+/*
+
+=for apidoc Am|STRLEN|isSTRICT_UTF8_CHAR|const U8 *s|const U8 *e
+
+Evaluates to non-zero if the first few bytes of the string starting at C<s> and
+looking no further than S<C<e - 1>> are well-formed UTF-8 that represents some
+Unicode code point completely acceptable for open interchange between all
+applications; otherwise it evaluates to 0. If non-zero, the value gives how
+many bytes starting at C<s> comprise the code point's representation. Any
+bytes remaining before C<e>, but beyond the ones needed to form the first code
+point in C<s>, are not examined.
+
+The largest acceptable code point is the Unicode maximum 0x10FFFF, and must not
+be a surrogate nor a non-character code point. Thus this excludes any code
+point from Perl's extended UTF-8.
+
+This is used to efficiently decide if the next few bytes in C<s> is
+legal Unicode-acceptable UTF-8 for a single character.
+
+Use C<L</isC9_STRICT_UTF8_CHAR>> to use the L<Unicode Corrigendum
+#9|http://www.unicode.org/versions/corrigendum9.html> definition of allowable
+code points; C<L</isUTF8_CHAR>> to check for Perl's extended UTF-8;
+and C<L</isUTF8_CHAR_flags>> for a more customized definition.
+
+Use C<L</is_strict_utf8_string>>, C<L</is_strict_utf8_string_loc>>, and
+C<L</is_strict_utf8_string_loclen>> to check entire strings.
+
+=cut
+*/
+
+#define isSTRICT_UTF8_CHAR(s, e) \
+ (UNLIKELY((e) <= (s)) \
+ ? 0 \
+ : (UTF8_IS_INVARIANT(*s)) \
+ ? 1 \
+ : UNLIKELY(((e) - (s)) < UTF8SKIP(s)) \
+ ? 0 \
+ : is_STRICT_UTF8_CHAR_utf8_no_length_checks(s))
+
+/*
+
+=for apidoc Am|STRLEN|isC9_STRICT_UTF8_CHAR|const U8 *s|const U8 *e
+
+Evaluates to non-zero if the first few bytes of the string starting at C<s> and
+looking no further than S<C<e - 1>> are well-formed UTF-8 that represents some
+Unicode non-surrogate code point; otherwise it evaluates to 0. If non-zero,
+the value gives how many bytes starting at C<s> comprise the code point's
+representation. Any bytes remaining before C<e>, but beyond the ones needed to
+form the first code point in C<s>, are not examined.
+
+The largest acceptable code point is the Unicode maximum 0x10FFFF. This
+differs from C<L</isSTRICT_UTF8_CHAR>> only in that it accepts non-character
+code points. This corresponds to
+L<Unicode Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>.
+which said that non-character code points are merely discouraged rather than
+completely forbidden in open interchange. See
+L<perlunicode/Noncharacter code points>.
+
+Use C<L</isUTF8_CHAR>> to check for Perl's extended UTF-8; and
+C<L</isUTF8_CHAR_flags>> for a more customized definition.
+
+Use C<L</is_c9strict_utf8_string>>, C<L</is_c9strict_utf8_string_loc>>, and
+C<L</is_c9strict_utf8_string_loclen>> to check entire strings.
+
+=cut
+*/
+
+#define isC9_STRICT_UTF8_CHAR(s, e) \
+ (UNLIKELY((e) <= (s)) \
+ ? 0 \
+ : (UTF8_IS_INVARIANT(*s)) \
+ ? 1 \
+ : UNLIKELY(((e) - (s)) < UTF8SKIP(s)) \
+ ? 0 \
+ : is_C9_STRICT_UTF8_CHAR_utf8_no_length_checks(s))
+
+/*
+
+=for apidoc Am|STRLEN|isUTF8_CHAR_flags|const U8 *s|const U8 *e| const U32 flags
+
+Evaluates to non-zero if the first few bytes of the string starting at C<s> and
+looking no further than S<C<e - 1>> are well-formed UTF-8, as extended by Perl,
+that represents some code point, subject to the restrictions given by C<flags>;
+otherwise it evaluates to 0. If non-zero, the value gives how many bytes
+starting at C<s> comprise the code point's representation. Any bytes remaining
+before C<e>, but beyond the ones needed to form the first code point in C<s>,
+are not examined.
+
+If C<flags> is 0, this gives the same results as C<L</isUTF8_CHAR>>;
+if C<flags> is C<UTF8_DISALLOW_ILLEGAL_INTERCHANGE>, this gives the same results
+as C<L</isSTRICT_UTF8_CHAR>>;
+and if C<flags> is C<UTF8_DISALLOW_ILLEGAL_C9_INTERCHANGE>, this gives
+the same results as C<L</isC9_STRICT_UTF8_CHAR>>.
+Otherwise C<flags> may be any combination of the C<UTF8_DISALLOW_I<foo>> flags
+understood by C<L</utf8n_to_uvchr>>, with the same meanings.
+
+The three alternative macros are for the most commonly needed validations; they
+are likely to run somewhat faster than this more general one, as they can be
+inlined into your code.
+
+Use L</is_utf8_string_flags>, L</is_utf8_string_loc_flags>, and
+L</is_utf8_string_loclen_flags> to check entire strings.
+
+=cut
+*/
+
+#define isUTF8_CHAR_flags(s, e, flags) \
+ (UNLIKELY((e) <= (s)) \
+ ? 0 \
+ : (UTF8_IS_INVARIANT(*s)) \
+ ? 1 \
+ : UNLIKELY(((e) - (s)) < UTF8SKIP(s)) \
+ ? 0 \
+ : _is_utf8_char_helper(s, e, flags))
+