In Perl_pad_check_dup(), use sv rather than name for diagnostics.

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

diff --git a/utf8.h b/utf8.h
index 9f6e4e8..e70559e 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,6 @@
 /*    utf8.h
  *
- *    Copyright (C) 2000, 2001, 2002, 2005 by Larry Wall and others
+ *    Copyright (C) 2000, 2001, 2002, 2005, 2006, 2007, 2009 by Larry Wall and others
  *
  *    You may distribute under the terms of either the GNU General Public
  *    License or the Artistic License, as specified in the README file.
@@ -51,6 +51,7 @@ END_EXTERN_C
 
 /* Native character to iso-8859-1 */
 #define NATIVE_TO_ASCII(ch)      (ch)
+#define NATIVE8_TO_UNI(ch)        (ch)
 #define ASCII_TO_NATIVE(ch)      (ch)
 /* Transform after encoding */
 #define NATIVE_TO_UTF(ch)        (ch)
@@ -111,14 +112,14 @@ 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))
+#define NATIVE_IS_INVARIANT(c)         UNI_IS_INVARIANT(NATIVE8_TO_UNI(c))
 #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 UTF_START_MARK(len) ((len >  7) ? 0xFF : (0xFE << (7-len)))
-#define UTF_START_MASK(len) ((len >= 7) ? 0x00 : (0x1F >> (len-2)))
+#define UTF_START_MARK(len) (((len) >  7) ? 0xFF : (0xFE << (7-(len))))
+#define UTF_START_MASK(len) (((len) >= 7) ? 0x00 : (0x1F >> ((len)-2)))
 
 #define UTF_CONTINUATION_MARK          0x80
 #define UTF_ACCUMULATION_SHIFT         6
@@ -213,7 +214,7 @@ encoded character.
 #define UNICODE_ILLEGAL                        0xFFFF
 
 /* Though our UTF-8 encoding can go beyond this,
- * let's be conservative and do as Unicode 3.2 says. */
+ * let's be conservative and do as Unicode 5.1 says. */
 #define PERL_UNICODE_MAX       0x10FFFF
 
 #define UNICODE_ALLOW_SURROGATE 0x0001 /* Allow UTF-16 surrogates (EVIL) */
@@ -234,35 +235,28 @@ encoded character.
 
 #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) && \
+#ifndef EBCDIC
+#   define LATIN_SMALL_LETTER_SHARP_S  0x00DF
+#   define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0x00FF
+#   define MICRO_SIGN 0x00B5
+#endif
+
+#define ANYOF_FOLD_SHARP_S(node, input, end)   \
+       (ANYOF_BITMAP_TEST(node, 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
 
 #ifdef EBCDIC
@@ -340,3 +334,13 @@ encoded character.
 #define IS_UTF8_CHAR_FAST(n) ((n) <= 4)
 
 #endif /* IS_UTF8_CHAR() for UTF-8 */
+
+/*
+ * Local variables:
+ * c-indentation-style: bsd
+ * c-basic-offset: 4
+ * indent-tabs-mode: t
+ * End:
+ *
+ * ex: set ts=8 sts=4 sw=4 noet:
+ */