X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/ecc1615fad60409fb5f52f04c821b95dcf54f48d..5f270787832458b6f6e80d68a820cd42a983fbb2:/utf8.h diff --git a/utf8.h b/utf8.h index ae68ff1..fb83507 100644 --- a/utf8.h +++ b/utf8.h @@ -14,8 +14,8 @@ * */ -#ifndef H_UTF8 /* Guard against recursive inclusion */ -#define H_UTF8 1 +#ifndef PERL_UTF8_H_ /* Guard against recursive inclusion */ +#define PERL_UTF8_H_ 1 /* Use UTF-8 as the default script encoding? * Turning this on will break scripts having non-UTF-8 binary @@ -34,11 +34,6 @@ #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 - /* =head1 Unicode Support L has an introduction to this API. @@ -66,21 +61,21 @@ the string is invariant. #define is_ascii_string(s, len) is_utf8_invariant_string(s, len) #define is_invariant_string(s, len) is_utf8_invariant_string(s, len) +#define uvoffuni_to_utf8_flags(d,uv,flags) \ + uvoffuni_to_utf8_flags_msgs(d, uv, flags, 0) #define uvchr_to_utf8(a,b) uvchr_to_utf8_flags(a,b,0) #define uvchr_to_utf8_flags(d,uv,flags) \ - uvoffuni_to_utf8_flags(d,NATIVE_TO_UNI(uv),flags) + uvchr_to_utf8_flags_msgs(d,uv,flags, 0) +#define uvchr_to_utf8_flags_msgs(d,uv,flags,msgs) \ + uvoffuni_to_utf8_flags_msgs(d,NATIVE_TO_UNI(uv),flags, msgs) #define utf8_to_uvchr_buf(s, e, lenp) \ - utf8n_to_uvchr(s, (U8*)(e) - (U8*)(s), lenp, \ - ckWARN_d(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY) + utf8_to_uvchr_buf_helper((const U8 *) (s), (const U8 *) e, lenp) +#define utf8n_to_uvchr(s, len, lenp, flags) \ + utf8n_to_uvchr_error(s, len, lenp, flags, 0) +#define utf8n_to_uvchr_error(s, len, lenp, flags, errors) \ + utf8n_to_uvchr_msgs(s, len, lenp, flags, errors, 0) #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) -#define to_utf8_lower(a,b,c) _to_utf8_lower_flags(a,b,c,0) -#define to_utf8_upper(a,b,c) _to_utf8_upper_flags(a,b,c,0) -#define to_utf8_title(a,b,c) _to_utf8_title_flags(a,b,c,0) - -/* Source backward compatibility. */ -#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) @@ -104,11 +99,19 @@ the string is invariant. #else /* ! EBCDIC */ START_EXTERN_C -/* 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 */ +/* + +=for apidoc AmnU|STRLEN|UTF8_MAXBYTES + +The maximum width of a single UTF-8 encoded character, 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. + +=cut + */ #define UTF8_MAXBYTES 13 #ifdef DOINIT @@ -141,20 +144,53 @@ EXTCONST unsigned char PL_utf8skip[]; END_EXTERN_C -#if defined(_MSC_VER) && _MSC_VER < 1400 -/* older MSVC versions have a smallish macro buffer */ -#define PERL_SMALL_MACRO_BUFFER -#endif +/* -/* Native character to/from iso-8859-1. Are the identity functions on ASCII - * platforms */ -#ifdef PERL_SMALL_MACRO_BUFFER -#define NATIVE_TO_LATIN1(ch) ((U8)(ch)) -#define LATIN1_TO_NATIVE(ch) ((U8)(ch)) -#else -#define NATIVE_TO_LATIN1(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) (ch))) -#define LATIN1_TO_NATIVE(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) (ch))) -#endif +=for apidoc Am|U8|NATIVE_TO_LATIN1|U8 ch + +Returns the Latin-1 (including ASCII and control characters) equivalent of the +input native code point given by C. Thus, C on +EBCDIC platforms returns 65. These each represent the character C<"A"> on +their respective platforms. On ASCII platforms no conversion is needed, so +this macro expands to just its input, adding no time nor space requirements to +the implementation. + +For conversion of code points potentially larger than will fit in a character, +use L. + +=for apidoc Am|U8|LATIN1_TO_NATIVE|U8 ch + +Returns the native equivalent of the input Latin-1 code point (including ASCII +and control characters) given by C. Thus, C on +EBCDIC platforms returns 194. These