[perl5.git] / utfebcdic.h

/*    utfebcdic.h
 *
 *    Copyright (C) 2001, 2002, 2003, 2005, 2006, 2007, 2009,
 *    2010, 2011 by Larry Wall, Nick Ing-Simmons, and others
 *
 *    You may distribute under the terms of either the GNU General Public
 *    License or the Artistic License, as specified in the README file.
 *
 * Macros to implement UTF-EBCDIC as perl's internal encoding
 * Adapted from version 7.1 of Unicode Technical Report #16:
 *  http://www.unicode.org/unicode/reports/tr16
 *
 * To summarize, the way it works is:
 * To convert an EBCDIC code point to UTF-EBCDIC:
 *  1)	convert to Unicode.  No conversion is necesary for code points above
 *      255, as Unicode and EBCDIC are identical in this range.  For smaller
 *      code points, the conversion is done by lookup in the PL_e2a table (with
 *      inverse PL_a2e) in the generated file 'ebcdic_tables.h'.  The 'a'
 *      stands for ASCII platform, meaning 0-255 Unicode.
 *  2)	convert that to a utf8-like string called I8 ('I' stands for
 *	intermediate) with variant characters occupying multiple bytes.  This
 *	step is similar to the utf8-creating step from Unicode, but the details
 *	are different.  This transformation is called UTF8-Mod.  There is a
 *	chart about the bit patterns in a comment later in this file.  But
 *	essentially here are the differences:
 *			    UTF8		I8
 *	invariant byte	    starts with 0	starts with 0 or 100
 *	continuation byte   starts with 10	starts with 101
 *	start byte	    same in both: if the code point requires N bytes,
 *			    then the leading N bits are 1, followed by a 0.  (No
 *			    trailing 0 for the very largest possible allocation
 *			    in I8, far beyond the current Unicode standard's
 *			    max, as shown in the comment later in this file.)
 *  3)	Use the algorithm in tr16 to convert each byte from step 2 into
 *	final UTF-EBCDIC.  This is done by table lookup from a table
 *	constructed from the algorithm, reproduced in ebcdic_tables.h as
 *	PL_utf2e, with its inverse being PL_e2utf.  They are constructed so that
 *	all EBCDIC invariants remain invariant, but no others do, and the first
 *	byte of a variant will always have its upper bit set.  But note that
 *	the upper bit of some invariants is also 1.
 *
 *  For example, the ordinal value of 'A' is 193 in EBCDIC, and also is 193 in
 *  UTF-EBCDIC.  Step 1) converts it to 65, Step 2 leaves it at 65, and Step 3
 *  converts it back to 193.  As an example of how a variant character works,
 *  take LATIN SMALL LETTER Y WITH DIAERESIS, which is typically 0xDF in
 *  EBCDIC.  Step 1 converts it to the Unicode value, 0xFF.  Step 2 converts
 *  that to two bytes = 11000111 10111111 = C7 BF, and Step 3 converts those to
 *  0x8B 0x73.
 *
 * If you're starting from Unicode, skip step 1.  For UTF-EBCDIC to straight
 * EBCDIC, reverse the steps.
 *
 * The EBCDIC invariants have been chosen to be those characters whose Unicode
 * equivalents have ordinal numbers less than 160, that is the same characters
 * that are expressible in ASCII, plus the C1 controls.  So there are 160
 * invariants instead of the 128 in UTF-8.
 *
 * The purpose of Step 3 is to make the encoding be invariant for the chosen
 * characters.  This messes up the convenient patterns found in step 2, so
