/* utf8.h
*
- * Copyright (c) 1998-2000, Larry Wall
+ * Copyright (c) 1998-2001, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
#define IN_BYTE (PL_curcop->op_private & HINT_BYTE)
#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTE)
-#define UTF8_ALLOW_CONTINUATION 0x0001
-#define UTF8_ALLOW_NON_CONTINUATION 0x0002
-#define UTF8_ALLOW_FE_FF 0x0004
-#define UTF8_ALLOW_SHORT 0x0008
-#define UTF8_ALLOW_SURROGATE 0x0010
-#define UTF8_ALLOW_BOM 0x0020
-#define UTF8_ALLOW_FFFF 0x0040
-#define UTF8_ALLOW_LONG 0x0080
-#define UTF8_ALLOW_ANYUV (UTF8_ALLOW_FE_FF|UTF8_ALLOW_FFFF \
- |UTF8_ALLOW_BOM|UTF8_ALLOW_SURROGATE)
+#define UTF8_ALLOW_EMPTY 0x0001
+#define UTF8_ALLOW_CONTINUATION 0x0002
+#define UTF8_ALLOW_NON_CONTINUATION 0x0004
+#define UTF8_ALLOW_FE_FF 0x0008
+#define UTF8_ALLOW_SHORT 0x0010
+#define UTF8_ALLOW_SURROGATE 0x0020
+#define UTF8_ALLOW_BOM 0x0040
+#define UTF8_ALLOW_FFFF 0x0080
+#define UTF8_ALLOW_LONG 0x0100
+#define UTF8_ALLOW_ANYUV (UTF8_ALLOW_EMPTY|UTF8_ALLOW_FE_FF|\
+ UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|\
+ UTF8_ALLOW_FFFF|UTF8_ALLOW_LONG)
#define UTF8_ALLOW_ANY 0x00ff
#define UTF8_CHECK_ONLY 0x0100
#define UTF8_QUAD_MAX UINT64_C(0x1000000000)
-#define UTF8_IS_ASCII(c) ((c) < 0x80)
-#define UTF8_IS_START(c) ((c) >= 0xc0 && ((c) <= 0xfd))
-#define UTF8_IS_CONTINUATION(c) ((c) >= 0x80 && ((c) <= 0xbf))
-#define UTF8_IS_CONTINUED(c) ((c) & 0x80)
+/*
+
+ The following table is from Unicode 3.1.
+
+ Code Points 1st Byte 2nd Byte 3rd Byte 4th Byte
-#define UTF8_CONTINUATION_MASK 0x3f
+ 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
-#define UTF8_ACCUMULATE(old, new) ((old) << UTF8_ACCUMULATION_SHIFT | ((new) & UTF8_CONTINUATION_MASK))
+#define UTF8_ACCUMULATE(old, new) ((old) << UTF8_ACCUMULATION_SHIFT | (((U8)new) & UTF8_CONTINUATION_MASK))
+
+#define UTF8_EIGHT_BIT_HI(c) ( (((U8)(c))>>6) |0xc0)
+#define UTF8_EIGHT_BIT_LO(c) (((((U8)(c)) )&0x3f)|0x80)
#ifdef HAS_QUAD
#define UNISKIP(uv) ( (uv) < 0x80 ? 1 : \