Edit File by line

/* utfebcdic.h

[0] Fix | Delete

[1] Fix | Delete

[2] Fix | Delete

* 2010, 2011 by Larry Wall, Nick Ing-Simmons, and others

[3] Fix | Delete

[4] Fix | Delete

* You may distribute under the terms of either the GNU General Public

[5] Fix | Delete

* License or the Artistic License, as specified in the README file.

[6] Fix | Delete

[7] Fix | Delete

* Macros to implement UTF-EBCDIC as perl's internal encoding

[8] Fix | Delete

* Adapted from version 7.1 of Unicode Technical Report #16:

[9] Fix | Delete

* http://www.unicode.org/unicode/reports/tr16

[10] Fix | Delete

[11] Fix | Delete

* To summarize, the way it works is:

[12] Fix | Delete

* To convert an EBCDIC code point to UTF-EBCDIC:

[13] Fix | Delete

* 1) convert to Unicode. No conversion is necesary for code points above

[14] Fix | Delete

* 255, as Unicode and EBCDIC are identical in this range. For smaller

[15] Fix | Delete

* code points, the conversion is done by lookup in the PL_e2a table (with

[16] Fix | Delete

* inverse PL_a2e) in the generated file 'ebcdic_tables.h'. The 'a'

[17] Fix | Delete

* stands for ASCII platform, meaning 0-255 Unicode.

[18] Fix | Delete

* 2) convert that to a utf8-like string called I8 ('I' stands for

[19] Fix | Delete

* intermediate) with variant characters occupying multiple bytes. This

[20] Fix | Delete

* step is similar to the utf8-creating step from Unicode, but the details

[21] Fix | Delete

* are different. This transformation is called UTF8-Mod. There is a

[22] Fix | Delete

* chart about the bit patterns in a comment later in this file. But

[23] Fix | Delete

* essentially here are the differences:

[24] Fix | Delete

* UTF8 I8

[25] Fix | Delete

* invariant byte starts with 0 starts with 0 or 100

[26] Fix | Delete

* continuation byte starts with 10 starts with 101

[27] Fix | Delete

* start byte same in both: if the code point requires N bytes,

[28] Fix | Delete

* then the leading N bits are 1, followed by a 0. If

[29] Fix | Delete

* all 8 bits in the first byte are 1, the code point

[30] Fix | Delete

* will occupy 14 bytes (compared to 13 in Perl's

[31] Fix | Delete

* extended UTF-8). This is incompatible with what

[32] Fix | Delete

* tr16 implies should be the representation of code

[33] Fix | Delete

* points 2**30 and above, but allows Perl to be able

[34] Fix | Delete

* to represent all code points that fit in a 64-bit

[35] Fix | Delete

* word in either our extended UTF-EBCDIC or UTF-8.

[36] Fix | Delete

* 3) Use the algorithm in tr16 to convert each byte from step 2 into

[37] Fix | Delete

* final UTF-EBCDIC. This is done by table lookup from a table

[38] Fix | Delete

* constructed from the algorithm, reproduced in ebcdic_tables.h as

[39] Fix | Delete

* PL_utf2e, with its inverse being PL_e2utf. They are constructed so that

[40] Fix | Delete

* all EBCDIC invariants remain invariant, but no others do, and the first

[41] Fix | Delete

* byte of a variant will always have its upper bit set. But note that

[42] Fix | Delete

* the upper bit of some invariants is also 1. The table also is designed

[43] Fix | Delete

* so that lexically comparing two UTF-EBCDIC-variant characters yields

[44] Fix | Delete

* the Unicode code point order. (To get native code point order, one has

[45] Fix | Delete

* to convert the latin1-range characters to their native code point

[46] Fix | Delete

* value.)

[47] Fix | Delete

[48] Fix | Delete

* For example, the ordinal value of 'A' is 193 in EBCDIC, and also is 193 in

[49] Fix | Delete

* UTF-EBCDIC. Step 1) converts it to 65, Step 2 leaves it at 65, and Step 3

[50] Fix | Delete

* converts it back to 193. As an example of how a variant character works,

[51] Fix | Delete

* take LATIN SMALL LETTER Y WITH DIAERESIS, which is typically 0xDF in

[52] Fix | Delete

* EBCDIC. Step 1 converts it to the Unicode value, 0xFF. Step 2 converts

[53] Fix | Delete

* that to two bytes = 11000111 10111111 = C7 BF, and Step 3 converts those to

[54] Fix | Delete

* 0x8B 0x73.

[55] Fix | Delete

[56] Fix | Delete

* If you're starting from Unicode, skip step 1. For UTF-EBCDIC to straight

[57] Fix | Delete

* EBCDIC, reverse the steps.

[58] Fix | Delete

[59] Fix | Delete

* The EBCDIC invariants have been chosen to be those characters whose Unicode

[60] Fix | Delete

* equivalents have ordinal numbers less than 160, that is the same characters

[61] Fix | Delete

* that are expressible in ASCII, plus the C1 controls. So there are 160

[62] Fix | Delete

* invariants instead of the 128 in UTF-8.