 * generally, one has to undo step 3 into a temporary to use them.  However,
 * one "shadow", or parallel table, PL_utf8skip, has been constructed that
 * doesn't require undoing things.  It is such that for each byte, it says
 * how long the sequence is if that (UTF-EBCDIC) byte were to begin it
 *
 * There are actually 3 slightly different UTF-EBCDIC encodings in
 * ebcdic_tables.h, one for each of the code pages recognized by Perl.  That
 * means that there are actually three different sets of tables, one for each
 * code page.  (If Perl is compiled on platforms using another EBCDIC code
 * page, it may not compile, or Perl may silently mistake it for one of the
 * three.)
 *
 * Note that tr16 actually only specifies one version of UTF-EBCDIC, based on
 * the 1047 encoding, and which is supposed to be used for all code pages.
 * But this doesn't work.  To illustrate the problem, consider the '^' character.
 * On a 037 code page it is the single byte 176, whereas under 1047 UTF-EBCDIC
 * it is the single byte 95.  If Perl implemented tr16 exactly, it would mean
 * that changing a string containing '^' to UTF-EBCDIC would change that '^'
 * from 176 to 95 (and vice-versa), violating the rule that ASCII-range
 * characters are the same in UTF-8 or not.  Much code in Perl assumes this
 * rule.  See for example
 * http://grokbase.com/t/perl/mvs/025xf0yhmn/utf-ebcdic-for-posix-bc-malformed-utf-8-character
 * What Perl does is create a version of UTF-EBCDIC suited to each code page;
 * the one for the 1047 code page is identical to what's specified in tr16.
 * This complicates interchanging files between computers using different code
 * pages.  Best is to convert to I8 before sending them, as the I8
 * representation is the same no matter what the underlying code page is.
 *
 * Because of the way UTF-EBCDIC is constructed, the lowest 32 code points that
 * aren't equivalent to ASCII characters nor C1 controls form the set of
 * continuation bytes; the remaining 64 non-ASCII, non-control code points form
 * the potential start bytes, in order.  (However, the first 5 of these lead to
 * malformed overlongs, so there really are only 59 start bytes, and the first
 * three of the 59 are the start bytes for the Latin1 range.)  Hence the
 * UTF-EBCDIC for the smallest variant code point, 0x160, will have likely 0x41
 * as its continuation byte, provided 0x41 isn't an ASCII or C1 equivalent.
 * And its start byte will be the code point that is 37 (32+5) non-ASCII,
 * non-control code points past it.  (0 - 3F are controls, and 40 is SPACE,
 * leaving 41 as the first potentially available one.)  In contrast, on ASCII
 * platforms, the first 64 (not 32) non-ASCII code points are the continuation
 * bytes.  And the first 2 (not 5) potential start bytes form overlong
 * malformed sequences.
 *
 * EBCDIC characters above 0xFF are the same as Unicode in Perl's
 * implementation of all 3 encodings, so for those Step 1 is trivial.
 *
 * (Note that the entries for invariant characters are necessarily the same in
 * PL_e2a and PL_e2utf; likewise for their inverses.)
 *
 * UTF-EBCDIC strings are the same length or longer than UTF-8 representations
 * of the same string.  The maximum code point representable as 2 bytes in
 * UTF-EBCDIC is 0x3FFF, instead of 0x7FFF in UTF-8.
 */