each represent the character C<"B"> on +their respective platforms. On ASCII platforms no conversion is needed, so +this macro expands to just its input, adding no time nor space requirements to +the implementation. + +For conversion of code points potentially larger than will fit in a character, +use L. + +=for apidoc Am|UV|NATIVE_TO_UNI|UV ch + +Returns the Unicode equivalent of the input native code point given by C. +Thus, C on EBCDIC platforms returns 67. These each +represent the character C<"C"> on their respective platforms. On ASCII +platforms no conversion is needed, so this macro expands to just its input, +adding no time nor space requirements to the implementation. + +=for apidoc Am|UV|UNI_TO_NATIVE|UV ch + +Returns the native equivalent of the input Unicode code point given by C. +Thus, C on EBCDIC platforms returns 196. These each +represent the character C<"D"> on their respective platforms. On ASCII +platforms no conversion is needed, so this macro expands to just its input, +adding no time nor space requirements to the implementation. + +=cut +*/ + +#define NATIVE_TO_LATIN1(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) ((ch) | 0))) +#define LATIN1_TO_NATIVE(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) ((ch) | 0))) /* I8 is an intermediate version of UTF-8 used only in UTF-EBCDIC. We thus * consider it to be identical to UTF-8 on ASCII platforms. Strictly speaking @@ -162,17 +198,11 @@ END_EXTERN_C * because they are 8-bit encodings that serve the same purpose in Perl, and * rarely do we need to distinguish them. The term "NATIVE_UTF8" applies to * whichever one is applicable on the current platform */ -#ifdef PERL_SMALL_MACRO_BUFFER -#define NATIVE_UTF8_TO_I8(ch) ((U8) (ch)) -#define I8_TO_NATIVE_UTF8(ch) ((U8) (ch)) -#else -#define NATIVE_UTF8_TO_I8(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) (ch))) -#define I8_TO_NATIVE_UTF8(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) (ch))) -#endif +#define NATIVE_UTF8_TO_I8(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) ((ch) | 0))) +#define I8_TO_NATIVE_UTF8(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) ((U8) ((ch) | 0))) -/* Transforms in wide UV chars */ -#define UNI_TO_NATIVE(ch) ((UV) (ch)) -#define NATIVE_TO_UNI(ch) ((UV) (ch)) +#define UNI_TO_NATIVE(ch) ((UV) ((ch) | 0)) +#define NATIVE_TO_UNI(ch) ((UV) ((ch) | 0)) /* @@ -223,61 +253,11 @@ As you can see, the continuation bytes all begin with C<10>, and 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. - -*/ - -/* Anything larger than this will overflow the word if it were converted into a UV */ -#if defined(UV_IS_QUAD) -# define HIGHEST_REPRESENTABLE_UTF8 "\xFF\x80\x8F\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF\xBF" -#else -# define HIGHEST_REPRESENTABLE_UTF8 "\xFE\x83\xBF\xBF\xBF\xBF\xBF" -#endif - -/* Is the representation of the Unicode code point 'cp' the same regardless of - * being encoded in UTF-8 or not? */ -#define OFFUNI_IS_INVARIANT(cp) isASCII(cp) - -/* Is the representation of the code point 'cp' the same regardless of - * being encoded in UTF-8 or not? 'cp' is native if < 256; Unicode otherwise - * */ -#define UVCHR_IS_INVARIANT(cp) OFFUNI_IS_INVARIANT(cp) - -/* This defines the bits that are to be in the continuation bytes of a multi-byte - * UTF-8 encoded character that mark it is a continuation byte. */ -#define UTF_CONTINUATION_MARK 0x80 - -/* Misleadingly named: is the UTF8-encoded byte 'c' part of a variant sequence - * in UTF-8? This is the inverse of UTF8_IS_INVARIANT. The |0 makes sure this - * isn't mistakenly called with a ptr argument */ -#define UTF8_IS_CONTINUED(c) (((U8)((c) | 0)) & UTF_CONTINUATION_MARK) - -/* Is