[63] Fix | Delete

[64] Fix | Delete

* The purpose of Step 3 is to make the encoding be invariant for the chosen

[65] Fix | Delete

* characters. This messes up the convenient patterns found in step 2, so

[66] Fix | Delete

* generally, one has to undo step 3 into a temporary to use them. However,

[67] Fix | Delete

* one "shadow", or parallel table, PL_utf8skip, has been constructed that

[68] Fix | Delete

* doesn't require undoing things. It is such that for each byte, it says

[69] Fix | Delete

* how long the sequence is if that (UTF-EBCDIC) byte were to begin it

[70] Fix | Delete

[71] Fix | Delete

* There are actually 3 slightly different UTF-EBCDIC encodings in

[72] Fix | Delete

* ebcdic_tables.h, one for each of the code pages recognized by Perl. That

[73] Fix | Delete

* means that there are actually three different sets of tables, one for each

[74] Fix | Delete

* code page. (If Perl is compiled on platforms using another EBCDIC code

[75] Fix | Delete

* page, it may not compile, or Perl may silently mistake it for one of the

[76] Fix | Delete

* three.)

[77] Fix | Delete

[78] Fix | Delete

* Note that tr16 actually only specifies one version of UTF-EBCDIC, based on

[79] Fix | Delete

* the 1047 encoding, and which is supposed to be used for all code pages.

[80] Fix | Delete

* But this doesn't work. To illustrate the problem, consider the '^' character.

[81] Fix | Delete

* On a 037 code page it is the single byte 176, whereas under 1047 UTF-EBCDIC

[82] Fix | Delete

* it is the single byte 95. If Perl implemented tr16 exactly, it would mean

[83] Fix | Delete

* that changing a string containing '^' to UTF-EBCDIC would change that '^'

[84] Fix | Delete

* from 176 to 95 (and vice-versa), violating the rule that ASCII-range

[85] Fix | Delete

* characters are the same in UTF-8 or not. Much code in Perl assumes this

[86] Fix | Delete

* rule. See for example

[87] Fix | Delete

* http://grokbase.com/t/perl/mvs/025xf0yhmn/utf-ebcdic-for-posix-bc-malformed-utf-8-character

[88] Fix | Delete

* What Perl does is create a version of UTF-EBCDIC suited to each code page;

[89] Fix | Delete

* the one for the 1047 code page is identical to what's specified in tr16.

[90] Fix | Delete

* This complicates interchanging files between computers using different code

[91] Fix | Delete

* pages. Best is to convert to I8 before sending them, as the I8

[92] Fix | Delete

* representation is the same no matter what the underlying code page is.

[93] Fix | Delete

[94] Fix | Delete

* Because of the way UTF-EBCDIC is constructed, the lowest 32 code points that

[95] Fix | Delete

* aren't equivalent to ASCII characters nor C1 controls form the set of

[96] Fix | Delete

* continuation bytes; the remaining 64 non-ASCII, non-control code points form

[97] Fix | Delete

* the potential start bytes, in order. (However, the first 5 of these lead to

[98] Fix | Delete

* malformed overlongs, so there really are only 59 start bytes, and the first

[99] Fix | Delete

* three of the 59 are the start bytes for the Latin1 range.) Hence the

[100] Fix | Delete

* UTF-EBCDIC for the smallest variant code point, 0x160, will have likely 0x41

[101] Fix | Delete

* as its continuation byte, provided 0x41 isn't an ASCII or C1 equivalent.

[102] Fix | Delete

* And its start byte will be the code point that is 37 (32+5) non-ASCII,

[103] Fix | Delete

* non-control code points past it. (0 - 3F are controls, and 40 is SPACE,

[104] Fix | Delete

* leaving 41 as the first potentially available one.) In contrast, on ASCII

[105] Fix | Delete

* platforms, the first 64 (not 32) non-ASCII code points are the continuation

[106] Fix | Delete

* bytes. And the first 2 (not 5) potential start bytes form overlong

[107] Fix | Delete

* malformed sequences.

[108] Fix | Delete

[109] Fix | Delete

* EBCDIC characters above 0xFF are the same as Unicode in Perl's

[110] Fix | Delete

* implementation of all 3 encodings, so for those Step 1 is trivial.

[111] Fix | Delete

[112] Fix | Delete

* (Note that the entries for invariant characters are necessarily the same in

[113] Fix | Delete

* PL_e2a and PL_e2utf; likewise for their inverses.)

[114] Fix | Delete

[115] Fix | Delete

* UTF-EBCDIC strings are the same length or longer than UTF-8 representations

[116] Fix | Delete

* of the same string. The maximum code point representable as 2 bytes in

[117] Fix | Delete

* UTF-EBCDIC is 0x3FFF, instead of 0x7FFF in UTF-8.

[118] Fix | Delete

[119] Fix | Delete

[120] Fix | Delete

START_EXTERN_C

[121] Fix | Delete

[122] Fix | Delete

#ifdef DOINIT

[123] Fix | Delete

[124] Fix | Delete

#include "ebcdic_tables.h"

[125] Fix | Delete

[126] Fix | Delete

#else

[127] Fix | Delete

EXTCONST U8 PL_utf8skip[];

[128] Fix | Delete

EXTCONST U8 PL_e2utf[];

[129] Fix | Delete

EXTCONST U8 PL_utf2e[];

[130] Fix | Delete

EXTCONST U8 PL_e2a[];

[131] Fix | Delete

EXTCONST U8 PL_a2e[];

[132] Fix | Delete

EXTCONST U8 PL_fold[];

[133] Fix | Delete

EXTCONST U8 PL_fold_latin1[];