START_EXTERN_C

#ifdef DOINIT

#include "ebcdic_tables.h"

#else
EXTCONST U8 PL_utf8skip[];
EXTCONST U8 PL_e2utf[];
EXTCONST U8 PL_utf2e[];
EXTCONST U8 PL_e2a[];
EXTCONST U8 PL_a2e[];
EXTCONST U8 PL_fold[];
EXTCONST U8 PL_fold_latin1[];
EXTCONST U8 PL_latin1_lc[];
EXTCONST U8 PL_mod_latin1_uc[];
#endif

END_EXTERN_C

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

/* Use these when ch is known to be < 256 */
#define NATIVE_TO_LATIN1(ch)            (__ASSERT_(FITS_IN_8_BITS(ch)) PL_e2a[(U8)(ch)])
#define LATIN1_TO_NATIVE(ch)            (__ASSERT_(FITS_IN_8_BITS(ch)) PL_a2e[(U8)(ch)])

/* Use these on bytes */
#define NATIVE_UTF8_TO_I8(b)           (__ASSERT_(FITS_IN_8_BITS(b)) PL_e2utf[(U8)(b)])
#define I8_TO_NATIVE_UTF8(b)           (__ASSERT_(FITS_IN_8_BITS(b)) PL_utf2e[(U8)(b)])

/* Transforms in wide UV chars */
#define NATIVE_TO_UNI(ch)    (FITS_IN_8_BITS(ch) ? NATIVE_TO_LATIN1(ch) : (ch))
#define UNI_TO_NATIVE(ch)    (FITS_IN_8_BITS(ch) ? LATIN1_TO_NATIVE(ch) : (ch))

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

        Unicode                         U32 Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th byte
    U+0000..U+007F                     000000000xxxxxxx 0xxxxxxx
    U+0080..U+009F                     00000000100xxxxx 100xxxxx
    U+00A0..U+03FF                     000000yyyyyxxxxx 110yyyyy 101xxxxx
    U+0400..U+3FFF                     00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx
    U+4000..U+3FFFF                 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx
   U+40000..U+3FFFFF            0vvwwwwwzzzzzyyyyyxxxxx 111110vv 101wwwww 101zzzzz 101yyyyy 101xxxxx
  U+400000..U+3FFFFFF       0uvvvvvwwwwwzzzzzyyyyyxxxxx 1111110u 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
 U+4000000..U+7FFFFFFF 0tuuuuuvvvvvwwwwwzzzzzyyyyyxxxxx 1111111t 101uuuuu 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx

  Note: The I8 transformation is valid for UCS-4 values X'0' to
  X'7FFFFFFF' (the full extent of ISO/IEC 10646 coding space).

 */

/* Input is a true Unicode (not-native) code point */
#define OFFUNISKIP(uv) ( (uv) < 0xA0        ? 1 : \
		         (uv) < 0x400       ? 2 : \
		         (uv) < 0x4000      ? 3 : \
		         (uv) < 0x40000     ? 4 : \
		         (uv) < 0x400000    ? 5 : \
		         (uv) < 0x4000000   ? 6 : 7 )

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

/* It turns out that on EBCDIC platforms, the invariants are the characters
 * that have ASCII equivalents, plus the C1 controls.  Since the C0 controls
 * and DELETE are ASCII, this is the same as: (isASCII(uv) || isCNTRL_L1(uv))
 * */
#define UVCHR_IS_INVARIANT(uv) cBOOL(FITS_IN_8_BITS(uv)                        \
   && (PL_charclass[(U8) (uv)] & (_CC_mask(_CC_ASCII) | _CC_mask(_CC_CNTRL))))

#define UVCHR_SKIP(uv) (UVCHR_IS_INVARIANT(uv)  ? 1 :                       \
                        (uv) < 0x400            ? 2 :                       \
		        (uv) < 0x4000           ? 3 :                       \
		        (uv) < 0x40000          ? 4 :                       \
		        (uv) < 0x400000         ? 5 :                       \
		        (uv) < 0x4000000        ? 6 : 7 )

/* UTF-EBCDIC semantic macros - We used to transform back into I8 and then
 * compare, but now only have to do a single lookup by using a bit in
 * l1_char_class_tab.h.
 * Comments as to the meaning of each are given at their corresponding utf8.h
 * definitions. */

#define UTF8_IS_START(c)		_generic_isCC(c, _CC_UTF8_IS_START)
#define UTF8_IS_CONTINUATION(c)		_generic_isCC(c, _CC_UTF8_IS_CONTINUATION)

/* Equivalent to ! UVCHR_IS_INVARIANT(c) */
#define UTF8_IS_CONTINUED(c) 		cBOOL(FITS_IN_8_BITS(c)                 \
   && ! (PL_charclass[(U8) (c)] & (_CC_mask(_CC_ASCII) | _CC_mask(_CC_CNTRL))))

