Add macro for determining if UTF-8 is Unicode-strict

6 files changed, 323 insertions, 12 deletions

diff --git a/ext/XS-APItest/APItest.xs b/ext/XS-APItest/APItest.xs
index b20206e5d6..c226defc85 100644
--- a/ext/XS-APItest/APItest.xs
+++ b/ext/XS-APItest/APItest.xs
@@ -5327,6 +5327,13 @@ test_isUTF8_CHAR(char *s, STRLEN len)
     OUTPUT:
         RETVAL
 
+STRLEN
+test_isSTRICT_UTF8_CHAR(char *s, STRLEN len)
+    CODE:
+        RETVAL = isSTRICT_UTF8_CHAR((U8 *) s, (U8 *) s + len);
+    OUTPUT:
+        RETVAL
+
 IV
 test_is_utf8_valid_partial_char_flags(char *s, STRLEN len, U32 flags)
     CODE:
diff --git a/ext/XS-APItest/t/utf8.t b/ext/XS-APItest/t/utf8.t
index c909ebbfe9..acba778067 100644
--- a/ext/XS-APItest/t/utf8.t
+++ b/ext/XS-APItest/t/utf8.t
@@ -421,11 +421,15 @@ for my $u (sort { utf8::unicode_to_native($a) <=> utf8::unicode_to_native($b) }
         $this_utf8_flags &=
                         ~($UTF8_DISALLOW_ABOVE_31_BIT|$UTF8_WARN_ABOVE_31_BIT);
     }
+
+    my $valid_under_strict = 1;
     if ($n > 0x10FFFF) {
         $this_utf8_flags &= ~($UTF8_DISALLOW_SUPER|$UTF8_WARN_SUPER);
+        $valid_under_strict = 0;
     }
     elsif (($n & 0xFFFE) == 0xFFFE) {
         $this_utf8_flags &= ~($UTF8_DISALLOW_NONCHAR|$UTF8_WARN_NONCHAR);
+        $valid_under_strict = 0;
     }
 
     undef @warnings;
@@ -466,6 +470,29 @@ for my $u (sort { utf8::unicode_to_native($a) <=> utf8::unicode_to_native($b) }
 
     undef @warnings;
 
+    $ret = test_isSTRICT_UTF8_CHAR($bytes, $len);
+    my $expected_len = ($valid_under_strict) ? $len : 0;
+    is($ret, $expected_len, "Verify isSTRICT_UTF8_CHAR($display_bytes) returns expected length: $expected_len");
+
+    unless (is(scalar @warnings, 0,
+               "Verify isSTRICT_UTF8_CHAR() for $hex_n generated no warnings"))
+    {
+        diag "The warnings were: " . join(", ", @warnings);
+    }
+
+    undef @warnings;
+
+    $ret = test_isSTRICT_UTF8_CHAR($bytes, $len - 1);
+    is($ret, 0, "Verify isSTRICT_UTF8_CHAR() with too short length parameter returns 0");
+
+    unless (is(scalar @warnings, 0,
+               "Verify isSTRICT_UTF8_CHAR() generated no warnings"))
+    {
+        diag "The warnings were: " . join(", ", @warnings);
+    }
+
+    undef @warnings;
+
     $ret_ref = test_valid_utf8_to_uvchr($bytes);
     is($ret_ref->[0], $n, "Verify valid_utf8_to_uvchr($display_bytes) returns $hex_n");
     is($ret_ref->[1], $len, "Verify valid_utf8_to_uvchr() for $hex_n returns expected length: $len");
@@ -734,6 +761,14 @@ foreach my $test (@malformations) {
         diag "The warnings were: " . join(", ", @warnings);
     }
 
+    $ret = test_isSTRICT_UTF8_CHAR($bytes, $length);
+    is($ret, 0, "$testname: isSTRICT_UTF8_CHAR returns 0");
+    unless (is(scalar @warnings, 0,
+               "$testname: isSTRICT_UTF8_CHAR() generated no warnings"))
+    {
+        diag "The warnings were: " . join(", ", @warnings);
+    }
+
     for my $j (1 .. $length - 1) {
         my $partial = substr($bytes, 0, $j);
 