[134] Fix | Delete

EXTCONST U8 PL_latin1_lc[];

[135] Fix | Delete

EXTCONST U8 PL_mod_latin1_uc[];

[136] Fix | Delete

#endif

[137] Fix | Delete

[138] Fix | Delete

END_EXTERN_C

[139] Fix | Delete

[140] Fix | Delete

/* EBCDIC-happy ways of converting native code to UTF-8 */

[141] Fix | Delete

[142] Fix | Delete

/* Use these when ch is known to be < 256 */

[143] Fix | Delete

#define NATIVE_TO_LATIN1(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) PL_e2a[(U8)(ch)])

[144] Fix | Delete

#define LATIN1_TO_NATIVE(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) PL_a2e[(U8)(ch)])

[145] Fix | Delete

[146] Fix | Delete

/* Use these on bytes */

[147] Fix | Delete

#define NATIVE_UTF8_TO_I8(b) (__ASSERT_(FITS_IN_8_BITS(b)) PL_e2utf[(U8)(b)])

[148] Fix | Delete

#define I8_TO_NATIVE_UTF8(b) (__ASSERT_(FITS_IN_8_BITS(b)) PL_utf2e[(U8)(b)])

[149] Fix | Delete

[150] Fix | Delete

/* Transforms in wide UV chars */

[151] Fix | Delete

#define NATIVE_TO_UNI(ch) (FITS_IN_8_BITS(ch) ? NATIVE_TO_LATIN1(ch) : (UV) (ch))

[152] Fix | Delete

#define UNI_TO_NATIVE(ch) (FITS_IN_8_BITS(ch) ? LATIN1_TO_NATIVE(ch) : (UV) (ch))

[153] Fix | Delete

[154] Fix | Delete

/* How wide can a single UTF-8 encoded character become in bytes. */

[155] Fix | Delete

/* NOTE: Strictly speaking Perl's UTF-8 should not be called UTF-8 since UTF-8

[156] Fix | Delete

* is an encoding of Unicode, and Unicode's upper limit, 0x10FFFF, can be

[157] Fix | Delete

* expressed with 5 bytes. However, Perl thinks of UTF-8 as a way to encode

[158] Fix | Delete

* non-negative integers in a binary format, even those above Unicode. 14 is

[159] Fix | Delete

* the smallest number that covers 2**64

[160] Fix | Delete

[161] Fix | Delete

* WARNING: This number must be in sync with the value in

[162] Fix | Delete

* regen/charset_translations.pl. */

[163] Fix | Delete

#define UTF8_MAXBYTES 14

[164] Fix | Delete

[165] Fix | Delete

[166] Fix | Delete

The following table is adapted from tr16, it shows the I8 encoding of Unicode code points.

[167] Fix | Delete

[168] Fix | Delete

Unicode U32 Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th Byte

[169] Fix | Delete

U+0000..U+007F 000000000xxxxxxx 0xxxxxxx

[170] Fix | Delete

U+0080..U+009F 00000000100xxxxx 100xxxxx

[171] Fix | Delete

U+00A0..U+03FF 000000yyyyyxxxxx 110yyyyy 101xxxxx

[172] Fix | Delete

U+0400..U+3FFF 00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx

[173] Fix | Delete

U+4000..U+3FFFF 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx

[174] Fix | Delete

U+40000..U+3FFFFF 0vvwwwwwzzzzzyyyyyxxxxx 111110vv 101wwwww 101zzzzz 101yyyyy 101xxxxx

[175] Fix | Delete

U+400000..U+3FFFFFF 0uvvvvvwwwwwzzzzzyyyyyxxxxx 1111110u 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx

[176] Fix | Delete

U+4000000..U+3FFFFFFF 00uuuuuvvvvvwwwwwzzzzzyyyyyxxxxx 11111110 101uuuuu 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx

[177] Fix | Delete

[178] Fix | Delete

Beyond this, Perl uses an incompatible extension, similar to the one used in

[179] Fix | Delete

regular UTF-8. There are now 14 bytes. A full 32 bits of information thus looks like this:

[180] Fix | Delete

1st Byte 2nd-7th 8th Byte 9th Byte 10th B 11th B 12th B 13th B 14th B

[181] Fix | Delete

U+40000000..U+FFFFFFFF ttuuuuuvvvvvwwwwwzzzzzyyyyyxxxxx 11111111 10100000 101000tt 101uuuuu 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx

[182] Fix | Delete

[183] Fix | Delete

For 32-bit words, the 2nd through 7th bytes effectively function as leading

[184] Fix | Delete

zeros. Above 32 bits, these fill up, with each byte yielding 5 bits of

[185] Fix | Delete

information, so that with 13 continuation bytes, we can handle 65 bits, just

[186] Fix | Delete

above what a 64 bit word can hold

[187] Fix | Delete

[188] Fix | Delete

The following table gives the I8:

[189] Fix | Delete

[190] Fix | Delete

I8 Code Points 1st Byte 2nd Byte 3rd 4th 5th 6th 7th 8th 9th-14th

[191] Fix | Delete

[192] Fix | Delete

0x0000..0x009F 00..9F

[193] Fix | Delete

0x00A0..0x00FF * C5..C7 A0..BF

[194] Fix | Delete

U+0100..U+03FF C8..DF A0..BF

[195] Fix | Delete

U+0400..U+3FFF * E1..EF A0..BF A0..BF

[196] Fix | Delete

U+4000..U+7FFF F0 * B0..BF A0..BF A0..BF

[197] Fix | Delete

U+8000..U+D7FF F1 A0..B5 A0..BF A0..BF

[198] Fix | Delete

U+D800..U+DFFF F1 B6..B7 A0..BF A0..BF (surrogates)

