> 12 ) \