X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/038e8d3c44243c2a2ae7cca24ca6b3918f23f942..b0b8faca51fd2e1d0912e31df8092981201cfab4:/utf8.h diff --git a/utf8.h b/utf8.h index 18cb7b2..3fbc28a 100644 --- a/utf8.h +++ b/utf8.h @@ -1,12 +1,16 @@ /* utf8.h * - * Copyright (C) 2000, 2001, 2002, 2005 by Larry Wall and others + * Copyright (C) 2000, 2001, 2002, 2005, 2006, 2007, 2009, + * 2010, 2011 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. * */ +#ifndef H_UTF8 /* Guard against recursive inclusion */ +#define H_UTF8 1 + /* Use UTF-8 as the default script encoding? * Turning this on will break scripts having non-UTF-8 binary * data (such as Latin-1) in string literals. */ @@ -16,40 +20,93 @@ # define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8) #endif +/* For to_utf8_fold_flags, q.v. */ +#define FOLD_FLAGS_LOCALE 0x1 +#define FOLD_FLAGS_FULL 0x2 +#define FOLD_FLAGS_NOMIX_ASCII 0x4 + +/* For _core_swash_init(), internal core use only */ +#define _CORE_SWASH_INIT_USER_DEFINED_PROPERTY 0x1 +#define _CORE_SWASH_INIT_RETURN_IF_UNDEF 0x2 +#define _CORE_SWASH_INIT_ACCEPT_INVLIST 0x4 + +#define to_uni_fold(c, p, lenp) _to_uni_fold_flags(c, p, lenp, FOLD_FLAGS_FULL) +#define to_utf8_fold(c, p, lenp) _to_utf8_fold_flags(c, p, lenp, \ + FOLD_FLAGS_FULL, NULL) +#define to_utf8_lower(a,b,c) _to_utf8_lower_flags(a,b,c,0, NULL) +#define to_utf8_upper(a,b,c) _to_utf8_upper_flags(a,b,c,0, NULL) +#define to_utf8_title(a,b,c) _to_utf8_title_flags(a,b,c,0, NULL) + +/* 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) + +#define foldEQ_utf8(s1, pe1, l1, u1, s2, pe2, l2, u2) \ + foldEQ_utf8_flags(s1, pe1, l1, u1, s2, pe2, l2, u2, 0) +#define FOLDEQ_UTF8_NOMIX_ASCII (1 << 0) +#define FOLDEQ_UTF8_LOCALE (1 << 1) +#define FOLDEQ_S1_ALREADY_FOLDED (1 << 2) +#define FOLDEQ_S2_ALREADY_FOLDED (1 << 3) + +/* +=for apidoc ibcmp_utf8 + +This is a synonym for (! foldEQ_utf8()) + +=cut +*/ +#define ibcmp_utf8(s1, pe1, l1, u1, s2, pe2, l2, u2) \ + cBOOL(! foldEQ_utf8(s1, pe1, l1, u1, s2, pe2, l2, u2)) + #ifdef EBCDIC /* The equivalent of these macros but implementing UTF-EBCDIC are in the following header file: */ #include "utfebcdic.h" -#else + +#else /* ! EBCDIC */ START_EXTERN_C #ifdef DOINIT EXTCONST unsigned char PL_utf8skip[] = { -1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ -1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ -1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ -1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ -1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */ -1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */ -2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* scripts */ -3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6, /* cjk etc. */ -7,13, /* Perl extended (not UTF-8). Up to 72bit allowed (64-bit + reserved). */ +/* 0x00 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x10 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x20 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x30 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x40 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x50 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x60 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x70 