the byte 'c' the first byte of a multi-byte UTF8-8 encoded sequence? - * This doesn't catch invariants (they are single-byte). It also excludes the - * illegal overlong sequences that begin with C0 and C1. The |0 makes sure - * this isn't mistakenly called with a ptr argument */ -#define UTF8_IS_START(c) (((U8)((c) | 0)) >= 0xc2) - -/* For use in UTF8_IS_CONTINUATION() below */ -#define UTF_IS_CONTINUATION_MASK 0xC0 - -/* Is the byte 'c' part of a multi-byte UTF8-8 encoded sequence, and not the - * first byte thereof? The |0 makes sure this isn't mistakenly called with a - * ptr argument */ -#define UTF8_IS_CONTINUATION(c) \ - ((((U8)((c) | 0)) & UTF_IS_CONTINUATION_MASK) == UTF_CONTINUATION_MARK) - -/* Is the UTF8-encoded byte 'c' the first byte of a two byte sequence? Use - * UTF8_IS_NEXT_CHAR_DOWNGRADEABLE() instead if the input isn't known to - * be well-formed. Masking with 0xfe allows the low bit to be 0 or 1; thus - * this matches 0xc[23]. The |0 makes sure this isn't mistakenly called with a - * ptr argument */ -#define UTF8_IS_DOWNGRADEABLE_START(c) ((((U8)((c) | 0)) & 0xfe) == 0xc2) - -/* Is the UTF8-encoded byte 'c' the first byte of a sequence of bytes that - * represent a code point > 255? The |0 makes sure this isn't mistakenly - * called with a ptr argument */ -#define UTF8_IS_ABOVE_LATIN1(c) (((U8)((c) | 0)) >= 0xc4) +Perl's extended UTF-8 means we can have start bytes up through FF, though any +beginning with FF yields a code point that is too large for 32-bit ASCII +platforms. FF signals to use 13 bytes for the encoded character. This breaks +the paradigm that the number of leading bits gives how many total bytes there +are in the character. */ /* This is the number of low-order bits a continuation byte in a UTF-8 encoded * sequence contributes to the specification of the code point. In the bit @@ -293,13 +273,51 @@ Perl's extended UTF-8 means we can have start bytes up to FF. * 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 isUTF8_POSSIBLY_PROBLEMATIC(c) ((U8) c >= 0xED) +#define isUTF8_POSSIBLY_PROBLEMATIC(c) (__ASSERT_(FITS_IN_8_BITS(c)) \ + (U8) c >= 0xED) + +#define UNICODE_IS_PERL_EXTENDED(uv) UNLIKELY((UV) (uv) > 0x7FFFFFFF) #endif /* EBCDIC vs ASCII */ -/* 2**UTF_ACCUMULATION_SHIFT - 1 */ +/* 2**UTF_ACCUMULATION_SHIFT - 1. This masks out all but the bits that carry + * real information in a continuation byte. This turns out to be 0x3F in + * UTF-8, 0x1F in UTF-EBCDIC. */ #define UTF_CONTINUATION_MASK ((U8) ((1U << UTF_ACCUMULATION_SHIFT) - 1)) +/* For use in UTF8_IS_CONTINUATION(). This turns out to be 0xC0 in UTF-8, + * E0 in UTF-EBCDIC */ +#define UTF_IS_CONTINUATION_MASK ((U8) (0xFF << UTF_ACCUMULATION_SHIFT)) + +/* This defines the bits that are to be in the continuation bytes of a + * multi-byte UTF-8 encoded character that mark it is a continuation byte. + * This turns out to be 0x80 in UTF-8, 0xA0 in UTF-EBCDIC. (khw doesn't know + * the underlying reason that B0 works here) */ +#define UTF_CONTINUATION_MARK (UTF_IS_CONTINUATION_MASK & 0xB0) + +/* Is the byte 'c' part of a multi-byte UTF8-8 encoded sequence, and not the + * first byte thereof? */ +#define UTF8_IS_CONTINUATION(c) (__ASSERT_(FITS_IN_8_BITS(c)) \ + (((NATIVE_UTF8_TO_I8(c) & UTF_IS_CONTINUATION_MASK) \ + == UTF_CONTINUATION_MARK))) + +/* Is the representation of the Unicode code point 'cp' the same regardless of + * being encoded in UTF-8 or not? This is a fundamental property of + * UTF-8,EBCDIC */ +#define OFFUNI_IS_INVARIANT(c) (((WIDEST_UTYPE)(c)) < UTF_CONTINUATION_MARK) + +/* +=for apidoc Am|bool|UVCHR_IS_INVARIANT|UV cp + +Evaluates to 1 if the representation of code point C is the same whether or +not it is encoded in