[199] Fix | Delete

U+E000..U+FFFF F1 B8..BF A0..BF A0..BF

[200] Fix | Delete

U+10000..U+3FFFF F2..F7 A0..BF A0..BF A0..BF

[201] Fix | Delete

U+40000..U+FFFFF F8 * A8..BF A0..BF A0..BF A0..BF

[202] Fix | Delete

U+100000..U+10FFFF F9 A0..A1 A0..BF A0..BF A0..BF

[203] Fix | Delete

Below are above-Unicode code points

[204] Fix | Delete

U+110000..U+1FFFFF F9 A2..BF A0..BF A0..BF A0..BF

[205] Fix | Delete

U+200000..U+3FFFFF FA..FB A0..BF A0..BF A0..BF A0..BF

[206] Fix | Delete

U+400000..U+1FFFFFF FC * A4..BF A0..BF A0..BF A0..BF A0..BF

[207] Fix | Delete

U+2000000..U+3FFFFFF FD A0..BF A0..BF A0..BF A0..BF A0..BF

[208] Fix | Delete

U+4000000..U+3FFFFFFF FE * A2..BF A0..BF A0..BF A0..BF A0..BF A0..BF

[209] Fix | Delete

U+40000000.. FF A0..BF A0..BF A0..BF A0..BF A0..BF A0..BF * A1..BF A0..BF

[210] Fix | Delete

[211] Fix | Delete

Note the gaps before several of the byte entries above marked by '*'. These are

[212] Fix | Delete

caused by legal UTF-8 avoiding non-shortest encodings: it is technically

[213] Fix | Delete

possible to UTF-8-encode a single code point in different ways, but that is

[214] Fix | Delete

explicitly forbidden, and the shortest possible encoding should always be used

[215] Fix | Delete

(and that is what Perl does). */

[216] Fix | Delete

[217] Fix | Delete

/* This is a fundamental property of UTF-EBCDIC */

[218] Fix | Delete

#define OFFUNI_IS_INVARIANT(c) (((UV)(c)) < 0xA0)

[219] Fix | Delete

[220] Fix | Delete

/* It turns out that on EBCDIC platforms, the invariants are the characters

[221] Fix | Delete

* that have ASCII equivalents, plus the C1 controls. Since the C0 controls

[222] Fix | Delete

* and DELETE are ASCII, this is the same as: (isASCII(uv) || isCNTRL_L1(uv))

[223] Fix | Delete

* */

[224] Fix | Delete

#define UVCHR_IS_INVARIANT(uv) cBOOL(FITS_IN_8_BITS(uv) \

[225] Fix | Delete

&& (PL_charclass[(U8) (uv)] & (_CC_mask(_CC_ASCII) | _CC_mask(_CC_CNTRL))))

[226] Fix | Delete

[227] Fix | Delete

/* UTF-EBCDIC semantic macros - We used to transform back into I8 and then

[228] Fix | Delete

* compare, but now only have to do a single lookup by using a bit in

[229] Fix | Delete

* l1_char_class_tab.h.

[230] Fix | Delete

* Comments as to the meaning of each are given at their corresponding utf8.h

[231] Fix | Delete

* definitions. */

[232] Fix | Delete

[233] Fix | Delete

#define UTF8_IS_START(c) _generic_isCC(c, _CC_UTF8_IS_START)

[234] Fix | Delete

[235] Fix | Delete

#define UTF_IS_CONTINUATION_MASK 0xE0

[236] Fix | Delete

[237] Fix | Delete

#define UTF8_IS_CONTINUATION(c) _generic_isCC(c, _CC_UTF8_IS_CONTINUATION)

[238] Fix | Delete

[239] Fix | Delete

/* The above instead could be written as this:

[240] Fix | Delete

#define UTF8_IS_CONTINUATION(c) \

[241] Fix | Delete

(((NATIVE_UTF8_TO_I8(c) & UTF_IS_CONTINUATION_MASK) \

[242] Fix | Delete

== UTF_CONTINUATION_MARK)

[243] Fix | Delete

[244] Fix | Delete

[245] Fix | Delete

/* Equivalent to ! UVCHR_IS_INVARIANT(c) */

[246] Fix | Delete

#define UTF8_IS_CONTINUED(c) cBOOL(FITS_IN_8_BITS(c) \

[247] Fix | Delete

&& ! (PL_charclass[(U8) (c)] & (_CC_mask(_CC_ASCII) | _CC_mask(_CC_CNTRL))))

[248] Fix | Delete

[249] Fix | Delete

#define UTF8_IS_DOWNGRADEABLE_START(c) _generic_isCC(c, \

[250] Fix | Delete

_CC_UTF8_IS_DOWNGRADEABLE_START)

[251] Fix | Delete

[252] Fix | Delete

/* Equivalent to (UTF8_IS_START(c) && ! UTF8_IS_DOWNGRADEABLE_START(c))