@@ -1240,6 +1275,25 @@ foreach my $test (@tests) {
             diag "The warnings were: " . join(", ", @warnings);
         }
 
+        undef @warnings;
+        $ret = test_isSTRICT_UTF8_CHAR($bytes, $length);
+        if ($will_overflow) {
+            is($ret, 0, "isSTRICT_UTF8_CHAR() $testname: returns 0");
+        }
+        else {
+            my $expected_ret = (   $testname =~ /surrogate|non-character/
+                                || $allowed_uv > 0x10FFFF)
+                               ? 0
+                               : $length;
+            is($ret, $expected_ret,
+               "isSTRICT_UTF8_CHAR() $testname: returns expected length: $expected_ret");
+        }
+        unless (is(scalar @warnings, 0,
+                "isSTRICT_UTF8_CHAR() $testname: generated no warnings"))
+        {
+            diag "The warnings were: " . join(", ", @warnings);
+        }
+
         # Test partial character handling, for each byte not a full character
         for my $j (1.. $length - 1) {
 
diff --git a/regcharclass.h b/regcharclass.h
index e0a021aa93..2daedcd3ac 100644
--- a/regcharclass.h
+++ b/regcharclass.h
@@ -1876,6 +1876,6 @@
  * 5c7eb94310e2aaa15702fd6bed24ff0e7ab5448f9a8231d8c49ca96c9e941089 lib/unicore/mktables
  * cdecb300baad839a6f62791229f551a4fa33f3cbdca08e378dc976466354e778 lib/unicore/version
  * 913d2f93f3cb6cdf1664db888bf840bc4eb074eef824e082fceda24a9445e60c regen/charset_translations.pl
- * 1876ece914e2c14ed38c8a589adaa3d8193532c3a5bbe9ea5c3279bc9d29b279 regen/regcharclass.pl
+ * e3dc81163da3e92f7be01e9b953f6edb548eba93f1abb3d334e3b0469573c46d regen/regcharclass.pl
  * 393f8d882713a3ba227351ad0f00ea4839fda74fcf77dcd1cdf31519925adba5 regen/regcharclass_multi_char_folds.pl
  * ex: set ro: */
diff --git a/regen/regcharclass.pl b/regen/regcharclass.pl
index bd677acd15..abc4942354 100755
--- a/regen/regcharclass.pl
+++ b/regen/regcharclass.pl
@@ -1660,6 +1660,49 @@ SURROGATE: Surrogate code points
 #=> UTF8 :no_length_checks only_ebcdic_platform
 #0xA0 - 0x1FFFFF
 
+#STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points, no surrrogates nor non-character code points
+#=> UTF8 :no_length_checks only_ascii_platform
+#0x0080 - 0xD7FF
+#0xE000 - 0xFDCF
+#0xFDF0 - 0xFFFD
+#0x10000 - 0x1FFFD
+#0x20000 - 0x2FFFD
+#0x30000 - 0x3FFFD
+#0x40000 - 0x4FFFD
+#0x50000 - 0x5FFFD
+#0x60000 - 0x6FFFD
+#0x70000 - 0x7FFFD
+#0x80000 - 0x8FFFD
+#0x90000 - 0x9FFFD
+#0xA0000 - 0xAFFFD
+#0xB0000 - 0xBFFFD
+#0xC0000 - 0xCFFFD
+#0xD0000 - 0xDFFFD
+#0xE0000 - 0xEFFFD
+#0xF0000 - 0xFFFFD
+#0x100000 - 0x10FFFD
+#
+#STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points, no surrrogates nor non-character code points
+#=> UTF8 :no_length_checks only_ebcdic_platform
+#0x00A0 - 0xD7FF
+#0xE000 - 0xFDCF
+#0xFDF0 - 0xFFFD
+#0x10000 - 0x1FFFD
+#0x20000 - 0x2FFFD
+#0x30000 - 0x3FFFD
+#0x40000 - 0x4FFFD
+#0x50000 - 0x5FFFD
+#0x60000 - 0x6FFFD
+#0x70000 - 0x7FFFD
+#0x80000 - 0x8FFFD
+#0x90000 - 0x9FFFD
+#0xA0000 - 0xAFFFD
+#0xB0000 - 0xBFFFD
+#0xC0000 - 0xCFFFD
+#0xD0000 - 0xDFFFD
+#0xE0000 - 0xEFFFD
+#0xF0000 - 0xFFFFD
+#0x100000 - 0x10FFFD
 