UTF-8; otherwise evaluates to 0. UTF-8 invariant +characters can be copied as-is when converting to/from UTF-8, saving time. +C is Unicode if above 255; otherwise is platform-native. + +=cut + */ +#define UVCHR_IS_INVARIANT(cp) (OFFUNI_IS_INVARIANT(NATIVE_TO_UNI(cp))) + /* Internal macro to be used only in this file to aid in constructing other * publicly accessible macros. * The number of bytes required to express this uv in UTF-8, for just those @@ -358,6 +376,39 @@ encoded as UTF-8. C is a native (ASCII or EBCDIC) code point if less than */ #define UVCHR_SKIP(uv) ( UVCHR_IS_INVARIANT(uv) ? 1 : __BASE_UNI_SKIP(uv)) +#define UTF_MIN_START_BYTE \ + ((UTF_CONTINUATION_MARK >> UTF_ACCUMULATION_SHIFT) | UTF_START_MARK(2)) + +/* Is the byte 'c' the first byte of a multi-byte UTF8-8 encoded sequence? + * This excludes invariants (they are single-byte). It also excludes the + * illegal overlong sequences that begin with C0 and C1 on ASCII platforms, and + * C0-C4 I8 start bytes on EBCDIC ones. On EBCDIC E0 can't start a + * non-overlong sequence, so we define a base macro and for those platforms, + * extend it to also exclude E0 */ +#define UTF8_IS_START_base(c) (__ASSERT_(FITS_IN_8_BITS(c)) \ + (NATIVE_UTF8_TO_I8(c) >= UTF_MIN_START_BYTE)) +#ifdef EBCDIC +# define UTF8_IS_START(c) \ + (UTF8_IS_START_base(c) && (c) != I8_TO_NATIVE_UTF8(0xE0)) +#else +# define UTF8_IS_START(c) UTF8_IS_START_base(c) +#endif + +#define UTF_MIN_ABOVE_LATIN1_BYTE \ + ((0x100 >> UTF_ACCUMULATION_SHIFT) | UTF_START_MARK(2)) + +/* Is the UTF8-encoded byte 'c' the first byte of a sequence of bytes that + * represent a code point > 255? */ +#define UTF8_IS_ABOVE_LATIN1(c) (__ASSERT_(FITS_IN_8_BITS(c)) \ + (NATIVE_UTF8_TO_I8(c) >= UTF_MIN_ABOVE_LATIN1_BYTE)) + +/* Is the UTF8-encoded byte 'c' the first byte of a two byte sequence? Use + * UTF8_IS_NEXT_CHAR_DOWNGRADEABLE() instead if the input isn't known to + * be well-formed. */ +#define UTF8_IS_DOWNGRADEABLE_START(c) (__ASSERT_(FITS_IN_8_BITS(c)) \ + inRANGE(NATIVE_UTF8_TO_I8(c), \ + UTF_MIN_START_BYTE, UTF_MIN_ABOVE_LATIN1_BYTE - 1)) + /* The largest code point representable by two UTF-8 bytes on this platform. * As explained in the comments for __COMMON_UNI_SKIP, 32 start bytes with * UTF_ACCUMULATION_SHIFT bits of information each */ @@ -368,18 +419,26 @@ encoded as UTF-8. C is a native (ASCII or EBCDIC) code point if less than * continuation byte */ #define MAX_PORTABLE_UTF8_TWO_BYTE (32 * (1U << 5) - 1) -/* The maximum number of UTF-8 bytes a single Unicode character can - * uppercase/lowercase/fold into. Unicode guarantees that the maximum - * expansion is UTF8_MAX_FOLD_CHAR_EXPAND characters, but any above-Unicode - * code point will fold to itself, so we only have to look at the expansion of - * the maximum Unicode code point. But this number may be less than the space - * occupied by a very large code point under Perl's extended UTF-8. We have to - * make it large enough to fit any single character. (It turns out that ASCII - * and EBCDIC differ in which is larger) */ +/* + +=for apidoc AmnU|STRLEN|UTF8_MAXBYTES_CASE + +The maximum number of UTF-8 bytes a single Unicode character can +uppercase/lowercase/titlecase/fold into. + +=cut + + * Unicode guarantees that the maximum expansion is UTF8_MAX_FOLD_CHAR_EXPAND + * characters, but any above-Unicode code point will fold to itself, so we only + * have to look at the expansion of the maximum Unicode code point. But this + * number may be less than the space occupied by a very large code point under + * Perl's extended UTF-8. We have to make it large enough to fit any single + * character. (It turns out that ASCII and EBCDIC differ in which is larger) + * +=cut +*/ #define UTF8_MAXBYTES_CASE \ - (UTF8_MAXBYTES >= (UTF8_MAX_FOLD_CHAR_EXPAND * OFFUNISKIP(0x10FFFF)) \ - ? UTF8_MAXBYTES \ - : (UTF8_MAX_FOLD_CHAR_EXPAND * OFFUNISKIP(0x10FFFF))) + MAX(UTF8_MAXBYTES, UTF8_MAX_FOLD_CHAR_EXPAND * OFFUNISKIP(0x10FFFF)) /* 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 @@ -402,7 +461,7 @@ encoded as UTF-8. C is a native (ASCII or EBCDIC) code point if less than * UTF-8 encoded character that mark it as a start byte and give the number of * bytes that comprise the character. 