#define UTF8_IS_DOWNGRADEABLE_START(c)   _generic_isCC(c,                       \
                                              _CC_UTF8_IS_DOWNGRADEABLE_START)

/* Equivalent to (UTF8_IS_START(c) && ! UTF8_IS_DOWNGRADEABLE_START(c))
 * Makes sure that the START bit is set and the DOWNGRADEABLE bit isn't */
#define UTF8_IS_ABOVE_LATIN1(c) cBOOL(FITS_IN_8_BITS(c)                         \
  && ((PL_charclass[(U8) (c)] & ( _CC_mask(_CC_UTF8_IS_START)                   \
                                 |_CC_mask(_CC_UTF8_IS_DOWNGRADEABLE_START)))   \
                        == _CC_mask(_CC_UTF8_IS_START)))

#define isUTF8_POSSIBLY_PROBLEMATIC(c)                                          \
                _generic_isCC(c, _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE)

/* Can't exceed 7 on EBCDIC platforms */
#define UTF_START_MARK(len) (0xFF & (0xFE << (7-(len))))

#define UTF_START_MASK(len) (((len) >= 6) ? 0x01 : (0x1F >> ((len)-2)))
#define UTF_CONTINUATION_MARK		0xA0
#define UTF_CONTINUATION_MASK		((U8)0x1f)
#define UTF_ACCUMULATION_SHIFT		5

/* How wide can a single UTF-8 encoded character become in bytes. */
/* NOTE: Strictly speaking Perl's UTF-8 should not be called UTF-8 since UTF-8
 * is an encoding of Unicode, and Unicode's upper limit, 0x10FFFF, can be
 * expressed with 5 bytes.  However, Perl thinks of UTF-8 as a way to encode
 * non-negative integers in a binary format, even those above Unicode */
#define UTF8_MAXBYTES 7

/* The maximum number of UTF-8 bytes a single Unicode character can
 * uppercase/lowercase/fold into.  Unicode guarantees that the maximum
 * expansion is 3 characters.  On EBCDIC platforms, the highest Unicode
 * character occupies 5 bytes, therefore this number is 15 */
#define UTF8_MAXBYTES_CASE	15

/* ^? is defined to be APC on EBCDIC systems.  See the definition of toCTRL()
 * for more */
#define QUESTION_MARK_CTRL   LATIN1_TO_NATIVE(0x9F)