 QUOTEMETA: Meta-characters that \Q should quote
 => high :fast
diff --git a/utf8.h b/utf8.h
index 41d8118484..dba65d39dc 100644
--- a/utf8.h
+++ b/utf8.h
@@ -334,6 +334,55 @@ C<cp> is Unicode if above 255; otherwise is platform-native.
 /* The above macro handles UTF-8 that has this start byte as the maximum */
 #define _IS_UTF8_CHAR_HIGHEST_START_BYTE 0xF7
 
+/* A helper macro for isSTRICT_UTF8_CHAR, so use that one instead of this.
+ * Like is_UTF8_CHAR_utf8_no_length_checks(), this was moved here and LIKELYs
+ * added manually.
+ *
+	STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points, no
+                          surrrogates nor non-character code points
+*/
+/*** GENERATED CODE ***/
+#define is_STRICT_UTF8_CHAR_utf8_no_length_checks(s)                        \
+( ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) ?                          \
+    ( LIKELY( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 )                          \
+: ( 0xE0 == ((U8*)s)[0] ) ?                                                 \
+    ( LIKELY( ( ( ((U8*)s)[1] & 0xE0 ) == 0xA0 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\
+: ( ( 0xE1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xEC ) || 0xEE == ((U8*)s)[0] ) ?\
+    ( ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\
+: ( 0xED == ((U8*)s)[0] ) ?                                                 \
+    ( LIKELY( ( ( ((U8*)s)[1] & 0xE0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\
+: ( 0xEF == ((U8*)s)[0] ) ?                                                 \
+    ( ( ( 0x80 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0xB6 ) || ( 0xB8 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0xBE ) ) ?\
+	( LIKELY( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ? 3 : 0 )                      \
+    : ( 0xB7 == ((U8*)s)[1] ) ?                                             \
+	( LIKELY( ( ((U8*)s)[2] & 0xF0 ) == 0x80 || ( ((U8*)s)[2] & 0xF0 ) == 0xB0 ) ? 3 : 0 )\
+    : ( ( 0xBF == ((U8*)s)[1] ) && ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBD ) ) ? 3 : 0 )\
+: ( 0xF0 == ((U8*)s)[0] ) ?                                                 \
+    ( ( ( 0x90 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x9E ) || ( 0xA0 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0xAE ) || ( 0xB0 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0xBE ) ) ?\
+	( LIKELY( ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\
+    : ( ((U8*)s)[1] == 0x9F || ( ( ((U8*)s)[1] & 0xEF ) == 0xAF ) ) ?       \
+	( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBE ) ?                  \
+	    ( LIKELY( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ? 4 : 0 )                  \
+	: LIKELY( ( 0xBF == ((U8*)s)[2] ) && ( 0x80 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0xBD ) ) ? 4 : 0 )\
+    : 0 )                                                                   \
+: ( 0xF1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xF3 ) ?                          \
+    ( ( ( ( ((U8*)s)[1] & 0xC8 ) == 0x80 ) || ( ( ((U8*)s)[1] & 0xCC ) == 0x88 ) || ( ( ((U8*)s)[1] & 0xCE ) == 0x8C ) || ( ( ((U8*)s)[1] & 0xCF ) == 0x8E ) ) ?\
+	( LIKELY( ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\
+    : ( ( ((U8*)s)[1] & 0xCF ) == 0x8F ) ?                                  \
+	( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBE ) ?                  \
+	    ( LIKELY( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ? 4 : 0 )                  \
+	: LIKELY( ( 0xBF == ((U8*)s)[2] ) && ( 0x80 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0xBD ) ) ? 4 : 0 )\
+    : 0 )                                                                   \
+: ( 0xF4 == ((U8*)s)[0] ) ?                                                 \
+    ( ( 0x80 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x8E ) ?                      \
+	( LIKELY( ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\
+    : ( 0x8F == ((U8*)s)[1] ) ?                                             \
+	( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBE ) ?                  \
+	    ( LIKELY( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ? 4 : 0 )                  \
+	: LIKELY( ( 0xBF == ((U8*)s)[2] ) && ( 0x80 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0xBD ) ) ? 4 : 0 )\
+    : 0 )                                                                   \
+: 0 )
+
 #endif /* EBCDIC vs ASCII */
 