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */ +/* 0x80 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus: continuation byte */ +/* 0x90 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus: continuation byte */ +/* 0xA0 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus: continuation byte */ +/* 0xB0 */ 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus: continuation byte */ +/* 0xC0 */ 2,2, /* overlong */ +/* 0xC2 */ 2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* U+0080 to U+03FF */ +/* 0xD0 */ 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* U+0400 to U+07FF */ +/* 0xE0 */ 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3, /* U+0800 to U+FFFF */ +/* 0xF0 */ 4,4,4,4,4,4,4,4,5,5,5,5,6,6, /* above BMP to 2**31 - 1 */ +/* 0xFE */ 7,13, /* Perl extended (never was official UTF-8). Up to 72bit + allowed (64-bit + reserved). */ }; #else EXTCONST unsigned char PL_utf8skip[]; #endif END_EXTERN_C -#define UTF8SKIP(s) PL_utf8skip[*(const U8*)(s)] + +#include "regcharclass.h" +#include "unicode_constants.h" /* Native character to iso-8859-1 */ #define NATIVE_TO_ASCII(ch) (ch) #define ASCII_TO_NATIVE(ch) (ch) /* Transform after encoding */ #define NATIVE_TO_UTF(ch) (ch) +#define NATIVE_TO_I8(ch) NATIVE_TO_UTF(ch) /* a clearer synonym */ #define UTF_TO_NATIVE(ch) (ch) +#define I8_TO_NATIVE(ch) UTF_TO_NATIVE(ch) /* Transforms in wide UV chars */ #define UNI_TO_NATIVE(ch) (ch) #define NATIVE_TO_UNI(ch) (ch) @@ -57,9 +114,10 @@ END_EXTERN_C #define NATIVE_TO_NEED(enc,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 +/* As there are no translations, avoid the function wrapper */ +#define utf8n_to_uvchr utf8n_to_uvuni +#define valid_utf8_to_uvchr valid_utf8_to_uvuni +#define uvchr_to_utf8 uvuni_to_utf8 /* @@ -68,60 +126,76 @@ END_EXTERN_C 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+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+D800..U+DFFF +++++++ utf16 surrogates, not legal utf8 +++++++ U+E000..U+FFFF EE..EF 80..BF 80..BF - U+10000..U+3FFFF F0 90..BF 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 + Below are non-Unicode code points + U+110000..U+13FFFF F4 90..BF 80..BF 80..BF + U+110000..U+1FFFFF F5..F7 80..BF 80..BF 80..BF + U+200000: F8.. * 88..BF 80..BF 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. -The "gaps" are caused by legal UTF-8 avoiding non-shortest encodings: -it is technically possible to UTF-8-encode a single code point in different -ways, but that is explicitly forbidden, and the shortest possible encoding -should always be used (and that is what Perl does). +Note the gaps before several of the byte entries above marked by '*'. These are +caused by legal UTF-8 avoiding non-shortest encodings: it is technically +possible to UTF-8-encode a single code point in different ways, but that is +explicitly forbidden, and the shortest possible encoding should always be used +(and that is what Perl does). */ /* Another way to look at it, as bits: - Code Points 1st Byte 2nd Byte 3rd Byte 4th Byte + Code Points 1st Byte 2nd Byte 3rd Byte 4th Byte - 0aaaaaaa 0aaaaaaa - 00000bbbbbaaaaaa 110bbbbb 10aaaaaa - ccccbbbbbbaaaaaa 1110cccc 10bbbbbb 10aaaaaa - 00000dddccccccbbbbbbaaaaaa 11110ddd 