+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+Perl-extended-UTF-8 string; returns FALSE otherwise. If C<len> is 0, it will
+be calculated using C<strlen(s)> (which means if you use this option, that C<s>
+can't have embedded C<NUL> characters and has to have a terminating C<NUL>
+byte). Note that all characters being ASCII constitute 'a valid UTF-8 string'.
+
+This function considers Perl's extended UTF-8 to be valid. That means that
+code points above Unicode, surrogates, and non-character code points are
+considered valid by this function. Use C<L</is_strict_utf8_string>>,
+C<L</is_c9strict_utf8_string>>, or C<L</is_utf8_string_flags>> to restrict what
+code points are considered valid.
+
+See also
+C<L</is_utf8_invariant_string>>,
+C<L</is_utf8_invariant_string_loc>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
+
+=cut
+*/
+
+#define is_utf8_string(s, len) is_utf8_string_loclen(s, len, NULL, NULL)
+
+#if defined(PERL_CORE) || defined (PERL_EXT)
+
+/*
+=for apidoc is_utf8_non_invariant_string
+
+Returns TRUE if L<perlapi/is_utf8_invariant_string> returns FALSE for the first
+C<len> bytes of the string C<s>, but they are, nonetheless, legal Perl-extended
+UTF-8; otherwise returns FALSE.
+
+A TRUE return means that at least one code point represented by the sequence
+either is a wide character not representable as a single byte, or the
+representation differs depending on whether the sequence is encoded in UTF-8 or
+not.
+
+See also
+C<L<perlapi/is_utf8_invariant_string>>,
+C<L<perlapi/is_utf8_string>>
+
+=cut
+
+This is commonly used to determine if a SV's UTF-8 flag should be turned on.
+It needn't be if its string is entirely UTF-8 invariant, and it shouldn't be if
+it otherwise contains invalid UTF-8.
+
+It is an internal function because khw thinks that XS code shouldn't be working
+at this low a level. A valid use case could change that.
+
+*/
+
+PERL_STATIC_INLINE bool
+S_is_utf8_non_invariant_string(const U8* const s, STRLEN len)
+{
+ const U8 * first_variant;
+
+ PERL_ARGS_ASSERT_IS_UTF8_NON_INVARIANT_STRING;
+
+ if (is_utf8_invariant_string_loc(s, len, &first_variant)) {
+ return FALSE;
+ }
+
+ return is_utf8_string(first_variant, len - (first_variant - s));
+}
+
+#endif
+
+/*
+=for apidoc is_strict_utf8_string
+
+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+UTF-8-encoded string that is fully interchangeable by any application using
+Unicode rules; otherwise it returns FALSE. If C<len> is 0, it will be
+calculated using C<strlen(s)> (which means if you use this option, that C<s>
+can't have embedded C<NUL> characters and has to have a terminating C<NUL>
+byte). Note that all characters being ASCII constitute 'a valid UTF-8 string'.
+
+This function returns FALSE for strings containing any
+code points above the Unicode max of 0x10FFFF, surrogate code points, or
+non-character code points.
+
+See also
+C<L</is_utf8_invariant_string>>,
+C<L</is_utf8_invariant_string_loc>>,
+C<L</is_utf8_string>>,
+C<L</is_utf8_string_flags>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loc_flags>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_string_loclen_flags>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
+C<L</is_strict_utf8_string_loc>>,
+C<L</is_strict_utf8_string_loclen>>,
+C<L</is_c9strict_utf8_string>>,
+C<L</is_c9strict_utf8_string_loc>>,
+and
+C<L</is_c9strict_utf8_string_loclen>>.
+
+=cut
+*/
+
+#define is_strict_utf8_string(s, len) is_strict_utf8_string_loclen(s, len, NULL, NULL)
+
+/*
+=for apidoc is_c9strict_utf8_string
+
+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+UTF-8-encoded string that conforms to
+L<Unicode Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>;
+otherwise it returns FALSE. If C<len> is 0, it will be calculated using
+C<strlen(s)> (which means if you use this option, that C<s> can't have embedded
+C<NUL> characters and has to have a terminating C<NUL> byte). Note that all
+characters being ASCII constitute 'a valid UTF-8 string'.
+
+This function returns FALSE for strings containing any code points above the
+Unicode max of 0x10FFFF or surrogate code points, but accepts non-character
+code points per
+L<Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>.
+
+See also
+C<L</is_utf8_invariant_string>>,
+C<L</is_utf8_invariant_string_loc>>,
+C<L</is_utf8_string>>,
+C<L</is_utf8_string_flags>>,
+C<L</is_utf8_string_loc>>,
+C<L</is_utf8_string_loc_flags>>,
+C<L</is_utf8_string_loclen>>,
+C<L</is_utf8_string_loclen_flags>>,
+C<L</is_utf8_fixed_width_buf_flags>>,
+C<L</is_utf8_fixed_width_buf_loc_flags>>,
+C<L</is_utf8_fixed_width_buf_loclen_flags>>,
+C<L</is_strict_utf8_string>>,
+C<L</is_strict_utf8_string_loc>>,
+C<L</is_strict_utf8_string_loclen>>,
+C<L</is_c9strict_utf8_string_loc>>,
+and
+C<L</is_c9strict_utf8_string_loclen>>.
+
+=cut
+*/
+
+#define is_c9strict_utf8_string(s, len) is_c9strict_utf8_string_loclen(s, len, NULL, 0)
+
+/*
+=for apidoc is_utf8_string_flags
+
+Returns TRUE if the first C<len> bytes of string C<s> form a valid
+UTF-8 string, subject to the restrictions imposed by C<flags>;
+returns FALSE otherwise. If C<len> is 0, it will be calculated