 /* 2**UTF_ACCUMULATION_SHIFT - 1 */
@@ -885,9 +934,6 @@ point's representation.
 
 #define SHARP_S_SKIP 2
 
-/* If you want to exclude surrogates, and beyond legal Unicode, see the blame
- * log for earlier versions which gave details for these */
-
 /*
 
 =for apidoc Am|STRLEN|isUTF8_CHAR|const U8 *s|const U8 *e
@@ -928,6 +974,35 @@ is a valid UTF-8 character.
 
 #define is_utf8_char_buf(buf, buf_end) isUTF8_CHAR(buf, buf_end)
 
+/*
+
+=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.
+
+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.
+
+=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))
+
 /* Do not use; should be deprecated.  Use isUTF8_CHAR() instead; this is
  * retained solely for backwards compatibility */
 #define IS_UTF8_CHAR(p, n)      (isUTF8_CHAR(p, (p) + (n)) == n)
diff --git a/utfebcdic.h b/utfebcdic.h
index 7d37fbccdb..b0e62ca11a 100644
--- a/utfebcdic.h
+++ b/utfebcdic.h
@@ -275,19 +275,21 @@ explicitly forbidden, and the shortest possible encoding should always be used
 #   define HIGHEST_REPRESENTABLE_UTF8  "\xFF\xA0\xA0\xA0\xA0\xA0\xA0\xA3\xBF\xBF\xBF\xBF\xBF\xBF"
 #endif
 
-/* A helper macro for isUTF8_CHAR, so use that one instead of this.  This was
- * generated by regen/regcharclass.pl, and then moved here.  Then it was
+/* Helper macros for isUTF8_CHAR_foo, so use those instead of this.  These were
+ * generated by regen/regcharclass.pl, and then moved here.  Then they were
  * hand-edited to add some LIKELY() calls, presuming that malformations are
  * unlikely.  The lines that generated it were then commented out.  This was
  * done because it takes on the order of 10 minutes to generate, and is never
- * going to change, unless the generated code is improved, and figuring out
- * the LIKELYs there would be hard.
+ * going to change, unless the generated code is improved, and figuring out the
+ * LIKELYs there would be hard.
  *
-        UTF8_CHAR: Matches legal UTF-EBCDIC variant code points up through 0x1FFFFFF
+ */
+
+#if '^' == 95 /* CP 1047 */
+/*      UTF8_CHAR: Matches legal UTF-EBCDIC variant code points up through 0x1FFFFFF
 
 	0xA0 - 0x1FFFFF
 */
-#if '^' == 95 /* CP 1047 */
 
 /*** GENERATED CODE ***/
 #define is_UTF8_CHAR_utf8_no_length_checks(s)                               \
@@ -303,6 +305,72 @@ explicitly forbidden, and the shortest possible encoding should always be used
     ( LIKELY( ( ( ( ( 0x49 == ((U8*)s)[1] || 0x4A == ((U8*)s)[1] ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\
 : ( ( ( ( ( 0xEE == ((U8*)s)[0] ) && LIKELY( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFC ) == 0x70 ) ) && LIKELY( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) ) && LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) && LIKELY( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )
 
