With Damian's approval synchronize damian's modules'

[p5sagit/p5-mst-13.2.git] / utf8.h

diff --git a/utf8.h b/utf8.h
index e9598b8..160e5d2 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,6 @@
 /*    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.
@@ -31,18 +31,24 @@ END_EXTERN_C
 
 /* #define IN_UTF8 (PL_curcop->op_private & HINT_UTF8) */
 #define IN_BYTE (PL_curcop->op_private & HINT_BYTE)
+#ifdef USE_BYTES_DOWNGRADES
+#define DO_UTF8(sv) (SvUTF8(sv) && !(IN_BYTE && sv_utf8_downgrade(sv,0)))
+#else
 #define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTE)
+#endif
 
-#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
 
@@ -62,17 +68,34 @@ END_EXTERN_C
 
 #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
-#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)>>6)&0x3f)|0x80)
+#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 : \
@@ -81,7 +104,7 @@ END_EXTERN_C
                      (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 : \
@@ -112,3 +135,18 @@ END_EXTERN_C
 #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
+