utf8.h revision 7c478bd95313f5f23a4c958a745db2134aa03244
/* utf8.h
*
* Copyright (C) 2000, 2001, 2002, by Larry Wall 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.
*
*/
/* Use UTF-8 as the default script encoding?
* Turning this on will break scripts having non-UTF-8 binary
* data (such as Latin-1) in string literals. */
#ifdef USE_UTF8_SCRIPTS
# define USE_UTF8_IN_NAMES (!IN_BYTES)
#else
#endif
#ifdef EBCDIC
/* The equivalent of these macros but implementing UTF-EBCDIC
are in the following header file:
*/
#include "utfebcdic.h"
#else
#ifdef DOINIT
EXTCONST unsigned char PL_utf8skip[] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* scripts */
3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6, /* cjk etc. */
7,13, /* Perl extended (not UTF-8). Up to 72bit allowed (64-bit + reserved). */
};
#else
EXTCONST unsigned char PL_utf8skip[];
#endif
/* Native character to iso-8859-1 */
/* Transform after encoding */
/* Transforms in wide UV chars */
/* Transforms in invariant space */
/* As there are no translations avoid the function wrapper */
#define Perl_uvchr_to_utf8 Perl_uvuni_to_utf8
/*
The following table is from Unicode 3.2.
Code Points 1st Byte 2nd Byte 3rd Byte 4th Byte
U+0000..U+007F 00..7F
U+0080..U+07FF C2..DF 80..BF
U+0800..U+0FFF E0 A0..BF 80..BF
U+1000..U+CFFF E1..EC 80..BF 80..BF
U+D000..U+D7FF ED 80..9F 80..BF
U+D800..U+DFFF ******* ill-formed *******
U+E000..U+FFFF EE..EF 80..BF 80..BF
U+10000..U+3FFFF F0 90..BF 80..BF 80..BF
U+40000..U+FFFFF F1..F3 80..BF 80..BF 80..BF
U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
Note the A0..BF in U+0800..U+0FFF, the 80..9F in U+D000...U+D7FF,
the 90..BF in U+10000..U+3FFFF, and the 80...8F in U+100000..U+10FFFF.
The "gaps" are caused by legal UTF-8 avoiding non-shortest encodings:
it is technically possible to UTF-8-encode a single code point in different
ways, but that is explicitly forbidden, and the shortest possible encoding
should always be used (and that is what Perl does).
*/
/*
Another way to look at it, as bits:
Code Points 1st Byte 2nd Byte 3rd Byte 4th Byte
0aaaaaaa 0aaaaaaa
00000bbbbbaaaaaa 110bbbbb 10aaaaaa
ccccbbbbbbaaaaaa 1110cccc 10bbbbbb 10aaaaaa
00000dddccccccbbbbbbaaaaaa 11110ddd 10cccccc 10bbbbbb 10aaaaaa
As you can see, the continuation bytes all begin with C<10>, and the
leading bits of the start byte tell how many bytes the are in the
encoded character.
*/
#define UTF_CONTINUATION_MARK 0x80
#define UTF_ACCUMULATION_SHIFT 6
#define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT) | (((U8)new) & UTF_CONTINUATION_MASK))
#ifdef HAS_QUAD
#else
/* No, I'm not even going to *TRY* putting #ifdef inside a #define */
#endif
/*
* Note: we try to be careful never to call the isXXX_utf8() functions
* unless we're pretty sure we've seen the beginning of a UTF-8 character
* (that is, the two high bits are set). Otherwise we risk loading in the
* heavy-duty SWASHINIT and SWASHGET routines unnecessarily.
*/
? isIDFIRST(*(p)) \
: isIDFIRST_utf8((U8*)p))
? isALNUM(*(p)) \
: isALNUM_utf8((U8*)p))
#endif /* EBCDIC vs ASCII */
/* Rest of these are attributes of Unicode and perl's internals rather than the encoding */
/* how wide can a single UTF-8 encoded character become */
#define UTF8_MAXLEN 13
/* how wide a character can become when upper/lowercased */
#define UTF8_MAXLEN_UCLC_MULT 3
/* how wide a character can become when casefolded */
#define UTF8_MAXLEN_FOLD_MULT 3
#define UTF8_ALLOW_EMPTY 0x0001
#define UTF8_ALLOW_CONTINUATION 0x0002
#define UTF8_ALLOW_NON_CONTINUATION 0x0004
#define UTF8_ALLOW_FE_FF 0x0008
#define UTF8_ALLOW_SHORT 0x0010
#define UTF8_ALLOW_SURROGATE 0x0020
#define UTF8_ALLOW_LONG 0x0080
#define UTF8_ALLOW_ANY 0x00FF
#define UTF8_CHECK_ONLY 0x0200
#define UNICODE_SURROGATE_FIRST 0xD800
#define UNICODE_SURROGATE_LAST 0xDFFF
#define UNICODE_REPLACEMENT 0xFFFD
#define UNICODE_BYTE_ORDER_MARK 0xFEFF
#define UNICODE_ILLEGAL 0xFFFF
/* Though our UTF-8 encoding can go beyond this,
* let's be conservative and do as Unicode 3.2 says. */
#define PERL_UNICODE_MAX 0x10FFFF
#define UNICODE_ALLOW_ANY 0x000F
#define UNICODE_IS_SURROGATE(c) ((c) >= UNICODE_SURROGATE_FIRST && \
(c) <= UNICODE_SURROGATE_LAST)
#define UNICODE_IS_REPLACEMENT(c) ((c) == UNICODE_REPLACEMENT)
#define UNICODE_IS_BYTE_ORDER_MARK(c) ((c) == UNICODE_BYTE_ORDER_MARK)
#define UNICODE_IS_ILLEGAL(c) ((c) == UNICODE_ILLEGAL)
#ifdef HAS_QUAD
#endif
#define UTF8_IS_ASCII(c) UTF8_IS_INVARIANT(c)
#define UNICODE_LATIN_SMALL_LETTER_SHARP_S 0x00DF
#define UNICODE_GREEK_CAPITAL_LETTER_SIGMA 0x03A3
#define UNICODE_GREEK_SMALL_LETTER_FINAL_SIGMA 0x03C2
#define UNICODE_GREEK_SMALL_LETTER_SIGMA 0x03C3
#define EBCDIC_LATIN_SMALL_LETTER_SHARP_S 0x0059
#define UNI_DISPLAY_ISPRINT 0x0001
#define UNI_DISPLAY_BACKSLASH 0x0002
#ifdef EBCDIC
#else
#endif
#define SHARP_S_SKIP 2