[253] Fix | Delete

* Makes sure that the START bit is set and the DOWNGRADEABLE bit isn't */

[254] Fix | Delete

#define UTF8_IS_ABOVE_LATIN1(c) cBOOL(FITS_IN_8_BITS(c) \

[255] Fix | Delete

&& ((PL_charclass[(U8) (c)] & ( _CC_mask(_CC_UTF8_IS_START) \

[256] Fix | Delete

|_CC_mask(_CC_UTF8_IS_DOWNGRADEABLE_START))) \

[257] Fix | Delete

== _CC_mask(_CC_UTF8_IS_START)))

[258] Fix | Delete

[259] Fix | Delete

#define isUTF8_POSSIBLY_PROBLEMATIC(c) \

[260] Fix | Delete

_generic_isCC(c, _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE)

[261] Fix | Delete

[262] Fix | Delete

#define UTF_CONTINUATION_MARK 0xA0

[263] Fix | Delete

#define UTF_ACCUMULATION_SHIFT 5

[264] Fix | Delete

[265] Fix | Delete

/* ^? is defined to be APC on EBCDIC systems. See the definition of toCTRL()

[266] Fix | Delete

* for more */

[267] Fix | Delete

#define QUESTION_MARK_CTRL LATIN1_TO_NATIVE(0x9F)

[268] Fix | Delete

[269] Fix | Delete

/* Any I8 string larger than this will overflow the word if it were converted into a UV */

[270] Fix | Delete

#if defined(UV_IS_QUAD)

[271] Fix | Delete

# define HIGHEST_REPRESENTABLE_UTF8 "\xFF\xAF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF"

[272] Fix | Delete

#else

[273] Fix | Delete

# define HIGHEST_REPRESENTABLE_UTF8 "\xFF\xA0\xA0\xA0\xA0\xA0\xA0\xA3\xBF\xBF\xBF\xBF\xBF\xBF"

[274] Fix | Delete

#endif

[275] Fix | Delete

[276] Fix | Delete

/* Helper macros for isUTF8_CHAR_foo, so use those instead of this. These were

[277] Fix | Delete

* generated by regen/regcharclass.pl, and then moved here. Then they were

[278] Fix | Delete

* hand-edited to add some LIKELY() calls, presuming that malformations are

[279] Fix | Delete

* unlikely. The lines that generated it were then commented out. This was

[280] Fix | Delete

* done because it takes on the order of 10 minutes to generate, and is never

[281] Fix | Delete

* going to change, unless the generated code is improved, and figuring out the

[282] Fix | Delete

* LIKELYs there would be hard.

[283] Fix | Delete

[284] Fix | Delete

[285] Fix | Delete

[286] Fix | Delete

#if '^' == 95 /* CP 1047 */

[287] Fix | Delete

/* UTF8_CHAR: Matches legal UTF-EBCDIC variant code points up through 0x1FFFFFF

[288] Fix | Delete

[289] Fix | Delete

0xA0 - 0x1FFFFF

[290] Fix | Delete

[291] Fix | Delete

[292] Fix | Delete

/*** GENERATED CODE ***/

[293] Fix | Delete

#define is_UTF8_CHAR_utf8_no_length_checks(s) \

[294] Fix | Delete

( ( 0x80 == ((const U8*)s)[0] || ( 0x8A <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0x90 ) || ( 0x9A <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xA0 ) || ( 0xAA <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xAC ) || ( 0xAE <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xB6 ) ) ?\

[295] Fix | Delete

( LIKELY( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFC ) == 0x70 ) ? 2 : 0 )\

[296] Fix | Delete

: ( ( ( ((const U8*)s)[0] & 0xFC ) == 0xB8 ) || ((const U8*)s)[0] == 0xBC || ( ( ((const U8*)s)[0] & 0xFE ) == 0xBE ) || ( ( ((const U8*)s)[0] & 0xEE ) == 0xCA ) || ( ( ((const U8*)s)[0] & 0xFC ) == 0xCC ) ) ?\

[297] Fix | Delete

( LIKELY( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) ) ? 3 : 0 )\

[298] Fix | Delete

: ( 0xDC == ((const U8*)s)[0] ) ? \

[299] Fix | Delete

( LIKELY( ( ( ( 0x57 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\

[300] Fix | Delete

: ( ( 0xDD <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xDF ) || 0xE1 == ((const U8*)s)[0] || ( 0xEA <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xEC ) ) ?\

[301] Fix | Delete

( LIKELY( ( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\

[302] Fix | Delete

: ( 0xED == ((const U8*)s)[0] ) ? \

[303] Fix | Delete

( LIKELY( ( ( ( ( 0x49 == ((const U8*)s)[1] || 0x4A == ((const U8*)s)[1] ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( ((const U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\

[304] Fix | Delete

: ( ( ( ( ( 0xEE == ((const U8*)s)[0] ) && LIKELY( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFC ) == 0x70 ) ) && LIKELY( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) ) && LIKELY( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) && LIKELY( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( ((const U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )

[305] Fix | Delete

[306] Fix | Delete

/* UTF8_CHAR_STRICT: Matches legal Unicode UTF-8 variant code points, no

[307] Fix | Delete

surrrogates nor non-character code points */

[308] Fix | Delete

/*** GENERATED CODE ***/

[309] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s) \

[310] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) ?\

[311] Fix | Delete

( LIKELY( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\

[312] Fix | Delete

: ( 0x73 == ((const U8*)s)[1] ) ? \

[313] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ?\

[314] Fix | Delete

( LIKELY( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ? 4 : 0 )\

[315] Fix | Delete

: LIKELY( ( 0x73 == ((const U8*)s)[2] ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFE ) == 0x70 ) ) ? 4 : 0 )\