'len' is the number of bytes in the * multi-byte sequence. */ -#define UTF_START_MARK(len) (((len) > 7) ? 0xFF : (0xFF & (0xFE << (7-(len))))) +#define UTF_START_MARK(len) (((len) > 7) ? 0xFF : ((U8) (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. 'len' is the number of bytes in the @@ -415,21 +474,16 @@ encoded as UTF-8. C is a native (ASCII or EBCDIC) code point if less than * that this is asymmetric on EBCDIC platforms, in that the 'new' parameter is * the UTF-EBCDIC byte, whereas the 'old' parameter is a Unicode (not EBCDIC) * code point in process of being generated */ -#define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT) \ - | ((NATIVE_UTF8_TO_I8((U8)new)) \ +#define UTF8_ACCUMULATE(old, new) (__ASSERT_(FITS_IN_8_BITS(new)) \ + ((old) << UTF_ACCUMULATION_SHIFT) \ + | ((NATIVE_UTF8_TO_I8(new)) \ & UTF_CONTINUATION_MASK)) -/* If a value is anded with this, 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)) - /* 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))) +#define UTF8_IS_NEXT_CHAR_DOWNGRADEABLE(s, e) \ + ( UTF8_IS_DOWNGRADEABLE_START(*(s)) \ + && ( (e) - (s) > 1) \ + && UTF8_IS_CONTINUATION(*((s)+1))) /* Number of bytes a code point occupies in UTF-8. */ #define NATIVE_SKIP(uv) UVCHR_SKIP(uv) @@ -464,8 +518,10 @@ encoded as UTF-8. C is a native (ASCII or EBCDIC) code point if less than * Note that the result can be larger than 255 if the input character is not * downgradable */ #define TWO_BYTE_UTF8_TO_NATIVE(HI, LO) \ - ( __ASSERT_(PL_utf8skip[HI] == 2) \ - __ASSERT_(UTF8_IS_CONTINUATION(LO)) \ + (__ASSERT_(FITS_IN_8_BITS(HI)) \ + __ASSERT_(FITS_IN_8_BITS(LO)) \ + __ASSERT_(PL_utf8skip[HI] == 2) \ + __ASSERT_(UTF8_IS_CONTINUATION(LO)) \ UNI_TO_NATIVE(UTF8_ACCUMULATE((NATIVE_UTF8_TO_I8(HI) & UTF_START_MASK(2)), \ (LO)))) @@ -475,31 +531,111 @@ encoded as UTF-8. C is a native (ASCII or EBCDIC) code point if less than /* =for apidoc Am|STRLEN|UTF8SKIP|char* s -returns the number of bytes in the UTF-8 encoded character whose first (perhaps -only) byte is pointed to by C. +returns the number of bytes a non-malformed UTF-8 encoded character whose first +(perhaps only) byte is pointed to by C. + +If there is a possibility of malformed input, use instead: + +=over + +=item L> if you know the maximum ending pointer in the +buffer pointed to by C; or + +=item L> if you don't know it. + +=back + +It is better to restructure your code so the end pointer is passed down so that +you know what it actually is at the point of this call, but if that isn't +possible, L> can minimize the chance of accessing beyond the end +of the input buffer. =cut */ #define UTF8SKIP(s) PL_utf8skip[*(const U8*)(s)] + +/* +=for apidoc Am|STRLEN|UTF8_SKIP|char* s +This is a synonym for L> + +=cut +*/ + #define UTF8_SKIP(s) UTF8SKIP(s) +/* +=for apidoc Am|STRLEN|UTF8_CHK_SKIP|char* s + +This is a safer version of L>, but still not as safe as +L>. This version doesn't blindly assume that the input +string pointed to by C is well-formed, but verifies that there isn't a NUL +terminating character before the expected end of the next character in C. +The length C returns stops just before any such NUL. + +Perl tends to add NULs, as an insurance policy, after the end of strings in +SV's, so it is likely that using this macro will prevent inadvertent reading +beyond the end of the input buffer, even if it is malformed UTF-8. + +This macro is intended to be used by XS modules where the inputs could be +malformed, and it isn't feasible to restructure to use the safer +L>, for example when interfacing with a C library. + +=cut +*/ + +#define UTF8_CHK_SKIP(s) \ + (s[0] == '\0' ? 