10cccccc 10bbbbbb 10aaaaaa + 0aaa aaaa 0aaa aaaa + 0000 0bbb bbaa aaaa 110b bbbb 10aa aaaa + cccc bbbb bbaa aaaa 1110 cccc 10bb bbbb 10aa aaaa + 00 000d ddcc cccc bbbb bbaa aaaa 1111 0ddd 10cc cccc 10bb bbbb 10aa aaaa 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 +leading bits of the start byte tell how many bytes there are in the encoded character. -*/ +Perl's extended UTF-8 means we can have start bytes up to FF. +*/ #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 UTF8_IS_START(c) (((U8)c) >= 0xc0 && (((U8)c) <= 0xfd)) -#define UTF8_IS_CONTINUATION(c) (((U8)c) >= 0x80 && (((U8)c) <= 0xbf)) +#define UTF8_IS_START(c) (((U8)c) >= 0xc2) +#define UTF8_IS_CONTINUATION(c) ((((U8)c) & 0xC0) == 0x80) #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))) +/* Use UTF8_IS_NEXT_CHAR_DOWNGRADEABLE() instead if the input isn't known to + * be well-formed. Masking with 0xfe allows low bit to be 0 or 1; thus this + * matches 0xc[23]. */ +#define UTF8_IS_DOWNGRADEABLE_START(c) (((U8)c & 0xfe) == 0xc2) + +#define UTF8_IS_ABOVE_LATIN1(c) ((U8)(c) >= 0xc4) + +#define UTF_START_MARK(len) (((len) > 7) ? 0xFF : (0xFE << (7-(len)))) + +/* Masks out the initial one bits in a start byte, leaving the real data ones. + * Doesn't work on an invariant byte */ +#define UTF_START_MASK(len) (((len) >= 7) ? 0x00 : (0x1F >> ((len)-2))) #define UTF_CONTINUATION_MARK 0x80 #define UTF_ACCUMULATION_SHIFT 6 + +/* 2**UTF_ACCUMULATION_SHIFT - 1 */ #define UTF_CONTINUATION_MASK ((U8)0x3f) -#define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT) | (((U8)new) & UTF_CONTINUATION_MASK)) -#define UTF8_EIGHT_BIT_HI(c) ((((U8)(c))>>UTF_ACCUMULATION_SHIFT)|UTF_START_MARK(2)) -#define UTF8_EIGHT_BIT_LO(c) (((((U8)(c)))&UTF_CONTINUATION_MASK)|UTF_CONTINUATION_MARK) +/* This sets the UTF_CONTINUATION_MASK in the upper bits of a word. If a value + * is anded with it, and the result is non-zero, then using the original value + * in UTF8_ACCUMULATE will overflow, shifting bits off the left */ +#define UTF_ACCUMULATION_OVERFLOW_MASK \ + (((UV) UTF_CONTINUATION_MASK) << ((sizeof(UV) * CHARBITS) \ + - UTF_ACCUMULATION_SHIFT)) #ifdef HAS_QUAD #define UNISKIP(uv) ( (uv) < 0x80 ? 1 : \ @@ -141,198 +215,324 @@ encoded character. (uv) < 0x80000000 ? 6 : 7 ) #endif -/* - * 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. - */ -#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((const U8*)p) < 0xc0))) \ - ? isIDFIRST(*(p)) \ - : isIDFIRST_utf8((const U8*)p)) -#define isALNUM_lazy_if(p,c) ((IN_BYTES || (!c || (*((const U8*)p) < 0xc0))) \ - ? isALNUM(*(p)) \ - : isALNUM_utf8((const U8*)p)) +/* 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 Unicode's upper limit, 0x10FFFF, can be + * expressed with 4 bytes. However, Perl thinks of UTF-8 as a way to encode + * non-negative integers in a binary format, even those above Unicode */ +#define UTF8_MAXBYTES 13 + +/* The maximum number of UTF-8 bytes a single Unicode character can + * uppercase/lowercase/fold into. Unicode guarantees that the maximum + * expansion is 3 characters. On ASCIIish platforms, the highest Unicode + * character occupies 4 bytes, therefore this number would be 12, but this is + * smaller than the maximum width a single above-Unicode