+
+#define UTF8_MAXBYTES 13
+/* How wide can a single UTF-8 encoded character become in bytes.
+ * NOTE: Strictly speaking Perl's UTF-8 should not be called UTF-8
+ * since UTF-8 is an encoding of Unicode and given Unicode's current
+ * upper limit only four bytes is possible. Perl thinks of UTF-8
+ * as a way to encode non-negative integers in a binary format. */
+#define UTF8_MAXLEN UTF8_MAXBYTES
+
+/* The maximum number of UTF-8 bytes a single Unicode character can
+ * uppercase/lowercase/fold into; this number depends on the Unicode
+ * version. An example of maximal expansion is the U+03B0 which
+ * uppercases to U+03C5 U+0308 U+0301. The Unicode databases that
+ * tell these things are UnicodeData.txt, CaseFolding.txt, and
+ * SpecialCasing.txt. */
+#define UTF8_MAXBYTES_CASE 6
+
+#define IN_BYTES (CopHINTS_get(PL_curcop) & HINT_BYTES)
+#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)
+#define IN_UNI_8_BIT ( (CopHINTS_get(PL_curcop) & HINT_UNI_8_BIT) \
+ && ! IN_LOCALE_RUNTIME && ! IN_BYTES)
+
+#define UTF8_ALLOW_EMPTY 0x0001
+#define UTF8_ALLOW_CONTINUATION 0x0002
+#define UTF8_ALLOW_NON_CONTINUATION 0x0004
+#define UTF8_ALLOW_FE_FF 0x0008 /* Allow FE or FF start bytes, \
+ yields above 0x7fffFFFF */
+#define UTF8_ALLOW_SHORT 0x0010 /* expecting more bytes */
+#define UTF8_ALLOW_SURROGATE 0x0020
+#define UTF8_ALLOW_FFFF 0x0040 /* Allow UNICODE_ILLEGAL */
+#define UTF8_ALLOW_LONG 0x0080 /* expecting fewer bytes */
+#define UTF8_ALLOW_ANYUV (UTF8_ALLOW_EMPTY|UTF8_ALLOW_FE_FF|\
+ UTF8_ALLOW_SURROGATE|UTF8_ALLOW_FFFF)
+#define UTF8_ALLOW_ANY 0x00FF
+#define UTF8_CHECK_ONLY 0x0200
+#define UTF8_ALLOW_DEFAULT (ckWARN(WARN_UTF8) ? 0 : \
+ UTF8_ALLOW_ANYUV)
+
+#define UNICODE_SURROGATE_FIRST 0xD800
+#define UNICODE_SURROGATE_LAST 0xDFFF
+#define UNICODE_REPLACEMENT 0xFFFD
+#define UNICODE_BYTE_ORDER_MARK 0xFEFF
+#define UNICODE_ILLEGAL 0xFFFF
+
+/* Though our UTF-8 encoding can go beyond this,
+ * 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) */
+#define UNICODE_ALLOW_FDD0 0x0002 /* Allow the U+FDD0...U+FDEF */
+#define UNICODE_ALLOW_FFFF 0x0004 /* Allow U+FFF[EF], U+1FFF[EF], ... */
+#define UNICODE_ALLOW_SUPER 0x0008 /* Allow past 0x10FFFF */
+#define UNICODE_ALLOW_ANY 0x000F
+
+#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_BYTE_ORDER_MARK)
+#define UNICODE_IS_ILLEGAL(c) ((c) == UNICODE_ILLEGAL)
+
+#ifdef HAS_QUAD
+# define UTF8_QUAD_MAX UINT64_C(0x1000000000)
+#endif
+
+#define UTF8_IS_ASCII(c) UTF8_IS_INVARIANT(c)
+
+#define UNICODE_GREEK_CAPITAL_LETTER_SIGMA 0x03A3
+#define UNICODE_GREEK_SMALL_LETTER_FINAL_SIGMA 0x03C2
+#define UNICODE_GREEK_SMALL_LETTER_SIGMA 0x03C3
+
+#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)