#define MAX_UTF8_TWO_BYTE 0x3FF

/*
 * ex: set ts=8 sts=4 sw=4 et:
 */
Commit	Line	Data
1d72bdf6 NIS	1	/* utfebcdic.h
1d72bdf6 NIS	2	*
2eee27d7 SS	3	* Copyright (C) 2001, 2002, 2003, 2005, 2006, 2007, 2009,
2eee27d7 SS	4	* 2010, 2011 by Larry Wall, Nick Ing-Simmons, and others
1d72bdf6 NIS	5	*
	6	* You may distribute under the terms of either the GNU General Public
	7	* License or the Artistic License, as specified in the README file.
	8	*
	9	* Macros to implement UTF-EBCDIC as perl's internal encoding
97237291	10	* Adapted from version 7.1 of Unicode Technical Report #16:
1d72bdf6	11	* http://www.unicode.org/unicode/reports/tr16
fe749c9a KW	12	*
fe749c9a KW	13	* To summarize, the way it works is:
c229c178 KW	14	* To convert an EBCDIC code point to UTF-EBCDIC:
	15	* 1) convert to Unicode. No conversion is necesary for code points above
	16	* 255, as Unicode and EBCDIC are identical in this range. For smaller
	17	* code points, the conversion is done by lookup in the PL_e2a table (with
	18	* inverse PL_a2e) in the generated file 'ebcdic_tables.h'. The 'a'
	19	* stands for ASCII platform, meaning 0-255 Unicode.
97237291	20	* 2) convert that to a utf8-like string called I8 ('I' stands for
d06134e5 KW	21	* intermediate) with variant characters occupying multiple bytes. This
	22	* step is similar to the utf8-creating step from Unicode, but the details
	23	* are different. This transformation is called UTF8-Mod. There is a
	24	* chart about the bit patterns in a comment later in this file. But
fe749c9a KW	25	* essentially here are the differences:
	26	* UTF8 I8
	27	* invariant byte starts with 0 starts with 0 or 100
	28	* continuation byte starts with 10 starts with 101
	29	* start byte same in both: if the code point requires N bytes,
	30	* then the leading N bits are 1, followed by a 0. (No
	31	* trailing 0 for the very largest possible allocation
	32	* in I8, far beyond the current Unicode standard's
	33	* max, as shown in the comment later in this file.)
97237291 KW	34	* 3) Use the algorithm in tr16 to convert each byte from step 2 into
97237291 KW	35	* final UTF-EBCDIC. This is done by table lookup from a table
4bc3dcfa	36	* constructed from the algorithm, reproduced in ebcdic_tables.h as
97237291 KW	37	* PL_utf2e, with its inverse being PL_e2utf. They are constructed so that
	38	* all EBCDIC invariants remain invariant, but no others do, and the first
	39	* byte of a variant will always have its upper bit set. But note that
	40	* the upper bit of some invariants is also 1.
	41	*
	42	* For example, the ordinal value of 'A' is 193 in EBCDIC, and also is 193 in
	43	* UTF-EBCDIC. Step 1) converts it to 65, Step 2 leaves it at 65, and Step 3
	44	* converts it back to 193. As an example of how a variant character works,
	45	* take LATIN SMALL LETTER Y WITH DIAERESIS, which is typically 0xDF in
	46	* EBCDIC. Step 1 converts it to the Unicode value, 0xFF. Step 2 converts
	47	* that to two bytes = 11000111 10111111 = C7 BF, and Step 3 converts those to
	48	* 0x8B 0x73.
45f80db9	49	*
fe749c9a KW	50	* If you're starting from Unicode, skip step 1. For UTF-EBCDIC to straight
	51	* EBCDIC, reverse the steps.
	52	*
	53	* The EBCDIC invariants have been chosen to be those characters whose Unicode
	54	* equivalents have ordinal numbers less than 160, that is the same characters