character can occupy, + * so use that instead */ +#if UTF8_MAXBYTES < 12 +#error UTF8_MAXBYTES must be at least 12 +#endif +#define UTF8_MAXBYTES_CASE UTF8_MAXBYTES #endif /* EBCDIC vs ASCII */ -/* Rest of these are attributes of Unicode and perl's internals rather than the encoding */ +/* Rest of these are attributes of Unicode and perl's internals rather than the + * encoding, or happen to be the same in both ASCII and EBCDIC (at least at + * this level; the macros that some of these call may have different + * definitions in the two encodings */ + +#define NATIVE8_TO_UNI(ch) NATIVE_TO_ASCII(ch) /* a clearer synonym */ + +#define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT) \ + | (((U8)new) & UTF_CONTINUATION_MASK)) + +/* This works in the face of malformed UTF-8. */ +#define UTF8_IS_NEXT_CHAR_DOWNGRADEABLE(s, e) (UTF8_IS_DOWNGRADEABLE_START(*s) \ + && ( (e) - (s) > 1) \ + && UTF8_IS_CONTINUATION(*((s)+1))) + +/* Convert a two (not one) byte utf8 character to a unicode code point value. + * Needs just one iteration of accumulate. Should not be used unless it is + * known that the two bytes are legal: 1) two-byte start, and 2) continuation. + * Note that the result can be larger than 255 if the input character is not + * downgradable */ +#define TWO_BYTE_UTF8_TO_UNI(HI, LO) \ + UTF8_ACCUMULATE((NATIVE_TO_UTF(HI) & UTF_START_MASK(2)), \ + NATIVE_TO_UTF(LO)) + +#define UTF8SKIP(s) PL_utf8skip[*(const U8*)(s)] + +#define UTF8_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_UTF(c)) +#define NATIVE_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE8_TO_UNI(c)) + +#define MAX_PORTABLE_UTF8_TWO_BYTE 0x3FF /* constrained by EBCDIC */ + +/* The macros in the next sets are used to generate the two utf8 or utfebcdic + * bytes from an ordinal that is known to fit into two bytes; it must be less + * than 0x3FF to work across both encodings. */ +/* Nocast allows these to be used in the case label of a switch statement */ +#define UTF8_TWO_BYTE_HI_nocast(c) NATIVE_TO_I8(((c) \ + >> UTF_ACCUMULATION_SHIFT) | (0xFF & UTF_START_MARK(2))) +#define UTF8_TWO_BYTE_LO_nocast(c) NATIVE_TO_I8(((c) & UTF_CONTINUATION_MASK) \ + | UTF_CONTINUATION_MARK) + +#define UTF8_TWO_BYTE_HI(c) ((U8) (UTF8_TWO_BYTE_HI_nocast(c))) +#define UTF8_TWO_BYTE_LO(c) ((U8) (UTF8_TWO_BYTE_LO_nocast(c))) + +/* This name is used when the source is a single byte */ +#define UTF8_EIGHT_BIT_HI(c) UTF8_TWO_BYTE_HI((U8)(c)) +#define UTF8_EIGHT_BIT_LO(c) UTF8_TWO_BYTE_LO((U8)(c)) + +/* + * 'UTF' is whether or not p is encoded in UTF8. The names 'foo_lazy_if' stem + * from an earlier version of these macros in which they didn't call the + * foo_utf8() macros (i.e. were 'lazy') unless they decided that *p is the + * beginning of a utf8 character. Now that foo_utf8() determines that itself, + * no need to do it again here + */ +#define isIDFIRST_lazy_if(p,UTF) ((IN_BYTES || !UTF ) \ + ? isIDFIRST(*(p)) \ + : isIDFIRST_utf8((const U8*)p)) +#define isALNUM_lazy_if(p,UTF) ((IN_BYTES || (!UTF )) \ + ? isALNUM(*(p)) \ + : isALNUM_utf8((const U8*)p)) #define isIDFIRST_lazy(p) isIDFIRST_lazy_if(p,1) #define isALNUM_lazy(p) isALNUM_lazy_if(p,1) -#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 -#define