[316] Fix | Delete

: 0 )

[317] Fix | Delete

[318] Fix | Delete

[319] Fix | Delete

/*** GENERATED CODE ***/

[320] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s) \

[321] Fix | Delete

( ( 0xED == ((const U8*)s)[0] ) ? \

[322] Fix | Delete

( ( ( ( ((const U8*)s)[1] & 0xEF ) == 0x49 ) || ( ( ((const U8*)s)[1] & 0xF9 ) == 0x51 ) || ((const U8*)s)[1] == 0x63 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x65 ) || ((const U8*)s)[1] == 0x69 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x70 ) ) ?\

[323] Fix | Delete

( LIKELY( ( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( ((const U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\

[324] Fix | Delete

: ( ((const U8*)s)[1] == 0x4A || ((const U8*)s)[1] == 0x52 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x54 ) || ((const U8*)s)[1] == 0x58 || ((const U8*)s)[1] == 0x62 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x64 ) || ( ( ((const U8*)s)[1] & 0xFD ) == 0x68 ) || ( ( ((const U8*)s)[1] & 0xFD ) == 0x71 ) ) ?\

[325] Fix | Delete

[326] Fix | Delete

( LIKELY( ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( ((const U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )\

[327] Fix | Delete

: ( 0x73 == ((const U8*)s)[2] ) ? \

[328] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ?\

[329] Fix | Delete

( LIKELY( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( ((const U8*)s)[4] & 0xFC ) == 0x70 ) ? 5 : 0 )\

[330] Fix | Delete

: LIKELY( ( 0x73 == ((const U8*)s)[3] ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( ((const U8*)s)[4] & 0xFE ) == 0x70 ) ) ? 5 : 0 )\

[331] Fix | Delete

: 0 ) \

[332] Fix | Delete

: 0 ) \

[333] Fix | Delete

: ( 0xEE == ((const U8*)s)[0] ) ? \

[334] Fix | Delete

( ( 0x41 == ((const U8*)s)[1] ) ? \

[335] Fix | Delete

[336] Fix | Delete

: ( 0x42 == ((const U8*)s)[1] ) ? \

[337] Fix | Delete

[338] Fix | Delete

[339] Fix | Delete

: ( 0x73 == ((const U8*)s)[2] ) ? \

[340] Fix | Delete

[341] Fix | Delete

[342] Fix | Delete

[343] Fix | Delete

: 0 ) \

[344] Fix | Delete

: 0 ) \

[345] Fix | Delete

: 0 )

[346] Fix | Delete

[347] Fix | Delete

[348] Fix | Delete

/*** GENERATED CODE ***/

[349] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks(s) \

[350] Fix | Delete

[351] Fix | Delete

[352] Fix | Delete

[353] Fix | Delete

[354] Fix | Delete

: ( 0xDC == ((const U8*)s)[0] ) ? \

[355] Fix | Delete

[356] Fix | Delete

: ( 0xDD == ((const U8*)s)[0] ) ? \

[357] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x64 ) || ( 0x67 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) ?\

[358] Fix | Delete

[359] Fix | Delete

: ( 0x73 == ((const U8*)s)[1] ) ? \

[360] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x54 ) || ( 0x57 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ?\

[361] Fix | Delete

[362] Fix | Delete

: ( 0x55 == ((const U8*)s)[2] ) ? \

[363] Fix | Delete

( LIKELY( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x56 ) ) ? 4 : 0 )\

[364] Fix | Delete

: ( 0x56 == ((const U8*)s)[2] ) ? \

[365] Fix | Delete

( LIKELY( ( 0x57 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ? 4 : 0 )\

[366] Fix | Delete

[367] Fix | Delete

: 0 ) \

[368] Fix | Delete

: ( 0xDE == ((const U8*)s)[0] || 0xE1 == ((const U8*)s)[0] || 0xEB == ((const U8*)s)[0] ) ? \

[369] Fix | Delete

[370] Fix | Delete

: ( 0xDF == ((const U8*)s)[0] || 0xEA == ((const U8*)s)[0] || 0xEC == ((const U8*)s)[0] ) ? is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s) : is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s) )

[371] Fix | Delete

[372] Fix | Delete

/* C9_STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points

[373] Fix | Delete

including non-character code points, no surrogates

[374] Fix | Delete

0x00A0 - 0xD7FF

[375] Fix | Delete

0xE000 - 0x10FFFF

[376] Fix | Delete

[377] Fix | Delete

/*** GENERATED CODE ***/

[378] Fix | Delete

#define is_C9_STRICT_UTF8_CHAR_utf8_no_length_checks(s) \

[379] Fix | Delete

[380] Fix | Delete

[381] Fix | Delete

[382] Fix | Delete

[383] Fix | Delete

: ( 0xDC == ((const U8*)s)[0] ) ? \

[384] Fix | Delete

[385] Fix | Delete

: ( 0xDD == ((const U8*)s)[0] ) ? \

[386] Fix | Delete

( LIKELY( ( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x64 ) || ( 0x67 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFC ) == 0x70 ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) ? 4 : 0 )\

[387] Fix | Delete

: ( ( ((const U8*)s)[0] & 0xFE ) == 0xDE || 0xE1 == ((const U8*)s)[0] || ( 0xEA <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xEC ) ) ?\

