X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utfebcdic.h;h=2c56006ff67a6a972df61d212ca91c4c1bf3f9bb;hb=c4fbe2471f42249bd57e1c071c99349d2331aea5;hp=0eef54b00187346e730a8cee11300af58475723e;hpb=753838417b30f18133bff09e0b7fa58f5a0db60a;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utfebcdic.h b/utfebcdic.h
index 0eef54b..2c56006 100644
--- a/utfebcdic.h
+++ b/utfebcdic.h
@@ -15,17 +15,18 @@ START_EXTERN_C
 #ifdef DOINIT
 /* Indexed by encoded byte this table gives the length of the sequence.
    Adapted from the shadow flags table in tr16.
-   The entries marked 9 are continuation bytes.
+   The entries marked 9 in tr6 are continuation bytes and are marked
+   as length 1 here so that we can recover.
 */
 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,
 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,
-1,9,9,9,9,9,9,9,9,9,9,1,1,1,1,1,
-1,9,9,9,9,9,9,9,9,9,1,1,1,1,1,1,
-1,1,9,9,9,9,9,9,9,9,9,1,1,1,1,1,
-9,9,9,9,2,2,2,2,2,1,1,1,1,1,1,1,
+1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+1,1,1,1,2,2,2,2,2,1,1,1,1,1,1,1,
 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
 2,1,1,1,1,1,1,1,1,1,2,2,2,1,2,2,
@@ -221,7 +222,7 @@ END_EXTERN_C
 #define UTF_TO_NATIVE(ch)        PL_utf2e[(U8)(ch)]
 /* Transform in wide UV char space */
 #define NATIVE_TO_UNI(ch)        (((ch) > 255) ? (ch) : NATIVE_TO_ASCII(ch))
-#define UNI_TO_NATIVE(ch)        (((ch) > 255) ? (ch) : (UV) ASCII_TO_NATIVE(ch))
+#define UNI_TO_NATIVE(ch)        (((ch) > 255) ? (ch) : ASCII_TO_NATIVE(ch))
 /* Transform in invariant..byte space */
 #define NATIVE_TO_NEED(enc,ch)   ((enc) ? UTF_TO_NATIVE(NATIVE_TO_ASCII(ch)) : (ch))
 #define ASCII_TO_NEED(enc,ch)    ((enc) ? UTF_TO_NATIVE(ch) : ASCII_TO_NATIVE(ch))
@@ -233,10 +234,10 @@ END_EXTERN_C
  * unnecessarily.
  */
 
-#define isIDFIRST_lazy_if(p,c) ((IN_BYTE || (!c || UTF8_IS_INVARIANT(*p))) \
+#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
 				? isIDFIRST(*(p)) \
 				: isIDFIRST_utf8((U8*)p))
-#define isALNUM_lazy_if(p,c)   ((IN_BYTE || (!c || UTF8_IS_INVARIANT(*p))) \
+#define isALNUM_lazy_if(p,c)   ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
 				? isALNUM(*(p)) \
 				: isALNUM_utf8((U8*)p))
 
@@ -267,10 +268,13 @@ END_EXTERN_C
 		      (uv) < 0x400000       ? 5 : \
 		      (uv) < 0x4000000      ? 6 : 7 )
 
+
+#define UNI_IS_INVARIANT(c)		((c) <  0xA0)
 /* UTF-EBCDIC sematic macros - transform back into UTF-8-Mod and then compare */
-#define UTF8_IS_INVARIANT(c) 		(NATIVE_TO_UTF(c) <  0xA0)
+#define NATIVE_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_ASCII(c))
+#define UTF8_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
 #define UTF8_IS_START(c)		(NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xE0) != 0xA0)
-#define UTF8_IS_CONTINUATION(c)		(NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xE0) == 0xA0)
+#define UTF8_IS_CONTINUATION(c)		((NATIVE_TO_UTF(c) & 0xE0) == 0xA0)
 #define UTF8_IS_CONTINUED(c) 		(NATIVE_TO_UTF(c) >= 0xA0)
 #define UTF8_IS_DOWNGRADEABLE_START(c)	(NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xF8) == 0xC0)