Make measure_struct a file static.

[perl5.git] / utf8.h

diff --git a/utf8.h b/utf8.h
index 8269e4a..feff1b4 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -1,12 +1,21 @@
 /*    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.
  *
  */
 
+/* Use UTF-8 as the default script encoding?
+ * Turning this on will break scripts having non-UTF8 binary
+ * data (such as Latin-1) in string literals. */
+#ifdef USE_UTF8_SCRIPTS
+#    define USE_UTF8_IN_NAMES (!IN_BYTES)
+#else
+#    define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8)
+#endif
+
 #ifdef EBCDIC
 /* The equivalent of these macros but implementing UTF-EBCDIC
    are in the following header file:
@@ -111,10 +120,10 @@ END_EXTERN_C
  * (that is, the two high bits are set).  Otherwise we risk loading in the
  * heavy-duty SWASHINIT and SWASHGET routines unnecessarily.
  */
-#define isIDFIRST_lazy_if(p,c) ((IN_BYTE || (!c || (*((U8*)p) < 0xc0))) \
+#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \
                                ? isIDFIRST(*(p)) \
                                : isIDFIRST_utf8((U8*)p))
-#define isALNUM_lazy_if(p,c)   ((IN_BYTE || (!c || (*((U8*)p) < 0xc0))) \
+#define isALNUM_lazy_if(p,c)   ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \
                                ? isALNUM(*(p)) \
                                : isALNUM_utf8((U8*)p))
 
@@ -126,11 +135,17 @@ END_EXTERN_C
 #define isIDFIRST_lazy(p)      isIDFIRST_lazy_if(p,1)
 #define isALNUM_lazy(p)                isALNUM_lazy_if(p,1)
 
-#define UTF8_MAXLEN 13 /* how wide can a single UTF8 encoded character become */
+/* 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_MULT 3
+#define UTF8_MAXLEN_UCLC (UTF8_MAXLEN*UTF8_MAXLEN_UCLC_MULT)
+/* how wide a character can become when casefolded */
+#define UTF8_MAXLEN_FOLD_MULT 3
+#define UTF8_MAXLEN_FOLD (UTF8_MAXLEN*UTF8_MAXLEN_FOLD_MULT)
 
-/* #define IN_UTF8 (PL_curcop->op_private & HINT_UTF8) */
-#define IN_BYTE (PL_curcop->op_private & HINT_BYTE)
-#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTE)
+#define IN_BYTES (PL_curcop->op_private & HINT_BYTES)
+#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)
 
 #define UTF8_ALLOW_EMPTY               0x0001
 #define UTF8_ALLOW_CONTINUATION                0x0002
@@ -145,7 +160,7 @@ END_EXTERN_C
                                         UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|\
                                         UTF8_ALLOW_FFFF|UTF8_ALLOW_LONG)
 #define UTF8_ALLOW_ANY                 0x00ff
-#define UTF8_CHECK_ONLY                        0x0100
+#define UTF8_CHECK_ONLY                        0x0200
 
 #define UNICODE_SURROGATE_FIRST                0xd800
 #define UNICODE_SURROGATE_LAST         0xdfff
@@ -153,12 +168,56 @@ END_EXTERN_C
 #define UNICODE_BYTER_ORDER_MARK       0xfffe
 #define UNICODE_ILLEGAL                        0xffff
 
+/* Though our UTF-8 encoding can go beyond this,
+ * let's be conservative. */
+#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_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_REPLACMENT)
+#define UNICODE_IS_REPLACEMENT(c)      ((c) == UNICODE_REPLACEMENT)
 #define UNICODE_IS_BYTE_ORDER_MARK(c)  ((c) == UNICODE_BYTER_ORDER_MARK)
 #define UNICODE_IS_ILLEGAL(c)          ((c) == UNICODE_ILLEGAL)
 
-#define UTF8_QUAD_MAX  UINT64_C(0x1000000000)
+#ifdef HAS_QUAD
+#    define UTF8_QUAD_MAX      UINT64_C(0x1000000000)
+#endif
 
 #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