+/*      UTF8_CHAR_STRICT: Matches legal Unicode UTF-8 variant code points, no
+                          surrrogates nor non-character code points */
+/*** GENERATED CODE ***/
+#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s)                  \
+( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) ?\
+	( LIKELY( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\
+    : ( 0x73 == ((U8*)s)[1] ) ?                                             \
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ?\
+	    ( LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ? 4 : 0 )\
+	: LIKELY( ( 0x73 == ((U8*)s)[2] ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFE ) == 0x70 ) ) ? 4 : 0 )\
+    : 0 )
+
+
+/*** GENERATED CODE ***/
+#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s)                  \
+( ( 0xED == ((U8*)s)[0] ) ?                                                 \
+    ( ( ( ( ((U8*)s)[1] & 0xEF ) == 0x49 ) || ( ( ((U8*)s)[1] & 0xF9 ) == 0x51 ) || ((U8*)s)[1] == 0x63 || ( ( ((U8*)s)[1] & 0xFD ) == 0x65 ) || ((U8*)s)[1] == 0x69 || ( ( ((U8*)s)[1] & 0xFD ) == 0x70 ) ) ?\
+	( LIKELY( ( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\
+    : ( ((U8*)s)[1] == 0x4A || ((U8*)s)[1] == 0x52 || ( ( ((U8*)s)[1] & 0xFD ) == 0x54 ) || ((U8*)s)[1] == 0x58 || ((U8*)s)[1] == 0x62 || ( ( ((U8*)s)[1] & 0xFD ) == 0x64 ) || ( ( ((U8*)s)[1] & 0xFD ) == 0x68 ) || ( ( ((U8*)s)[1] & 0xFD ) == 0x71 ) ) ?\
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ?\
+	    ( LIKELY( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\
+	: ( 0x73 == ((U8*)s)[2] ) ?                                         \
+	    ( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ?\
+		( LIKELY( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ? 5 : 0 )\
+	    : LIKELY( ( 0x73 == ((U8*)s)[3] ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFE ) == 0x70 ) ) ? 5 : 0 )\
+	: 0 )                                                               \
+    : 0 )                                                                   \
+: ( 0xEE == ((U8*)s)[0] ) ?                                                 \
+    ( ( 0x41 == ((U8*)s)[1] ) ?                                             \
+	( LIKELY( ( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\
+    : ( 0x42 == ((U8*)s)[1] ) ?                                             \
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ?\
+	    ( LIKELY( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\
+	: ( 0x73 == ((U8*)s)[2] ) ?                                         \
+	    ( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ?\
+		( LIKELY( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFC ) == 0x70 ) ? 5 : 0 )\
+	    : LIKELY( ( 0x73 == ((U8*)s)[3] ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( ((U8*)s)[4] & 0xFE ) == 0x70 ) ) ? 5 : 0 )\
+	: 0 )                                                               \
+    : 0 )                                                                   \
+: 0 )
+
+
+/*** GENERATED CODE ***/
+#define is_STRICT_UTF8_CHAR_utf8_no_length_checks(s)                        \
+( ( 0x80 == ((U8*)s)[0] || ( 0x8A <= ((U8*)s)[0] && ((U8*)s)[0] <= 0x90 ) || ( 0x9A <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xA0 ) || ( 0xAA <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xAC ) || ( 0xAE <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xB6 ) ) ?\
+    ( LIKELY( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFC ) == 0x70 ) ? 2 : 0 )\
+: ( ( ( ((U8*)s)[0] & 0xFC ) == 0xB8 ) || ((U8*)s)[0] == 0xBC || ( ( ((U8*)s)[0] & 0xFE ) == 0xBE ) || ( ( ((U8*)s)[0] & 0xEE ) == 0xCA ) || ( ( ((U8*)s)[0] & 0xFC ) == 0xCC ) ) ?\
+    ( LIKELY( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) ) ? 3 : 0 )\
+: ( 0xDC == ((U8*)s)[0] ) ?                                                 \
+    ( LIKELY( ( ( ( 0x57 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\
+: ( 0xDD == ((U8*)s)[0] ) ?                                                 \
+    ( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x64 ) || ( 0x67 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) ?\
+	( LIKELY( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\
+    : ( 0x73 == ((U8*)s)[1] ) ?                                             \
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x54 ) || ( 0x57 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ?\
+	    ( LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ? 4 : 0 )\
+	: ( 0x55 == ((U8*)s)[2] ) ?                                         \
+	    ( LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x56 ) ) ? 4 : 0 )\
+	: ( 0x56 == ((U8*)s)[2] ) ?                                         \
+	    ( LIKELY( ( 0x57 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ? 4 : 0 )\
+	: LIKELY( ( 0x73 == ((U8*)s)[2] ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFE ) == 0x70 ) ) ? 4 : 0 )\
+    : 0 )                                                                   \
+: ( 0xDE == ((U8*)s)[0] || 0xE1 == ((U8*)s)[0] || 0xEB == ((U8*)s)[0] ) ?   \
+    ( LIKELY( ( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\
+: ( 0xDF == ((U8*)s)[0] || 0xEA == ((U8*)s)[0] || 0xEC == ((U8*)s)[0] ) ? is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s) : is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s) )
+
 #endif
 
