X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=c87bbf248c36203dd055c30fc40668186700d805;hb=ac1e784a7c71679a70a1ebe3997559be19c92895;hp=e23cff28c55a009dbcf98e95963043ca1d33b33e;hpb=f067b87872dea57cc42e70fbf2574bf4f17ace75;p=p5sagit%2Fp5-mst-13.2.git diff --git a/utf8.h b/utf8.h index e23cff2..c87bbf2 100644 --- a/utf8.h +++ b/utf8.h @@ -1,12 +1,21 @@ /* utf8.h * - * Copyright (c) 1998-2001, Larry Wall + * 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 +# define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8) +#endif + #ifdef EBCDIC /* The equivalent of these macros but implementing UTF-EBCDIC are in the following header file: @@ -33,7 +42,7 @@ EXTCONST unsigned char PL_utf8skip[]; #endif END_EXTERN_C -#define UTF8SKIP(s) PL_utf8skip[*(U8*)s] +#define UTF8SKIP(s) PL_utf8skip[*(const U8*)(s)] /* Native character to iso-8859-1 */ #define NATIVE_TO_ASCII(ch) (ch) @@ -54,20 +63,47 @@ END_EXTERN_C /* - The following table is from Unicode 3.1. + 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+FFFF E1..EF 80..BF 80..BF   + 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 UNI_IS_INVARIANT(c) (((UV)c) < 0x80) #define UTF8_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_UTF(c)) #define NATIVE_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_ASCII(c)) @@ -111,12 +147,12 @@ END_EXTERN_C * (that is, the two high bits are set). Otherwise we risk loading in the * heavy-duty SWASHINIT and SWASHGET routines unnecessarily. */ -#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \ +#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((const U8*)p) < 0xc0))) \ ? isIDFIRST(*(p)) \ - : isIDFIRST_utf8((U8*)p)) -#define isALNUM_lazy_if(p,c) ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \ + : isIDFIRST_utf8((const U8*)p)) +#define isALNUM_lazy_if(p,c) ((IN_BYTES || (!c || (*((const U8*)p) < 0xc0))) \ ? isALNUM(*(p)) \ - : isALNUM_utf8((U8*)p)) + : isALNUM_utf8((const U8*)p)) #endif /* EBCDIC vs ASCII */ @@ -126,9 +162,27 @@ END_EXTERN_C #define isIDFIRST_lazy(p) isIDFIRST_lazy_if(p,1) #define isALNUM_lazy(p) isALNUM_lazy_if(p,1) -#define UTF8_MAXLEN 13 /* how wide can a single UTF8 encoded character become */ +#define UTF8_MAXBYTES 13 +/* 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 given Unicode's current + * upper limit only four bytes is possible. Perl thinks of UTF-8 + * as a way to encode non-negative integers in a binary format. */ +#define UTF8_MAXLEN UTF8_MAXBYTES + +#define UTF8_MAXLEN_UCLC 3 /* Obsolete, do not use. */ +#define UTF8_MAXLEN_UCLC_MULT 39 /* Obsolete, do not use. */ +#define UTF8_MAXLEN_FOLD 3 /* Obsolete, do not use. */ +#define UTF8_MAXLEN_FOLD_MULT 39 /* Obsolete, do not use. */ + +/* The maximum number of UTF-8 bytes a single Unicode character can + * uppercase/lowercase/fold into; this number depends on the Unicode + * version. An example of maximal expansion is the U+03B0 which + * uppercases to U+03C5 U+0308 U+0301. The Unicode databases that + * tell these things are UnicodeDatabase.txt, CaseFolding.txt, and + * SpecialCasing.txt. */ +#define UTF8_MAXBYTES_CASE 6 -/* #define IN_UTF8 (PL_curcop->op_private & HINT_UTF8) */ #define IN_BYTES (PL_curcop->op_private & HINT_BYTES) #define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES) @@ -138,25 +192,33 @@ END_EXTERN_C #define UTF8_ALLOW_FE_FF 0x0008 #define UTF8_ALLOW_SHORT 0x0010 #define UTF8_ALLOW_SURROGATE 0x0020 -#define UTF8_ALLOW_BOM 0x0040 -#define UTF8_ALLOW_FFFF 0x0080 -#define UTF8_ALLOW_LONG 0x0100 +#define UTF8_ALLOW_FFFF 0x0040 /* Allows also FFFE. */ +#define UTF8_ALLOW_LONG 0x0080 #define UTF8_ALLOW_ANYUV (UTF8_ALLOW_EMPTY|UTF8_ALLOW_FE_FF|\ - UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|\ - UTF8_ALLOW_FFFF|UTF8_ALLOW_LONG) -#define UTF8_ALLOW_ANY 0x00ff -#define UTF8_CHECK_ONLY 0x0100 + UTF8_ALLOW_SURROGATE|UTF8_ALLOW_FFFF) +#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 -#define UNICODE_SURROGATE_FIRST 0xd800 -#define UNICODE_SURROGATE_LAST 0xdfff -#define UNICODE_REPLACEMENT 0xfffd -#define UNICODE_BYTER_ORDER_MARK 0xfffe -#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_SURROGATE 0x0001 /* Allow UTF-16 surrogates (EVIL) */ +#define UNICODE_ALLOW_FDD0 0x0002 /* Allow the U+FDD0...U+FDEF */ +#define UNICODE_ALLOW_FFFF 0x0004 /* Allow 0xFFF[EF], 0x1FFF[EF], ... */ +#define UNICODE_ALLOW_SUPER 0x0008 /* Allow past 10xFFFF */ +#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_BYTER_ORDER_MARK) +#define UNICODE_IS_BYTE_ORDER_MARK(c) ((c) == UNICODE_BYTE_ORDER_MARK) #define UNICODE_IS_ILLEGAL(c) ((c) == UNICODE_ILLEGAL) #ifdef HAS_QUAD @@ -164,3 +226,34 @@ END_EXTERN_C #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 +#define UNI_DISPLAY_QQ (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH) +#define UNI_DISPLAY_REGEX (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH) + +#ifdef EBCDIC +# define ANYOF_FOLD_SHARP_S(node, input, end) \ + (ANYOF_BITMAP_TEST(node, EBCDIC_LATIN_SMALL_LETTER_SHARP_S) && \ + (ANYOF_FLAGS(node) & ANYOF_UNICODE) && \ + (ANYOF_FLAGS(node) & ANYOF_FOLD) && \ + ((end) > (input) + 1) && \ + toLOWER((input)[0]) == 's' && \ + toLOWER((input)[1]) == 's') +#else +# define ANYOF_FOLD_SHARP_S(node, input, end) \ + (ANYOF_BITMAP_TEST(node, UNICODE_LATIN_SMALL_LETTER_SHARP_S) && \ + (ANYOF_FLAGS(node) & ANYOF_UNICODE) && \ + (ANYOF_FLAGS(node) & ANYOF_FOLD) && \ + ((end) > (input) + 1) && \ + toLOWER((input)[0]) == 's' && \ + toLOWER((input)[1]) == 's') +#endif +#define SHARP_S_SKIP 2