/* utf8.h
*
- * Copyright (C) 2000, 2001, 2002, by Larry Wall and others
+ * Copyright (C) 2000, 2001, 2002, 2005, 2006 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.
# define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8)
#endif
+/* Source backward compatibility. */
+#define uvuni_to_utf8(d, uv) uvuni_to_utf8_flags(d, uv, 0)
+#define is_utf8_string_loc(s, len, ep) is_utf8_string_loclen(s, len, ep, 0)
+
#ifdef EBCDIC
/* The equivalent of these macros but implementing UTF-EBCDIC
are in the following header file:
*/
#include "utfebcdic.h"
+
#else
START_EXTERN_C
#endif
END_EXTERN_C
-#define UTF8SKIP(s) PL_utf8skip[*(const U8*)s]
+#define UTF8SKIP(s) PL_utf8skip[*(const U8*)(s)]
/* Native character to iso-8859-1 */
#define NATIVE_TO_ASCII(ch) (ch)
#define ASCII_TO_NEED(enc,ch) (ch)
/* As there are no translations avoid the function wrapper */
-#define Perl_utf8n_to_uvchr Perl_utf8n_to_uvuni
-#define Perl_uvchr_to_utf8 Perl_uvuni_to_utf8
+#define utf8n_to_uvchr utf8n_to_uvuni
+#define uvchr_to_utf8 uvuni_to_utf8
/*
* Note: we try to be careful never to call the isXXX_utf8() functions
* unless we're pretty sure we've seen the beginning of a UTF-8 character
* (that is, the two high bits are set). Otherwise we risk loading in the
- * heavy-duty SWASHINIT and SWASHGET routines unnecessarily.
+ * heavy-duty swash_init and swash_fetch routines unnecessarily.
*/
#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((const U8*)p) < 0xc0))) \
? isIDFIRST(*(p)) \
* SpecialCasing.txt. */
#define UTF8_MAXBYTES_CASE 6
-#define IN_BYTES (PL_curcop->op_private & HINT_BYTES)
+#define IN_BYTES (CopHINTS_get(PL_curcop) & HINT_BYTES)
#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)
#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_FE_FF 0x0008 /* Allow above 0x7fffFFFF */
#define UTF8_ALLOW_SHORT 0x0010
#define UTF8_ALLOW_SURROGATE 0x0020
-#define UTF8_ALLOW_FFFF 0x0040 /* Allows also FFFE. */
+#define UTF8_ALLOW_FFFF 0x0040 /* Allow UNICODE_ILLEGAL */
#define UTF8_ALLOW_LONG 0x0080
#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_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 0xFFF[EF], 0x1FFF[EF], ... */
-#define UNICODE_ALLOW_SUPER 0x0008 /* Allow past 10xFFFF */
+#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 && \
toLOWER((input)[1]) == 's')
#endif
#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 */
https://perl5.git.perl.org / perl5.git / blobdiff