UTF8_MAXLEN_UCLC 3 /* Obsolete, do not use. */ -#define UTF8_MAXLEN_UCLC_MULT 39 /* Obsolete, do not use. */ -#define UTF8_MAXLEN_FOLD 3 /* Obsolete, do not use. */ -#define UTF8_MAXLEN_FOLD_MULT 39 /* Obsolete, do not use. */ +/* A Unicode character can fold to up to 3 characters */ +#define UTF8_MAX_FOLD_CHAR_EXPAND 3 -/* 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 UnicodeDatabase.txt, CaseFolding.txt, and - * 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 IN_UNI_8_BIT \ + (CopHINTS_get(PL_curcop) & (HINT_UNI_8_BIT|HINT_LOCALE_NOT_CHARS) \ + && ! IN_LOCALE_RUNTIME && ! IN_BYTES) -#define UTF8_ALLOW_EMPTY 0x0001 + +#define UTF8_ALLOW_EMPTY 0x0001 /* Allow a zero length string */ + +/* Allow first byte to be a continuation byte */ #define UTF8_ALLOW_CONTINUATION 0x0002 + +/* Allow second... bytes to be non-continuation bytes */ #define UTF8_ALLOW_NON_CONTINUATION 0x0004 -#define UTF8_ALLOW_FE_FF 0x0008 -#define UTF8_ALLOW_SHORT 0x0010 -#define UTF8_ALLOW_SURROGATE 0x0020 -#define UTF8_ALLOW_FFFF 0x0040 /* Allows also FFFE. */ -#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 + +/* expecting more bytes than were available in the string */ +#define UTF8_ALLOW_SHORT 0x0008 + +/* Overlong sequence; i.e., the code point can be specified in fewer bytes. */ +#define UTF8_ALLOW_LONG 0x0010 + +#define UTF8_DISALLOW_SURROGATE 0x0020 /* Unicode surrogates */ +#define UTF8_WARN_SURROGATE 0x0040 + +#define UTF8_DISALLOW_NONCHAR 0x0080 /* Unicode non-character */ +#define UTF8_WARN_NONCHAR 0x0100 /* code points */ + +#define UTF8_DISALLOW_SUPER 0x0200 /* Super-set of Unicode: code */ +#define UTF8_WARN_SUPER 0x0400 /* points above the legal max */ + +/* Code points which never were part of the original UTF-8 standard, the first + * byte of which is a FE or FF on ASCII platforms. */ +#define UTF8_DISALLOW_FE_FF 0x0800 +#define UTF8_WARN_FE_FF 0x1000 + +#define UTF8_CHECK_ONLY 0x2000 + +/* For backwards source compatibility. They do nothing, as the default now + * includes what they used to mean. The first one's meaning was to allow the + * just the single non-character 0xFFFF */ +#define UTF8_ALLOW_FFFF 0 +#define UTF8_ALLOW_SURROGATE 0 + +#define UTF8_DISALLOW_ILLEGAL_INTERCHANGE (UTF8_DISALLOW_SUPER|UTF8_DISALLOW_NONCHAR|UTF8_DISALLOW_SURROGATE|UTF8_DISALLOW_FE_FF) +#define UTF8_WARN_ILLEGAL_INTERCHANGE \ + (UTF8_WARN_SUPER|UTF8_WARN_NONCHAR|UTF8_WARN_SURROGATE|UTF8_WARN_FE_FF) +#define UTF8_ALLOW_ANY \ + (~(UTF8_DISALLOW_ILLEGAL_INTERCHANGE|UTF8_WARN_ILLEGAL_INTERCHANGE)) +#define UTF8_ALLOW_ANYUV \ + (UTF8_ALLOW_EMPTY \ + & ~(UTF8_DISALLOW_ILLEGAL_INTERCHANGE|UTF8_WARN_ILLEGAL_INTERCHANGE)) +#define UTF8_ALLOW_DEFAULT (ckWARN(WARN_UTF8) ? 0 : \ + UTF8_ALLOW_ANYUV) + +/* Surrogates, non-character code points and above-Unicode code points are + * problematic in some contexts. This allows code that needs to check for + * those to to quickly exclude the vast majority of code points it will + * encounter */ +#define UTF8_FIRST_PROBLEMATIC_CODE_POINT_FIRST_BYTE \ + FIRST_SURROGATE_UTF8_FIRST_BYTE + +#define UTF8_IS_SURROGATE(s) cBOOL(is_SURROGATE_utf8(s)) +#define UTF8_IS_REPLACEMENT(s, send) cBOOL(is_REPLACEMENT_utf8_safe(s,send)) + +/* ASCII EBCDIC I8 + * U+10FFFF: \xF4\x8F\xBF\xBF \xF9\xA1\xBF\xBF\xBF max legal Unicode + * U+110000: \xF4\x90\x80\x80 \xF9\xA2\xA0\xA0\xA0 + * U+110001: \xF4\x90\x80\x81 \xF9\xA2\xA0\xA0\xA1 + */ +#ifdef EBCDIC /* Both versions assume well-formed UTF8 */ +# define UTF8_IS_SUPER(s) (NATIVE_TO_I8(*(s)) >= 0xF9 \ + && (NATIVE_TO_I8(*(s)) > 0xF9) || (NATIVE_TO_I8(*((s)) + 1 >= 0xA2))) +#else +# define UTF8_IS_SUPER(s) (*(s) >= 0xF4 \ + && (*(s) > 0xF4 || (*((s) + 1) >= 0x90))) +#endif + +/* These are now machine generated, and the 'given' clause is no longer + * applicable */ +#define UTF8_IS_NONCHAR_GIVEN_THAT_NON_SUPER_AND_GE_PROBLEMATIC(s) \ + cBOOL(is_NONCHAR_utf8(s)) +#define UTF8_IS_NONCHAR_(s) \ + UTF8_IS_NONCHAR_GIVEN_THAT_NON_SUPER_AND_GE_PROBLEMATIC(s) #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 3.2 says. */ + * let's be conservative and do as Unicode 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 0xFFF[EF], 0x1FFF[EF], ... */ -#define UNICODE_ALLOW_SUPER 0x0008 /* Allow past 10xFFFF */ -#define UNICODE_ALLOW_ANY 0x000F +#define UNICODE_WARN_SURROGATE 0x0001 /* UTF-16 surrogates */ +#define UNICODE_WARN_NONCHAR 0x0002 /* Non-char code points */ +#define UNICODE_WARN_SUPER 0x0004 /* Above 0x10FFFF */ +#define UNICODE_WARN_FE_FF 0x0008 /* Above 0x10FFFF */ +#define UNICODE_DISALLOW_SURROGATE 0x0010 +#define UNICODE_DISALLOW_NONCHAR 0x0020 +#define UNICODE_DISALLOW_SUPER 0x0040 +#define UNICODE_DISALLOW_FE_FF 0x0080 +#define UNICODE_WARN_ILLEGAL_INTERCHANGE \ + (UNICODE_WARN_SURROGATE|UNICODE_WARN_NONCHAR|UNICODE_WARN_SUPER) +#define UNICODE_DISALLOW_ILLEGAL_INTERCHANGE \ + (UNICODE_DISALLOW_SURROGATE|UNICODE_DISALLOW_NONCHAR|UNICODE_DISALLOW_SUPER) + +/* For backward source compatibility, as are now the default */ +#define UNICODE_ALLOW_SURROGATE 0 +#define UNICODE_ALLOW_SUPER 0 +#define UNICODE_ALLOW_ANY 0 #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) +#define UNICODE_IS_NONCHAR(c) ((c >= 0xFDD0 && c <= 0xFDEF) \ + /* The other noncharacters end in FFFE or FFFF, which \ + * the mask below catches both of, but beyond the last \ + * official unicode code point, they aren't \ + * noncharacters, since those aren't Unicode \ + * characters at all */ \ + || ((((c & 0xFFFE) == 0xFFFE)) && ! UNICODE_IS_SUPER(c))) +#define UNICODE_IS_SUPER(c) ((c) > PERL_UNICODE_MAX) +#define UNICODE_IS_FE_FF(c) ((c) > 0x7FFFFFFF) #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 LATIN_SMALL_LETTER_SHARP_S LATIN_SMALL_LETTER_SHARP_S_NATIVE +#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS \ + LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE +#define MICRO_SIGN MICRO_SIGN_NATIVE +#define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE \ + LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE +#define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE \ + LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE #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 GREEK_SMALL_LETTER_MU 0x03BC +#define GREEK_CAPITAL_LETTER_MU 0x039C /* Upper and title case of MICRON */ +#define LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS 0x0178 /* Also is title case */ +#define LATIN_CAPITAL_LETTER_SHARP_S 0x1E9E +#define LATIN_SMALL_LETTER_LONG_S 0x017F +#define