+ if (len >= sizeof(FF_OVERLONG_PREFIX) - 1) {
+ return 1;
+ }
+
+ /* The missing bytes could cause the result to go one way or the other, so
+ * the result is indeterminate */
+ return -1;
+}
+
+#if defined(UV_IS_QUAD) /* These assume IV_MAX is 2**63-1 */
+# ifdef EBCDIC /* Actually is I8 */
+# define HIGHEST_REPRESENTABLE_UTF8 \
+ "\xFF\xA7\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF"
+# else
+# define HIGHEST_REPRESENTABLE_UTF8 \
+ "\xFF\x80\x87\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF"
+# endif
+#endif
+
+PERL_STATIC_INLINE int
+S_does_utf8_overflow(const U8 * const s,
+ const U8 * e,
+ const bool consider_overlongs)
+{
+ /* Returns an int indicating whether or not the UTF-8 sequence from 's' to
+ * 'e' - 1 would overflow an IV on this platform; that is if it represents
+ * a code point larger than the highest representable code point. It
+ * returns 1 if it does overflow; 0 if it doesn't, and -1 if there isn't
+ * enough information to tell. This last return value can happen if the
+ * sequence is incomplete, missing some trailing bytes that would form a
+ * complete character. If there are enough bytes to make a definitive
+ * decision, this function does so.
+ *
+ * If 'consider_overlongs' is TRUE, the function checks for the possibility
+ * that the sequence is an overlong that doesn't overflow. Otherwise, it
+ * assumes the sequence is not an overlong. This can give different
+ * results only on ASCII 32-bit platforms.
+ *
+ * (For ASCII platforms, we could use memcmp() because we don't have to
+ * convert each byte to I8, but it's very rare input indeed that would
+ * approach overflow, so the loop below will likely only get executed once.)
+ *
+ * 'e' - 1 must not be beyond a full character. */
+
+
+ PERL_ARGS_ASSERT_DOES_UTF8_OVERFLOW;
+ assert(s <= e && s + UTF8SKIP(s) >= e);
+
+#if ! defined(UV_IS_QUAD)
+
+ return is_utf8_cp_above_31_bits(s, e, consider_overlongs);
+
+#else
+
+ PERL_UNUSED_ARG(consider_overlongs);
+
+ {
+ const STRLEN len = e - s;
+ const U8 *x;
+ const U8 * y = (const U8 *) HIGHEST_REPRESENTABLE_UTF8;
+
+ for (x = s; x < e; x++, y++) {
+
+ if (UNLIKELY(NATIVE_UTF8_TO_I8(*x) == *y)) {
+ continue;
+ }
+
+ /* If this byte is larger than the corresponding highest UTF-8
+ * byte, the sequence overflow; otherwise the byte is less than,
+ * and so the sequence doesn't overflow */
+ return NATIVE_UTF8_TO_I8(*x) > *y;
+
+ }
+
+ /* Got to the end and all bytes are the same. If the input is a whole
+ * character, it doesn't overflow. And if it is a partial character,
+ * there's not enough information to tell */
+ if (len < sizeof(HIGHEST_REPRESENTABLE_UTF8) - 1) {
+ return -1;
+ }
+
+ return 0;
+ }
+
+#endif