	55	* that are expressible in ASCII, plus the C1 controls. So there are 160
bc2161fd	56	* invariants instead of the 128 in UTF-8.
fe749c9a KW	57	*
	58	* The purpose of Step 3 is to make the encoding be invariant for the chosen
	59	* characters. This messes up the convenient patterns found in step 2, so
	60	* generally, one has to undo step 3 into a temporary to use them. However,
97237291 KW	61	* one "shadow", or parallel table, PL_utf8skip, has been constructed that
	62	* doesn't require undoing things. It is such that for each byte, it says
	63	* how long the sequence is if that (UTF-EBCDIC) byte were to begin it
	64	*
	65	* There are actually 3 slightly different UTF-EBCDIC encodings in
4bc3dcfa	66	* ebcdic_tables.h, one for each of the code pages recognized by Perl. That
97237291 KW	67	* means that there are actually three different sets of tables, one for each
	68	* code page. (If Perl is compiled on platforms using another EBCDIC code
	69	* page, it may not compile, or Perl may silently mistake it for one of the
	70	* three.)
fe749c9a	71	*
97237291 KW	72	* Note that tr16 actually only specifies one version of UTF-EBCDIC, based on
	73	* the 1047 encoding, and which is supposed to be used for all code pages.
	74	* But this doesn't work. To illustrate the problem, consider the '^' character.
	75	* On a 037 code page it is the single byte 176, whereas under 1047 UTF-EBCDIC
	76	* it is the single byte 95. If Perl implemented tr16 exactly, it would mean
	77	* that changing a string containing '^' to UTF-EBCDIC would change that '^'
	78	* from 176 to 95 (and vice-versa), violating the rule that ASCII-range
	79	* characters are the same in UTF-8 or not. Much code in Perl assumes this
	80	* rule. See for example
	81	* http://grokbase.com/t/perl/mvs/025xf0yhmn/utf-ebcdic-for-posix-bc-malformed-utf-8-character
	82	* What Perl does is create a version of UTF-EBCDIC suited to each code page;
	83	* the one for the 1047 code page is identical to what's specified in tr16.
	84	* This complicates interchanging files between computers using different code
	85	* pages. Best is to convert to I8 before sending them, as the I8
	86	* representation is the same no matter what the underlying code page is.
fe749c9a	87	*
ff982d00 KW	88	* Because of the way UTF-EBCDIC is constructed, the lowest 32 code points that
	89	* aren't equivalent to ASCII characters nor C1 controls form the set of
	90	* continuation bytes; the remaining 64 non-ASCII, non-control code points form
	91	* the potential start bytes, in order. (However, the first 5 of these lead to
80bfb4dc KW	92	* malformed overlongs, so there really are only 59 start bytes, and the first
80bfb4dc KW	93	* three of the 59 are the start bytes for the Latin1 range.) Hence the
ff982d00 KW	94	* UTF-EBCDIC for the smallest variant code point, 0x160, will have likely 0x41
	95	* as its continuation byte, provided 0x41 isn't an ASCII or C1 equivalent.
	96	* And its start byte will be the code point that is 37 (32+5) non-ASCII,
	97	* non-control code points past it. (0 - 3F are controls, and 40 is SPACE,
	98	* leaving 41 as the first potentially available one.) In contrast, on ASCII
	99	* platforms, the first 64 (not 32) non-ASCII code points are the continuation
	100	* bytes. And the first 2 (not 5) potential start bytes form overlong
	101	* malformed sequences.
	102	*