+
+#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')
+#define SHARP_S_SKIP 2
+
+#ifdef EBCDIC
+/* IS_UTF8_CHAR() is not ported to EBCDIC */
+#else
+#define IS_UTF8_CHAR_1(p) \
+ ((p)[0] <= 0x7F)
+#define IS_UTF8_CHAR_2(p) \
+ ((p)[0] >= 0xC2 && (p)[0] <= 0xDF && \
+ (p)[1] >= 0x80 && (p)[1] <= 0xBF)
+#define IS_UTF8_CHAR_3a(p) \
+ ((p)[0] == 0xE0 && \
+ (p)[1] >= 0xA0 && (p)[1] <= 0xBF && \
+ (p)[2] >= 0x80 && (p)[2] <= 0xBF)
+#define IS_UTF8_CHAR_3b(p) \
+ ((p)[0] >= 0xE1 && (p)[0] <= 0xEC && \
+ (p)[1] >= 0x80 && (p)[1] <= 0xBF && \
+ (p)[2] >= 0x80 && (p)[2] <= 0xBF)
+#define IS_UTF8_CHAR_3c(p) \
+ ((p)[0] == 0xED && \
+ (p)[1] >= 0x80 && (p)[1] <= 0xBF && \
+ (p)[2] >= 0x80 && (p)[2] <= 0xBF)
+/* In IS_UTF8_CHAR_3c(p) one could use
+ * (p)[1] >= 0x80 && (p)[1] <= 0x9F
+ * if one wanted to exclude surrogates. */
+#define IS_UTF8_CHAR_3d(p) \
+ ((p)[0] >= 0xEE && (p)[0] <= 0xEF && \
+ (p)[1] >= 0x80 && (p)[1] <= 0xBF && \
+ (p)[2] >= 0x80 && (p)[2] <= 0xBF)
+#define IS_UTF8_CHAR_4a(p) \
+ ((p)[0] == 0xF0 && \
+ (p)[1] >= 0x90 && (p)[1] <= 0xBF && \
+ (p)[2] >= 0x80 && (p)[2] <= 0xBF && \
+ (p)[3] >= 0x80 && (p)[3] <= 0xBF)
+#define IS_UTF8_CHAR_4b(p) \
+ ((p)[0] >= 0xF1 && (p)[0] <= 0xF3 && \
+ (p)[1] >= 0x80 && (p)[1] <= 0xBF && \
+ (p)[2] >= 0x80 && (p)[2] <= 0xBF && \
+ (p)[3] >= 0x80 && (p)[3] <= 0xBF)
+/* In IS_UTF8_CHAR_4c(p) one could use
+ * (p)[0] == 0xF4
+ * if one wanted to stop at the Unicode limit U+10FFFF.
+ * The 0xF7 allows us to go to 0x1fffff (0x200000 would
+ * require five bytes). Not doing any further code points
+ * since that is not needed (and that would not be strict
+ * UTF-8, anyway). The "slow path" in Perl_is_utf8_char()
+ * will take care of the "extended UTF-8". */
+#define IS_UTF8_CHAR_4c(p) \
+ ((p)[0] == 0xF4 && (p)[0] <= 0xF7 && \
+ (p)[1] >= 0x80 && (p)[1] <= 0xBF && \
+ (p)[2] >= 0x80 && (p)[2] <= 0xBF && \
+ (p)[3] >= 0x80 && (p)[3] <= 0xBF)
+
+#define IS_UTF8_CHAR_3(p) \
+ (IS_UTF8_CHAR_3a(p) || \
+ IS_UTF8_CHAR_3b(p) || \
+ IS_UTF8_CHAR_3c(p) || \
+ IS_UTF8_CHAR_3d(p))
+#define IS_UTF8_CHAR_4(p) \
+ (IS_UTF8_CHAR_4a(p) || \
+ IS_UTF8_CHAR_4b(p) || \
+ IS_UTF8_CHAR_4c(p))
+
+/* IS_UTF8_CHAR(p) is strictly speaking wrong (not UTF-8) because it
+ * (1) allows UTF-8 encoded UTF-16 surrogates
+ * (2) it allows code points past U+10FFFF.
+ * The Perl_is_utf8_char() full "slow" code will handle the Perl
+ * "extended UTF-8". */
+#define IS_UTF8_CHAR(p, n) \
+ ((n) == 1 ? IS_UTF8_CHAR_1(p) : \
+ (n) == 2 ? IS_UTF8_CHAR_2(p) : \
+ (n) == 3 ? IS_UTF8_CHAR_3(p) : \
+ (n) == 4 ? IS_UTF8_CHAR_4(p) : 0)
+
+#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:
+ */