X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=b35cfebb5e8e35ccc60b810296e5142464500b43;hb=7607c2656ded0887feae5b11099e95289f89b6a8;hp=c475d0f2873285f91b4d3259dfbc5e3540adc670;hpb=39e02b423749ca43aca0385eea6257ecde9aee92;p=p5sagit%2Fp5-mst-13.2.git diff --git a/utf8.h b/utf8.h index c475d0f..b35cfeb 100644 --- a/utf8.h +++ b/utf8.h @@ -135,7 +135,12 @@ 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 */ +/* how wide can a single UTF8 encoded character become */ +#define UTF8_MAXLEN 13 +/* how wide a character can become when upper/lowercased */ +#define UTF8_MAXLEN_UCLC (UTF8_MAXLEN*2) +/* how wide a character can become when casefolded */ +#define UTF8_MAXLEN_FOLD (UTF8_MAXLEN*3) #define IN_BYTES (PL_curcop->op_private & HINT_BYTES) #define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES) @@ -153,7 +158,7 @@ END_EXTERN_C UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|\ UTF8_ALLOW_FFFF|UTF8_ALLOW_LONG) #define UTF8_ALLOW_ANY 0x00ff -#define UTF8_CHECK_ONLY 0x0100 +#define UTF8_CHECK_ONLY 0x0200 #define UNICODE_SURROGATE_FIRST 0xd800 #define UNICODE_SURROGATE_LAST 0xdfff @@ -161,6 +166,17 @@ END_EXTERN_C #define UNICODE_BYTER_ORDER_MARK 0xfffe #define UNICODE_ILLEGAL 0xffff +/* Though our UTF-8 encoding can go beyond this, + * let's be conservative. */ +#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_FFFE 0x0004 /* Allow 0xFFFE, 0x1FFFE, ... */ +#define UNICODE_ALLOW_FFFF 0x0008 /* Allow 0xFFFE, 0x1FFFE, ... */ +#define UNICODE_ALLOW_SUPER 0x0010 /* Allow past 10xFFFF */ +#define UNICODE_ALLOW_ANY 0xFFFF + #define UNICODE_IS_SURROGATE(c) ((c) >= UNICODE_SURROGATE_FIRST && \ (c) <= UNICODE_SURROGATE_LAST) #define UNICODE_IS_REPLACEMENT(c) ((c) == UNICODE_REPLACEMENT)