KELVIN_SIGN 0x212A +#define ANGSTROM_SIGN 0x212B #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) && \ +#define ANYOF_FOLD_SHARP_S(node, input, end) \ + (ANYOF_BITMAP_TEST(node, LATIN_SMALL_LETTER_SHARP_S) && \ + (ANYOF_NONBITMAP(node)) && \ + (ANYOF_FLAGS(node) & ANYOF_LOC_NONBITMAP_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 -#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)) +/* If you want to exclude surrogates, and beyond legal Unicode, see the blame + * log for earlier versions which gave details for these */ + +#ifndef EBCDIC +/* This was generated by regen/regcharclass.pl, and then moved here. The lines + * that generated it were then commented out. This was done solely because it + * takes on the order of 10 minutes to generate, and is never going to change. + * The EBCDIC equivalent hasn't been commented out in regcharclass.pl, so it + * should generate and run the correct stuff */ +/*** GENERATED CODE ***/ +#define is_UTF8_CHAR_utf8_safe(s,e) \ +( ((e)-(s) > 3) ? \ + ( ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) ? 1 \ + : ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) ? \ + ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 ) \ + : ( 0xE0 == ((U8*)s)[0] ) ? \ + ( ( ( ( ((U8*)s)[1] & 0xE0 ) == 0xA0 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ + : ( 0xE1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xEF ) ? \ + ( ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ + : ( 0xF0 == ((U8*)s)[0] ) ? \ + ( ( ( ( 0x90 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0xBF ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\ + : ( 0xF1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xF7 ) ? \ + ( ( ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\ + : 0 ) \ +: ((e)-(s) > 2) ? \ + ( ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) ? 1 \ + : ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) ? \ + ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 ) \ + : ( 0xE0 == ((U8*)s)[0] ) ? \ + ( ( ( ( ((U8*)s)[1] & 0xE0 ) == 0xA0 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ + : ( 0xE1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xEF ) ? \ + ( ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ + : 0 ) \ +: ((e)-(s) > 1) ? \ + ( ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) ? 1 \ + : ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) ? \ + ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 ) \ + : 0 ) \ +: ((e)-(s) > 0) ? \ + ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) \ +: 0 ) +#endif /* 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(p, n) (is_UTF8_CHAR_utf8_safe(p, (p) + (n)) == n) -#define IS_UTF8_CHAR_FAST(n) ((n) <= 4) +/* regen/regcharclass.pl generates is_UTF8_CHAR_utf8_safe() macros for up to + * these number of bytes. So this has to be coordinated with it */ +#ifdef EBCDIC +# define IS_UTF8_CHAR_FAST(n) ((n) <= 5) +#else +# define IS_UTF8_CHAR_FAST(n) ((n) <= 4) +#endif -#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) +#endif /* H_UTF8 */ -#endif /* IS_UTF8_CHAR() for UTF-8 */ +/* + * Local variables: + * c-indentation-style: bsd + * c-basic-offset: 4 + * indent-tabs-mode: nil + * End: + * + * ex: set ts=8 sts=4 sw=4 et: + */