[388] Fix | Delete

[389] Fix | Delete

: ( 0xED == ((const U8*)s)[0] ) ? \

[390] Fix | Delete

[391] Fix | Delete

: LIKELY( ( ( ( ( 0xEE == ((const U8*)s)[0] ) && ( 0x41 == ((const U8*)s)[1] || 0x42 == ((const U8*)s)[1] ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFC ) == 0x70 ) ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( ((const U8*)s)[4] & 0xFC ) == 0x70 ) ) ? 5 : 0 )

[392] Fix | Delete

[393] Fix | Delete

#endif

[394] Fix | Delete

[395] Fix | Delete

#if '^' == 176 /* CP 037 */

[396] Fix | Delete

[397] Fix | Delete

/*** GENERATED CODE ***/

[398] Fix | Delete

#define is_UTF8_CHAR_utf8_no_length_checks(s) \

[399] Fix | Delete

( ( 0x78 == ((const U8*)s)[0] || 0x80 == ((const U8*)s)[0] || ( 0x8A <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0x90 ) || ( 0x9A <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xA0 ) || ( 0xAA <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xAF ) || ( 0xB1 <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xB5 ) ) ?\

[400] Fix | Delete

( LIKELY( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) ? 2 : 0 )\

[401] Fix | Delete

: ( ((const U8*)s)[0] == 0xB7 || ( ( ((const U8*)s)[0] & 0xFE ) == 0xB8 ) || ( ( ((const U8*)s)[0] & 0xFC ) == 0xBC ) || ( ( ((const U8*)s)[0] & 0xEE ) == 0xCA ) || ( ( ((const U8*)s)[0] & 0xFC ) == 0xCC ) ) ?\

[402] Fix | Delete

( LIKELY( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) ? 3 : 0 )\

[403] Fix | Delete

: ( 0xDC == ((const U8*)s)[0] ) ? \

[404] Fix | Delete

( LIKELY( ( ( ( 0x57 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\

[405] Fix | Delete

: ( ( 0xDD <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xDF ) || 0xE1 == ((const U8*)s)[0] || ( 0xEA <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xEC ) ) ?\

[406] Fix | Delete

( LIKELY( ( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\

[407] Fix | Delete

: ( 0xED == ((const U8*)s)[0] ) ? \

[408] Fix | Delete

( LIKELY( ( ( ( ( 0x49 == ((const U8*)s)[1] || 0x4A == ((const U8*)s)[1] ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || 0x5F == ((const U8*)s)[4] || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\

[409] Fix | Delete

: ( ( ( ( ( 0xEE == ((const U8*)s)[0] ) && LIKELY( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) ) && LIKELY( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) && LIKELY( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) && LIKELY( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || 0x5F == ((const U8*)s)[4] || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )

[410] Fix | Delete

[411] Fix | Delete

/* XXX Below do not have LIKELY() added */

[412] Fix | Delete

/*** GENERATED CODE ***/

[413] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s) \

[414] Fix | Delete

( ( ( ( ((const U8*)s)[1] & 0xEF ) == 0x49 ) || ( ( ((const U8*)s)[1] & 0xF9 ) == 0x51 ) || ((const U8*)s)[1] == 0x62 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x64 ) || ( ( ((const U8*)s)[1] & 0xFD ) == 0x68 ) || ((const U8*)s)[1] == 0x71 ) ?\

[415] Fix | Delete

( ( ( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || 0x5F == ((const U8*)s)[4] || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\

[416] Fix | Delete

: ( ((const U8*)s)[1] == 0x4A || ((const U8*)s)[1] == 0x52 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x54 ) || ((const U8*)s)[1] == 0x58 || ((const U8*)s)[1] == 0x5F || ((const U8*)s)[1] == 0x63 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x65 ) || ((const U8*)s)[1] == 0x69 || ( ( ((const U8*)s)[1] & 0xFD ) == 0x70 ) ) ?\

[417] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFE ) == 0x70 ) ?\

[418] Fix | Delete

( ( ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || 0x5F == ((const U8*)s)[4] || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x72 ) ) ) ? 5 : 0 )\

[419] Fix | Delete

: ( 0x72 == ((const U8*)s)[2] ) ? \

[420] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( ((const U8*)s)[3] & 0xFE ) == 0x70 ) ?\

[421] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || 0x5F == ((const U8*)s)[4] || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x72 ) ) ? 5 : 0 )\

[422] Fix | Delete

: ( ( 0x72 == ((const U8*)s)[3] ) && ( ( 0x41 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x59 ) || 0x5F == ((const U8*)s)[4] || ( 0x62 <= ((const U8*)s)[4] && ((const U8*)s)[4] <= 0x6A ) || 0x70 == ((const U8*)s)[4] ) ) ? 5 : 0 )\

[423] Fix | Delete

: 0 ) \

[424] Fix | Delete

: 0 )

[425] Fix | Delete

[426] Fix | Delete

[427] Fix | Delete

/*** GENERATED CODE ***/

[428] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s) \

[429] Fix | Delete

( ( 0xEE == ((const U8*)s)[0] ) ? \

[430] Fix | Delete

( ( 0x41 == ((const U8*)s)[1] ) ? \

[431] Fix | Delete

[432] Fix | Delete

: ( 0x42 == ((const U8*)s)[1] ) ? \

[433] Fix | Delete

[434] Fix | Delete

[435] Fix | Delete

: ( 0x72 == ((const U8*)s)[2] ) ? \

[436] Fix | Delete

[437] Fix | Delete

[438] Fix | Delete

[439] Fix | Delete

: 0 ) \

[440] Fix | Delete

: 0 ) \

[441] Fix | Delete

: 0 )