1 : MIN(UTF8SKIP(s), \ + my_strnlen((char *) (s), UTF8SKIP(s)))) +/* + +=for apidoc Am|STRLEN|UTF8_SAFE_SKIP|char* s|char* e +returns 0 if S= e>>; otherwise returns the number of bytes in the +UTF-8 encoded character whose first byte is pointed to by C. But it never +returns beyond C. On DEBUGGING builds, it asserts that S= e>>. + +=cut + */ +#define UTF8_SAFE_SKIP(s, e) (__ASSERT_((e) >= (s)) \ + ((e) - (s)) <= 0 \ + ? 0 \ + : MIN(((e) - (s)), UTF8_SKIP(s))) + /* Most code that says 'UNI_' really means the native value for code points up * through 255 */ #define UNI_IS_INVARIANT(cp) UVCHR_IS_INVARIANT(cp) -/* Is the byte 'c' the same character when encoded in UTF-8 as when not. This - * works on both UTF-8 encoded strings and non-encoded, as it returns TRUE in - * each for the exact same set of bit patterns. It is valid on a subset of - * what UVCHR_IS_INVARIANT is valid on, so can just use that; and the compiler - * should optimize out anything extraneous given the implementation of the - * latter. The |0 makes sure this isn't mistakenly called with a ptr argument. - * */ +/* +=for apidoc Am|bool|UTF8_IS_INVARIANT|char c + +Evaluates to 1 if the byte C represents the same character when encoded in +UTF-8 as when not; otherwise evaluates to 0. UTF-8 invariant characters can be +copied as-is when converting to/from UTF-8, saving time. + +In spite of the name, this macro gives the correct result if the input string +from which C comes is not encoded in UTF-8. + +See C> for checking if a UV is invariant. + +=cut + +The reason it works on both UTF-8 encoded strings and non-UTF-8 encoded, is +that it returns TRUE in each for the exact same set of bit patterns. It is +valid on a subset of what UVCHR_IS_INVARIANT is valid on, so can just use that; +and the compiler should optimize out anything extraneous given the +implementation of the latter. The |0 makes sure this isn't mistakenly called +with a ptr argument. +*/ #define UTF8_IS_INVARIANT(c) UVCHR_IS_INVARIANT((c) | 0) /* Like the above, but its name implies a non-UTF8 input, which as the comments * above show, doesn't matter as to its implementation */ #define NATIVE_BYTE_IS_INVARIANT(c) UVCHR_IS_INVARIANT(c) +/* Misleadingly named: is the UTF8-encoded byte 'c' part of a variant sequence + * in UTF-8? This is the inverse of UTF8_IS_INVARIANT. */ +#define UTF8_IS_CONTINUED(c) (__ASSERT_(FITS_IN_8_BITS(c)) \ + (! UTF8_IS_INVARIANT(c))) + /* The macros in the next 4 sets are used to generate the two utf8 or utfebcdic * bytes from an ordinal that is known to fit into exactly two (not one) bytes; * it must be less than 0x3FF to work across both encodings. */ @@ -556,20 +692,22 @@ only) byte is pointed to by C. * 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 isWORDCHAR_lazy_if(p,UTF) ((IN_BYTES || (!UTF)) \ - ? isWORDCHAR(*(p)) \ - : isWORDCHAR_utf8((const U8*)p)) -#define isALNUM_lazy_if(p,UTF) isWORDCHAR_lazy_if(p,UTF) +#define isIDFIRST_lazy_if_safe(p, e, UTF) \ + ((IN_BYTES || !UTF) \ + ? isIDFIRST(*(p)) \ + : isIDFIRST_utf8_safe(p, e)) +#define isWORDCHAR_lazy_if_safe(p, e, UTF) \ + ((IN_BYTES || !UTF) \ + ? isWORDCHAR(*(p)) \ + : isWORDCHAR_utf8_safe((U8 *) p, (U8 *) e)) +#define