fe749c9a KW	103	* EBCDIC characters above 0xFF are the same as Unicode in Perl's
	104	* implementation of all 3 encodings, so for those Step 1 is trivial.
	105	*
	106	* (Note that the entries for invariant characters are necessarily the same in
97237291	107	* PL_e2a and PL_e2utf; likewise for their inverses.)
fe749c9a KW	108	*
	109	* UTF-EBCDIC strings are the same length or longer than UTF-8 representations
	110	* of the same string. The maximum code point representable as 2 bytes in
	111	* UTF-EBCDIC is 0x3FFF, instead of 0x7FFF in UTF-8.
1d72bdf6 NIS	112	*/
	113
	114	START_EXTERN_C
	115
	116	#ifdef DOINIT
f5e1abaf	117
4bc3dcfa	118	#include "ebcdic_tables.h"
44f2fc15	119
1d72bdf6	120	#else
f466f02a KW	121	EXTCONST U8 PL_utf8skip[];
	122	EXTCONST U8 PL_e2utf[];
	123	EXTCONST U8 PL_utf2e[];
	124	EXTCONST U8 PL_e2a[];
	125	EXTCONST U8 PL_a2e[];
	126	EXTCONST U8 PL_fold[];
	127	EXTCONST U8 PL_fold_latin1[];
	128	EXTCONST U8 PL_latin1_lc[];
	129	EXTCONST U8 PL_mod_latin1_uc[];
1d72bdf6 NIS	130	#endif
	131
	132	END_EXTERN_C
	133
1e54db1a	134	/* EBCDIC-happy ways of converting native code to UTF-8 */
1d72bdf6	135
e9b19ab7 KW	136	/* Use these when ch is known to be < 256 */
	137	#define NATIVE_TO_LATIN1(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) PL_e2a[(U8)(ch)])
	138	#define LATIN1_TO_NATIVE(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) PL_a2e[(U8)(ch)])
59a449d5	139
e9b19ab7 KW	140	/* Use these on bytes */
	141	#define NATIVE_UTF8_TO_I8(b) (__ASSERT_(FITS_IN_8_BITS(b)) PL_e2utf[(U8)(b)])
	142	#define I8_TO_NATIVE_UTF8(b) (__ASSERT_(FITS_IN_8_BITS(b)) PL_utf2e[(U8)(b)])
59a449d5	143
bc3632a8	144	/* Transforms in wide UV chars */
8dcc0f39 KW	145	#define NATIVE_TO_UNI(ch) (FITS_IN_8_BITS(ch) ? NATIVE_TO_LATIN1(ch) : (ch))
8dcc0f39 KW	146	#define UNI_TO_NATIVE(ch) (FITS_IN_8_BITS(ch) ? LATIN1_TO_NATIVE(ch) : (ch))
bc3632a8	147
1d72bdf6	148	/*
d06134e5	149	The following table is adapted from tr16, it shows I8 encoding of Unicode code points.
1d72bdf6	150
80bfb4dc	151	Unicode U32 Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th byte
1d72bdf6 NIS	152	U+0000..U+007F 000000000xxxxxxx 0xxxxxxx
1d72bdf6 NIS	153	U+0080..U+009F 00000000100xxxxx 100xxxxx
1d72bdf6 NIS	154	U+00A0..U+03FF 000000yyyyyxxxxx 110yyyyy 101xxxxx
	155	U+0400..U+3FFF 00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx
	156	U+4000..U+3FFFF 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx
	157	U+40000..U+3FFFFF 0vvwwwwwzzzzzyyyyyxxxxx 111110vv 101wwwww 101zzzzz 101yyyyy 101xxxxx
	158	U+400000..U+3FFFFFF 0uvvvvvwwwwwzzzzzyyyyyxxxxx 1111110u 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
	159	U+4000000..U+7FFFFFFF 0tuuuuuvvvvvwwwwwzzzzzyyyyyxxxxx 1111111t 101uuuuu 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
	160
d06134e5	161	Note: The I8 transformation is valid for UCS-4 values X'0' to
1d72bdf6 NIS	162	X'7FFFFFFF' (the full extent of ISO/IEC 10646 coding space).
	163
	164	*/
	165
5aaebcb3 KW	166	/* Input is a true Unicode (not-native) code point */
5aaebcb3 KW	167	#define OFFUNISKIP(uv) ( (uv) < 0xA0 ? 1 : \
1ff3baa2 KW	168	(uv) < 0x400 ? 2 : \
	169	(uv) < 0x4000 ? 3 : \
	170	(uv) < 0x40000 ? 4 : \
	171	(uv) < 0x400000 ? 5 : \
	172	(uv) < 0x4000000 ? 6 : 7 )
	173
2d1545e5	174	#define OFFUNI_IS_INVARIANT(c) (((UV)(c)) < 0xA0)
530495eb	175
38953e5a KW	176	/* It turns out that on EBCDIC platforms, the invariants are the characters
