#define UTF8_QUAD_MAX UINT64_C(0x1000000000)
+/*
+
+ The following table is from Unicode 3.1.
+
+ 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+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
+
+ */
+
#define UTF8_IS_ASCII(c) (((U8)c) < 0x80)
#define UTF8_IS_START(c) (((U8)c) >= 0xc0 && (((U8)c) <= 0xfd))
#define UTF8_IS_CONTINUATION(c) (((U8)c) >= 0x80 && (((U8)c) <= 0xbf))
#define UTF8_IS_CONTINUED(c) (((U8)c) & 0x80)
+#define UTF8_IS_DOWNGRADEABLE_START(c) (((U8)c & 0xfc) != 0xc0)
#define UTF8_CONTINUATION_MASK ((U8)0x3f)
#define UTF8_ACCUMULATION_SHIFT 6
(uv) < 0x200000 ? 4 : \
(uv) < 0x4000000 ? 5 : \
(uv) < 0x80000000 ? 6 : \
- (uv) < UTF8_QUAD_MAX ? 7 : 13 )
+ (uv) < UTF8_QUAD_MAX ? 7 : 13 )
#else
/* No, I'm not even going to *TRY* putting #ifdef inside a #define */
#define UNISKIP(uv) ( (uv) < 0x80 ? 1 : \
#endif
#define isIDFIRST_lazy(p) isIDFIRST_lazy_if(p,1)
#define isALNUM_lazy(p) isALNUM_lazy_if(p,1)
+
+/* EBCDIC-happy ways of converting native code to UTF8 */
+
+#ifdef EBCDIC
+#define NATIVE_TO_ASCII(ch) PL_e2a[(ch)]
+#define ASCII_TO_NATIVE(ch) PL_a2e[(ch)]
+#define UNI_TO_NATIVE(ch) (((ch) > 0x100) ? (ch) : (UV) PL_a2e[(ch)])
+#define NATIVE_TO_UNI(ch) (((ch) > 0x100) ? (ch) : (UV) PL_e2a[(ch)])
+#else
+#define NATIVE_TO_ASCII(ch) (ch)
+#define ASCII_TO_NATIVE(ch) (ch)
+#define UNI_TO_NATIVE(ch) (ch)
+#define NATIVE_TO_UNI(ch) (ch)
+#endif
+