isALNUM_lazy_if_safe(p, e, UTF) isWORDCHAR_lazy_if_safe(p, e, UTF) #define UTF8_MAXLEN UTF8_MAXBYTES /* A Unicode character can fold to up to 3 characters */ #define UTF8_MAX_FOLD_CHAR_EXPAND 3 -#define IN_BYTES (CopHINTS_get(PL_curcop) & HINT_BYTES) +#define IN_BYTES UNLIKELY(CopHINTS_get(PL_curcop) & HINT_BYTES) /* @@ -588,54 +726,82 @@ case any call to string overloading updates the internal UTF-8 encoding flag. * Is so within 'feature unicode_strings' or 'locale :not_characters', and not * within 'use bytes'. UTF-8 locales are not tested for here, but perhaps * could be */ -#define IN_UNI_8_BIT \ - (((CopHINTS_get(PL_curcop) & (HINT_UNI_8_BIT)) \ - || (CopHINTS_get(PL_curcop) & HINT_LOCALE_PARTIAL \ - /* -1 below is for :not_characters */ \ - && _is_in_locale_category(FALSE, -1))) \ - && ! IN_BYTES) +#define IN_UNI_8_BIT \ + (( ( (CopHINTS_get(PL_curcop) & HINT_UNI_8_BIT)) \ + || ( CopHINTS_get(PL_curcop) & HINT_LOCALE_PARTIAL \ + /* -1 below is for :not_characters */ \ + && _is_in_locale_category(FALSE, -1))) \ + && (! IN_BYTES)) #define UTF8_ALLOW_EMPTY 0x0001 /* Allow a zero length string */ +#define UTF8_GOT_EMPTY UTF8_ALLOW_EMPTY /* Allow first byte to be a continuation byte */ #define UTF8_ALLOW_CONTINUATION 0x0002 +#define UTF8_GOT_CONTINUATION UTF8_ALLOW_CONTINUATION -/* Allow second... bytes to be non-continuation bytes */ +/* Unexpected non-continuation byte */ #define UTF8_ALLOW_NON_CONTINUATION 0x0004 +#define UTF8_GOT_NON_CONTINUATION UTF8_ALLOW_NON_CONTINUATION /* expecting more bytes than were available in the string */ #define UTF8_ALLOW_SHORT 0x0008 +#define UTF8_GOT_SHORT UTF8_ALLOW_SHORT -/* Overlong sequence; i.e., the code point can be specified in fewer bytes. */ +/* Overlong sequence; i.e., the code point can be specified in fewer bytes. + * First one will convert the overlong to the REPLACEMENT CHARACTER; second + * will return what the overlong evaluates to */ #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, which only - * went up to 2 ** 31 - 1. Note that these all overflow a signed 32-bit word, - * The first byte of these code points is FE or FF on ASCII platforms. If the - * first byte is FF, it will overflow a 32-bit word. */ -#define UTF8_DISALLOW_ABOVE_31_BIT 0x0800 -#define UTF8_WARN_ABOVE_31_BIT 0x1000 - -/* For back compat, these old names are misleading for UTF_EBCDIC */ -#define UTF8_DISALLOW_FE_FF UTF8_DISALLOW_ABOVE_31_BIT -#define UTF8_WARN_FE_FF UTF8_WARN_ABOVE_31_BIT - -#define UTF8_CHECK_ONLY 0x2000 +#define UTF8_ALLOW_LONG_AND_ITS_VALUE (UTF8_ALLOW_LONG|0x0020) +#define UTF8_GOT_LONG UTF8_ALLOW_LONG + +#define UTF8_ALLOW_OVERFLOW 0x0080 +#define UTF8_GOT_OVERFLOW UTF8_ALLOW_OVERFLOW + +#define UTF8_DISALLOW_SURROGATE 0x0100 /* Unicode surrogates */ +#define UTF8_GOT_SURROGATE UTF8_DISALLOW_SURROGATE +#define UTF8_WARN_SURROGATE 0x0200 + +/* Unicode non-character code points */ +#define UTF8_DISALLOW_NONCHAR 0x0400 +#define UTF8_GOT_NONCHAR UTF8_DISALLOW_NONCHAR +#define UTF8_WARN_NONCHAR 0x0800 + +/* Super-set of Unicode: code points above the legal max */ +#define UTF8_DISALLOW_SUPER 0x1000 +#define UTF8_GOT_SUPER UTF8_DISALLOW_SUPER +#define UTF8_WARN_SUPER 0x2000 + +/* The original UTF-8 standard did not define UTF-8 with start bytes of 0xFE or + * 0xFF, though UTF-EBCDIC did. This allowed both versions to represent code + * points up to 2 ** 31 - 1. Perl extends UTF-8 so that 0xFE and 0xFF are + * usable on ASCII platforms, and 0xFF means something different than + * UTF-EBCDIC defines. These changes allow code points of 64 bits (actually + * somewhat more) to be represented on both platforms. But these are Perl + * extensions, and not likely to be interchangeable with other languages. Note + * that on