	177	* that have ASCII equivalents, plus the C1 controls. Since the C0 controls
	178	* and DELETE are ASCII, this is the same as: (isASCII(uv) \|\| isCNTRL_L1(uv))
	179	* */
	180	#define UVCHR_IS_INVARIANT(uv) cBOOL(FITS_IN_8_BITS(uv) \
	181	&& (PL_charclass[(U8) (uv)] & (_CC_mask(_CC_ASCII) \| _CC_mask(_CC_CNTRL))))
	182
5352a763 KW	183	#define UVCHR_SKIP(uv) (UVCHR_IS_INVARIANT(uv) ? 1 : \
	184	(uv) < 0x400 ? 2 : \
	185	(uv) < 0x4000 ? 3 : \
	186	(uv) < 0x40000 ? 4 : \
	187	(uv) < 0x400000 ? 5 : \
	188	(uv) < 0x4000000 ? 6 : 7 )
38953e5a	189
e4fd7312 KW	190	/* UTF-EBCDIC semantic macros - We used to transform back into I8 and then
	191	* compare, but now only have to do a single lookup by using a bit in
	192	* l1_char_class_tab.h.
15824458	193	* Comments as to the meaning of each are given at their corresponding utf8.h
1ff3baa2	194	* definitions. */
0447e8df	195
e4fd7312 KW	196	#define UTF8_IS_START(c) _generic_isCC(c, _CC_UTF8_IS_START)
	197	#define UTF8_IS_CONTINUATION(c) _generic_isCC(c, _CC_UTF8_IS_CONTINUATION)
	198
	199	/* Equivalent to ! UVCHR_IS_INVARIANT(c) */
	200	#define UTF8_IS_CONTINUED(c) cBOOL(FITS_IN_8_BITS(c) \
	201	&& ! (PL_charclass[(U8) (c)] & (_CC_mask(_CC_ASCII) \| _CC_mask(_CC_CNTRL))))
	202
	203	#define UTF8_IS_DOWNGRADEABLE_START(c) _generic_isCC(c, \
	204	_CC_UTF8_IS_DOWNGRADEABLE_START)
	205
	206	/* Equivalent to (UTF8_IS_START(c) && ! UTF8_IS_DOWNGRADEABLE_START(c))
	207	* Makes sure that the START bit is set and the DOWNGRADEABLE bit isn't */
	208	#define UTF8_IS_ABOVE_LATIN1(c) cBOOL(FITS_IN_8_BITS(c) \
	209	&& ((PL_charclass[(U8) (c)] & ( _CC_mask(_CC_UTF8_IS_START) \
	210	\|_CC_mask(_CC_UTF8_IS_DOWNGRADEABLE_START))) \
	211	== _CC_mask(_CC_UTF8_IS_START)))
1d72bdf6	212
5d5376e2 KW	213	#define isUTF8_POSSIBLY_PROBLEMATIC(c) \
	214	_generic_isCC(c, _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE)
	215
ee372ee9 KW	216	/* Can't exceed 7 on EBCDIC platforms */
	217	#define UTF_START_MARK(len) (0xFF & (0xFE << (7-(len))))
	218
22901f30	219	#define UTF_START_MASK(len) (((len) >= 6) ? 0x01 : (0x1F >> ((len)-2)))
1d72bdf6 NIS	220	#define UTF_CONTINUATION_MARK 0xA0
	221	#define UTF_CONTINUATION_MASK ((U8)0x1f)
	222	#define UTF_ACCUMULATION_SHIFT 5
	223
03c76984 KW	224	/* How wide can a single UTF-8 encoded character become in bytes. */
	225	/* NOTE: Strictly speaking Perl's UTF-8 should not be called UTF-8 since UTF-8
	226	* is an encoding of Unicode, and Unicode's upper limit, 0x10FFFF, can be
	227	* expressed with 5 bytes. However, Perl thinks of UTF-8 as a way to encode
	228	* non-negative integers in a binary format, even those above Unicode */
	229	#define UTF8_MAXBYTES 7
	230
	231	/* The maximum number of UTF-8 bytes a single Unicode character can
	232	* uppercase/lowercase/fold into. Unicode guarantees that the maximum
	233	* expansion is 3 characters. On EBCDIC platforms, the highest Unicode
	234	* character occupies 5 bytes, therefore this number is 15 */
	235	#define UTF8_MAXBYTES_CASE 15
	236
0ed2b00b KW	237	/* ^? is defined to be APC on EBCDIC systems. See the definition of toCTRL()
	238	* for more */
	239	#define QUESTION_MARK_CTRL LATIN1_TO_NATIVE(0x9F)
	240
843a4590 KW	241	#define MAX_UTF8_TWO_BYTE 0x3FF
843a4590 KW	242
e9a8c099	243	/*
14d04a33	244	* ex: set ts=8 sts=4 sw=4 et:
e9a8c099	245	*/