X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=b35cfebb5e8e35ccc60b810296e5142464500b43;hb=7607c2656ded0887feae5b11099e95289f89b6a8;hp=95fe5706f59bb4f298c3e538a36ba19f56978e70;hpb=2b9d42f0ba1bb562fe21327dc7948ab1a5397a19;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.h b/utf8.h
index 95fe570..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:
@@ -82,7 +91,7 @@ END_EXTERN_C
 #define UTF_CONTINUATION_MARK		0x80
 #define UTF_ACCUMULATION_SHIFT		6
 #define UTF_CONTINUATION_MASK		((U8)0x3f)
-#define UTF8_ACCUMULATE(old, new)	((old) << UTF_ACCUMULATION_SHIFT | (((U8)new) & UTF_CONTINUATION_MASK))
+#define UTF8_ACCUMULATE(old, new)	(((old) << UTF_ACCUMULATION_SHIFT) | (((U8)new) & UTF_CONTINUATION_MASK))
 
 #define UTF8_EIGHT_BIT_HI(c)	((((U8)(c))>>UTF_ACCUMULATION_SHIFT)|UTF_START_MARK(2))
 #define UTF8_EIGHT_BIT_LO(c)	(((((U8)(c)))&UTF_CONTINUATION_MASK)|UTF_CONTINUATION_MARK)
@@ -111,10 +120,10 @@ 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_BYTE || (!c || (*((U8*)p) < 0xc0))) \
+#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \
 				? isIDFIRST(*(p)) \
 				: isIDFIRST_utf8((U8*)p))
-#define isALNUM_lazy_if(p,c)   ((IN_BYTE || (!c || (*((U8*)p) < 0xc0))) \
+#define isALNUM_lazy_if(p,c)   ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \
 				? isALNUM(*(p)) \
 				: isALNUM_utf8((U8*)p))
 
@@ -126,11 +135,15 @@ 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_BYTE (PL_curcop->op_private & HINT_BYTE)
-#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTE)
+#define IN_BYTES (PL_curcop->op_private & HINT_BYTES)
+#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)
 
 #define UTF8_ALLOW_EMPTY		0x0001
 #define UTF8_ALLOW_CONTINUATION		0x0002
@@ -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_REPLACMENT)
+#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)