[442] Fix | Delete

[443] Fix | Delete

[444] Fix | Delete

/*** GENERATED CODE ***/

[445] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part2(s) \

[446] Fix | Delete

( ( ( ( ( 0x57 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )

[447] Fix | Delete

[448] Fix | Delete

[449] Fix | Delete

/*** GENERATED CODE ***/

[450] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks_part3(s) \

[451] Fix | Delete

( ( 0xDD == ((const U8*)s)[0] ) ? \

[452] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( ((const U8*)s)[1] & 0xFE ) == 0x62 || ( 0x66 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFE ) == 0x70 ) ?\

[453] Fix | Delete

( ( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\

[454] Fix | Delete

: ( 0x72 == ((const U8*)s)[1] ) ? \

[455] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x54 ) || ( 0x57 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( ((const U8*)s)[2] & 0xFE ) == 0x70 ) ?\

[456] Fix | Delete

[457] Fix | Delete

: ( 0x55 == ((const U8*)s)[2] ) ? \

[458] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x56 ) ) ? 4 : 0 )\

[459] Fix | Delete

: ( 0x56 == ((const U8*)s)[2] ) ? \

[460] Fix | Delete

( ( ( 0x57 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ? 4 : 0 )\

[461] Fix | Delete

: ( ( 0x72 == ((const U8*)s)[2] ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || 0x70 == ((const U8*)s)[3] ) ) ? 4 : 0 )\

[462] Fix | Delete

: 0 ) \

[463] Fix | Delete

: ( 0xDE == ((const U8*)s)[0] || 0xE1 == ((const U8*)s)[0] || 0xEB == ((const U8*)s)[0] ) ?\

[464] Fix | Delete

( ( ( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) && ( ( 0x41 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x59 ) || 0x5F == ((const U8*)s)[3] || ( 0x62 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[3] && ((const U8*)s)[3] <= 0x72 ) ) ) ? 4 : 0 )\

[465] Fix | Delete

: ( 0xDF == ((const U8*)s)[0] || 0xEA == ((const U8*)s)[0] || 0xEC == ((const U8*)s)[0] ) ?\

[466] Fix | Delete

( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( ((const U8*)s)[1] & 0xFE ) == 0x70 ) ?\

[467] Fix | Delete

[468] Fix | Delete

: ( 0x72 == ((const U8*)s)[1] ) ? \

[469] Fix | Delete

[470] Fix | Delete

[471] Fix | Delete

[472] Fix | Delete

: 0 ) \

[473] Fix | Delete

: ( 0xED == ((const U8*)s)[0] ) ? is_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s) : is_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s) )

[474] Fix | Delete

[475] Fix | Delete

[476] Fix | Delete

/*** GENERATED CODE ***/

[477] Fix | Delete

#define is_STRICT_UTF8_CHAR_utf8_no_length_checks(s) \

[478] Fix | Delete

[479] Fix | Delete

[480] Fix | Delete

[481] Fix | Delete

( ( ( ( 0x41 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x59 ) || 0x5F == ((const U8*)s)[1] || ( 0x62 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0x72 ) ) && ( ( 0x41 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x4A ) || ( 0x51 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x59 ) || 0x5F == ((const U8*)s)[2] || ( 0x62 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x6A ) || ( 0x70 <= ((const U8*)s)[2] && ((const U8*)s)[2] <= 0x72 ) ) ) ? 3 : 0 )\

[482] Fix | Delete

: ( 0xDC == ((const U8*)s)[0] ) ? is_STRICT_UTF8_CHAR_utf8_no_length_checks_part2(s) : is_STRICT_UTF8_CHAR_utf8_no_length_checks_part3(s) )

[483] Fix | Delete

[484] Fix | Delete

/* C9_STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points

[485] Fix | Delete

including non-character code points, no surrogates

[486] Fix | Delete

0x00A0 - 0xD7FF

[487] Fix | Delete

0xE000 - 0x10FFFF

[488] Fix | Delete

[489] Fix | Delete

/*** GENERATED CODE ***/

[490] Fix | Delete

#define is_C9_STRICT_UTF8_CHAR_utf8_no_length_checks_part0(s) \

[491] Fix | Delete

[492] Fix | Delete

[493] Fix | Delete

[494] Fix | Delete

/*** GENERATED CODE ***/

[495] Fix | Delete

#define is_C9_STRICT_UTF8_CHAR_utf8_no_length_checks_part1(s) \

[496] Fix | Delete

( ( ((const U8*)s)[0] == 0xB7 || ( ( ((const U8*)s)[0] & 0xFE ) == 0xB8 ) || ( ( ((const U8*)s)[0] & 0xFC ) == 0xBC ) || ( ( ((const U8*)s)[0] & 0xEE ) == 0xCA ) || ( ( ((const U8*)s)[0] & 0xFC ) == 0xCC ) ) ?\

[497] Fix | Delete

[498] Fix | Delete

: ( 0xDC == ((const U8*)s)[0] ) ? \

[499] Fix | Delete