X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=3787832f81da07a7c64d25d1b30c5161aabb9b99;hb=384e87d19f97455a7bad80b0a0403c35bbdf9b76;hp=8c27afab5033f09e6a8db1472b7350daab923dd7;hpb=c728cb41064fc29351e896c61d746060cee08d64;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.h b/utf8.h
index 8c27afa..3787832 100644
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,6 @@
 /*    utf8.h
  *
- *    Copyright (c) 1998-2001, Larry Wall
+ *    Copyright (c) 1998-2002, 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.
@@ -63,20 +63,43 @@ END_EXTERN_C
 
 /*
 
- The following table is from Unicode 3.1.
+ The following table is from Unicode 3.2.
 
  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+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+CFFF       E1..EC    80..BF    80..BF
+   U+D000..U+D7FF       ED        80..9F    80..BF
+   U+D800..U+DFFF       ******* ill-formed *******
+   U+E000..U+FFFF       EE..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
 
+Note the A0..BF in U+0800..U+0FFF, the 80..9F in U+D000...U+D7FF,
+the 90..BF in U+10000..U+3FFFF, and the 80...8F in U+100000..U+10FFFF.
+
  */
 
+/*
+ Another way to look at it, as bits:
+
+ Code Points                    1st Byte   2nd Byte  3rd Byte  4th Byte
+
+                    0aaaaaaa     0aaaaaaa
+            00000bbbbbaaaaaa     110bbbbb  10aaaaaa
+            ccccbbbbbbaaaaaa     1110cccc  10bbbbbb  10aaaaaa
+  00000dddccccccbbbbbbaaaaaa     11110ddd  10cccccc  10bbbbbb  10aaaaaa
+
+As you can see, the continuation bytes all begin with C<10>, and the
+leading bits of the start byte tell how many bytes the are in the
+encoded character.
+
+*/
+
+
 #define UNI_IS_INVARIANT(c)		(((UV)c) <  0x80)
 #define UTF8_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
 #define NATIVE_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_ASCII(c))
@@ -138,9 +161,11 @@ END_EXTERN_C
 /* 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)
+#define UTF8_MAXLEN_UCLC_MULT 3
+#define UTF8_MAXLEN_UCLC (UTF8_MAXLEN*UTF8_MAXLEN_UCLC_MULT)
 /* how wide a character can become when casefolded */
-#define UTF8_MAXLEN_FOLD (UTF8_MAXLEN*3)
+#define UTF8_MAXLEN_FOLD_MULT 3
+#define UTF8_MAXLEN_FOLD (UTF8_MAXLEN*UTF8_MAXLEN_FOLD_MULT)
 
 #define IN_BYTES (PL_curcop->op_private & HINT_BYTES)
 #define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)
@@ -163,24 +188,24 @@ END_EXTERN_C
 #define UNICODE_SURROGATE_FIRST		0xd800
 #define UNICODE_SURROGATE_LAST		0xdfff
 #define UNICODE_REPLACEMENT		0xfffd
-#define UNICODE_BYTER_ORDER_MARK	0xfffe
+#define UNICODE_BYTE_ORDER_MARK		0xfeff
 #define UNICODE_ILLEGAL			0xffff
 
 /* Though our UTF-8 encoding can go beyond this,
- * let's be conservative. */
+ * let's be conservative and do as Unicode 3.2 says. */
 #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_BOM	0x0004	/* Allow 0xFEFF */
+#define UNICODE_ALLOW_FFFF	0x0008	/* Allow 0xFFFF, 0x1FFFF, ... */
 #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_REPLACEMENT)
-#define UNICODE_IS_BYTE_ORDER_MARK(c)	((c) == UNICODE_BYTER_ORDER_MARK)
+#define UNICODE_IS_BYTE_ORDER_MARK(c)	((c) == UNICODE_BYTE_ORDER_MARK)
 #define UNICODE_IS_ILLEGAL(c)		((c) == UNICODE_ILLEGAL)
 
 #ifdef HAS_QUAD
@@ -189,12 +214,33 @@ END_EXTERN_C
 
 #define UTF8_IS_ASCII(c) UTF8_IS_INVARIANT(c)
 
+#define UNICODE_LATIN_SMALL_LETTER_SHARP_S	0x00DF
 #define UNICODE_GREEK_CAPITAL_LETTER_SIGMA	0x03A3
 #define UNICODE_GREEK_SMALL_LETTER_FINAL_SIGMA	0x03C2
 #define UNICODE_GREEK_SMALL_LETTER_SIGMA	0x03C3
 
+#define EBCDIC_LATIN_SMALL_LETTER_SHARP_S	0x0059
+
 #define UNI_DISPLAY_ISPRINT	0x0001
 #define UNI_DISPLAY_BACKSLASH	0x0002
 #define UNI_DISPLAY_QQ		(UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)
 #define UNI_DISPLAY_REGEX	(UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)
 
+#ifdef EBCDIC
+#   define ANYOF_FOLD_SHARP_S(node, input, end)	\
+	(ANYOF_BITMAP_TEST(node, EBCDIC_LATIN_SMALL_LETTER_SHARP_S) && \
+	 (ANYOF_FLAGS(node) & ANYOF_UNICODE) && \
+	 (ANYOF_FLAGS(node) & ANYOF_FOLD) && \
+	 ((end) > (input) + 1) && \
+	 toLOWER((input)[0]) == 's' && \
+	 toLOWER((input)[1]) == 's')
+#else
+#   define ANYOF_FOLD_SHARP_S(node, input, end)	\
+	(ANYOF_BITMAP_TEST(node, UNICODE_LATIN_SMALL_LETTER_SHARP_S) && \
+	 (ANYOF_FLAGS(node) & ANYOF_UNICODE) && \
+	 (ANYOF_FLAGS(node) & ANYOF_FOLD) && \
+	 ((end) > (input) + 1) && \
+	 toLOWER((input)[0]) == 's' && \
+	 toLOWER((input)[1]) == 's')
+#endif
+#define SHARP_S_SKIP 2