X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=b35cfebb5e8e35ccc60b810296e5142464500b43;hb=7607c2656ded0887feae5b11099e95289f89b6a8;hp=baee5ae2c456df1a6fa2020226e367d64ef941ed;hpb=0064a8a9866779dceb087452b9bfaa733c51adce;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.h b/utf8.h
index baee5ae..b35cfeb 100644
--- a/utf8.h
+++ b/utf8.h
@@ -7,6 +7,15 @@
  *
  */
 
+/* Use UTF-8 as the default script encoding?
+ * Turning this on will break scripts having non-UTF8 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:
@@ -126,9 +135,13 @@ 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_UTF8 (PL_curcop->op_private & HINT_UTF8) */
 #define IN_BYTES (PL_curcop->op_private & HINT_BYTES)
 #define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)
 
@@ -145,7 +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
@@ -153,12 +166,25 @@ 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)
 #define UNICODE_IS_BYTE_ORDER_MARK(c)	((c) == UNICODE_BYTER_ORDER_MARK)
 #define UNICODE_IS_ILLEGAL(c)		((c) == UNICODE_ILLEGAL)
 
-#define UTF8_QUAD_MAX	UINT64_C(0x1000000000)
+#ifdef HAS_QUAD
+#    define UTF8_QUAD_MAX	UINT64_C(0x1000000000)
+#endif
 
 #define UTF8_IS_ASCII(c) UTF8_IS_INVARIANT(c)