 #if '^' == 176 /* CP 037 */
@@ -321,10 +389,74 @@ explicitly forbidden, and the shortest possible encoding should always be used
     ( LIKELY( ( ( ( ( 0x49 == ((U8*)s)[1] || 0x4A == ((U8*)s)[1] ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\
 : ( ( ( ( ( 0xEE == ((U8*)s)[0] ) && LIKELY( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) ) && LIKELY( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ) && LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) && LIKELY( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )
 
+/*** GENERATED CODE ***/
+#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s)                  \
+( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFE ) == 0x70 ) ?\
+	( LIKELY( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\
+    : ( 0x72 == ((U8*)s)[1] ) ?                                             \
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFE ) == 0x70 ) ?\
+	    ( LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ? 4 : 0 )\
+	: LIKELY( ( 0x72 == ((U8*)s)[2] ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || 0x70 == ((U8*)s)[3] ) ) ? 4 : 0 )\
+    : 0 )
+
+
+/*** GENERATED CODE ***/
+#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s)                  \
+( ( 0xED == ((U8*)s)[0] ) ?                                                 \
+    ( ( ( ( ((U8*)s)[1] & 0xEF ) == 0x49 ) || ( ( ((U8*)s)[1] & 0xF9 ) == 0x51 ) || ((U8*)s)[1] == 0x62 || ( ( ((U8*)s)[1] & 0xFD ) == 0x64 ) || ( ( ((U8*)s)[1] & 0xFD ) == 0x68 ) || ((U8*)s)[1] == 0x71 ) ?\
+	( LIKELY( ( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\
+    : ( ((U8*)s)[1] == 0x4A || ((U8*)s)[1] == 0x52 || ( ( ((U8*)s)[1] & 0xFD ) == 0x54 ) || ((U8*)s)[1] == 0x58 || ((U8*)s)[1] == 0x5F || ((U8*)s)[1] == 0x63 || ( ( ((U8*)s)[1] & 0xFD ) == 0x65 ) || ((U8*)s)[1] == 0x69 || ( ( ((U8*)s)[1] & 0xFD ) == 0x70 ) ) ?\
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFE ) == 0x70 ) ?\
+	    ( LIKELY( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\
+	: ( 0x72 == ((U8*)s)[2] ) ?                                         \
+	    ( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFE ) == 0x70 ) ?\
+		( LIKELY( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ? 5 : 0 )\
+	    : LIKELY( ( 0x72 == ((U8*)s)[3] ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || 0x70 == ((U8*)s)[4] ) ) ? 5 : 0 )\
+	: 0 )                                                               \
+    : 0 )                                                                   \
+: ( 0xEE == ((U8*)s)[0] ) ?                                                 \
+    ( ( 0x41 == ((U8*)s)[1] ) ?                                             \
+	( LIKELY( ( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\
+    : ( 0x42 == ((U8*)s)[1] ) ?                                             \
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFE ) == 0x70 ) ?\
+	    ( LIKELY( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\
+	: ( 0x72 == ((U8*)s)[2] ) ?                                         \
+	    ( ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( ((U8*)s)[3] & 0xFE ) == 0x70 ) ?\
+		( LIKELY( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x72 ) ) ? 5 : 0 )\
+	    : LIKELY( ( 0x72 == ((U8*)s)[3] ) && ( ( 0x41 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x59 ) || 0x5F == ((U8*)s)[4] || ( 0x62 <= ((U8*)s)[4] && ((U8*)s)[4] <= 0x6A ) || 0x70 == ((U8*)s)[4] ) ) ? 5 : 0 )\
+	: 0 )                                                               \
+    : 0 )                                                                   \
+: 0 )
+
+
+/*** GENERATED CODE ***/
+#define is_STRICT_UTF8_CHAR_utf8_no_length_checks(s)                        \
+( ( 0x78 == ((U8*)s)[0] || 0x80 == ((U8*)s)[0] || ( 0x8A <= ((U8*)s)[0] && ((U8*)s)[0] <= 0x90 ) || ( 0x9A <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xA0 ) || ( 0xAA <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xAF ) || ( 0xB1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xB5 ) ) ?\
+    ( LIKELY( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) ? 2 : 0 )\
+: ( ((U8*)s)[0] == 0xB7 || ( ( ((U8*)s)[0] & 0xFE ) == 0xB8 ) || ( ( ((U8*)s)[0] & 0xFC ) == 0xBC ) || ( ( ((U8*)s)[0] & 0xEE ) == 0xCA ) || ( ( ((U8*)s)[0] & 0xFC ) == 0xCC ) ) ?\
+    ( LIKELY( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ) ? 3 : 0 )\
+: ( 0xDC == ((U8*)s)[0] ) ?                                                 \
+    ( LIKELY( ( ( ( 0x57 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\
+: ( 0xDD == ((U8*)s)[0] ) ?                                                 \
+    ( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( ((U8*)s)[1] & 0xFE ) == 0x62 || ( 0x66 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( ((U8*)s)[1] & 0xFE ) == 0x70 ) ?\
+	( LIKELY( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\
+    : ( 0x72 == ((U8*)s)[1] ) ?                                             \
+	( ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x54 ) || ( 0x57 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( ((U8*)s)[2] & 0xFE ) == 0x70 ) ?\
+	    ( LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ? 4 : 0 )\
+	: ( 0x55 == ((U8*)s)[2] ) ?                                         \
+	    ( LIKELY( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x56 ) ) ? 4 : 0 )\
+	: ( 0x56 == ((U8*)s)[2] ) ?                                         \
+	    ( LIKELY( ( 0x57 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ? 4 : 0 )\
+	: LIKELY( ( 0x72 == ((U8*)s)[2] ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || 0x70 == ((U8*)s)[3] ) ) ? 4 : 0 )\
+    : 0 )                                                                   \
+: ( 0xDE == ((U8*)s)[0] || 0xE1 == ((U8*)s)[0] || 0xEB == ((U8*)s)[0] ) ?   \
+    ( LIKELY( ( ( ( 0x41 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x59 ) || 0x5F == ((U8*)s)[1] || ( 0x62 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x59 ) || 0x5F == ((U8*)s)[2] || ( 0x62 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x59 ) || 0x5F == ((U8*)s)[3] || ( 0x62 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\
+: ( 0xDF == ((U8*)s)[0] || 0xEA == ((U8*)s)[0] || 0xEC == ((U8*)s)[0] ) ? is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s) : is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s) )
+
 #endif
 
-/* The above macro in both code pages handles UTF-8 that has this start byte
- * (expressed in I8) as the maximum */
+/* is_UTF8_CHAR_utf8_no_length_checks() in both code pages handles UTF-8 that
+ * has this start byte (expressed in I8) as the maximum */
 #define _IS_UTF8_CHAR_HIGHEST_START_BYTE 0xF9
 
 /*