ASCII platforms, FE overflows a signed 32-bit word, and FF an + * unsigned one. */ +#define UTF8_DISALLOW_PERL_EXTENDED 0x4000 +#define UTF8_GOT_PERL_EXTENDED UTF8_DISALLOW_PERL_EXTENDED +#define UTF8_WARN_PERL_EXTENDED 0x8000 + +/* For back compat, these old names are misleading for overlongs and + * UTF_EBCDIC. */ +#define UTF8_DISALLOW_ABOVE_31_BIT UTF8_DISALLOW_PERL_EXTENDED +#define UTF8_GOT_ABOVE_31_BIT UTF8_GOT_PERL_EXTENDED +#define UTF8_WARN_ABOVE_31_BIT UTF8_WARN_PERL_EXTENDED +#define UTF8_DISALLOW_FE_FF UTF8_DISALLOW_PERL_EXTENDED +#define UTF8_WARN_FE_FF UTF8_WARN_PERL_EXTENDED + +#define UTF8_CHECK_ONLY 0x10000 +#define _UTF8_NO_CONFIDENCE_IN_CURLEN 0x20000 /* Internal core use only */ /* 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_FE_FF 0 #define UTF8_ALLOW_SURROGATE 0 /* C9 refers to Unicode Corrigendum #9: allows but discourages non-chars */ @@ -648,14 +814,20 @@ case any call to string overloading updates the internal UTF-8 encoding flag. #define UTF8_WARN_ILLEGAL_INTERCHANGE \ (UTF8_WARN_ILLEGAL_C9_INTERCHANGE|UTF8_WARN_NONCHAR) -#define UTF8_ALLOW_ANY \ - (~( UTF8_DISALLOW_ILLEGAL_INTERCHANGE|UTF8_DISALLOW_ABOVE_31_BIT \ - |UTF8_WARN_ILLEGAL_INTERCHANGE|UTF8_WARN_ABOVE_31_BIT)) -#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) +/* This is typically used for code that processes UTF-8 input and doesn't want + * to have to deal with any malformations that might be present. All such will + * be safely replaced by the REPLACEMENT CHARACTER, unless other flags + * overriding this are also present. */ +#define UTF8_ALLOW_ANY ( UTF8_ALLOW_CONTINUATION \ + |UTF8_ALLOW_NON_CONTINUATION \ + |UTF8_ALLOW_SHORT \ + |UTF8_ALLOW_LONG \ + |UTF8_ALLOW_OVERFLOW) + +/* Accept any Perl-extended UTF-8 that evaluates to any UV on the platform, but + * not any malformed. This is the default. */ +#define UTF8_ALLOW_ANYUV 0 +#define UTF8_ALLOW_DEFAULT UTF8_ALLOW_ANYUV /* =for apidoc Am|bool|UTF8_IS_SURROGATE|const U8 *s|const U8 *e @@ -673,6 +845,8 @@ point's representation. #define UTF8_IS_REPLACEMENT(s, send) is_REPLACEMENT_utf8_safe(s,send) +#define MAX_LEGAL_CP ((UV)IV_MAX) + /* =for apidoc Am|bool|UTF8_IS_SUPER|const U8 *s|const U8 *e @@ -689,7 +863,7 @@ represent a code point that cannot fit in a UV on the current platform. Hence this macro can give different results when run on a 64-bit word machine than on one with a 32-bit word size. -Note that it is deprecated to have code points that are larger than what can +Note that it is illegal to have code points that are larger than what can fit in an IV on the current machine. =cut @@ -704,16 +878,16 @@ fit in an IV on the current machine. (( LIKELY((e) > (s) + 4) \ && NATIVE_UTF8_TO_I8(*(s)) >= 0xF9 \ && ( NATIVE_UTF8_TO_I8(*(s)) > 0xF9 \ - || (NATIVE_UTF8_TO_I8(*(s) + 1) >= 0xA2)) \ + || (NATIVE_UTF8_TO_I8(*((s) + 1)) >= 0xA2)) \ && LIKELY((s) + UTF8SKIP(s) <= (e))) \ - ? _is_utf8_char_slow(s, UTF8SKIP(s)) : 0) + ? is_utf8_char_helper(s, s + UTF8SKIP(s), 0) : 0) #else # define UTF8_IS_SUPER(s, e) \ (( LIKELY((e) > (s) + 3) \ && (*(U8*) (s)) >= 0xF4 \ && ((*(U8*) (s)) > 0xF4 || (*((U8*) (s) + 1) >= 0x90))\ && LIKELY((s) + UTF8SKIP(s) <= (e))) \ - ? _is_utf8_char_slow(s, UTF8SKIP(s)) : 0) + ? is_utf8_char_helper(s, s + UTF8SKIP(s), 0) : 0) #endif /* These are now machine generated, and the 'given' clause is no longer @@ -730,6 +904,10 @@ of the Unicode non-character code points; otherwise it evaluates to 0. If non-zero, the value gives how many bytes starting at C comprise the code point's representation. +=for apidoc AmnU|UV|UNICODE_REPLACEMENT + +Evaluates to 0xFFFD, the code point of the Unicode REPLACEMENT CHARACTER + =cut */ #define UTF8_IS_NONCHAR(s, e) \ @@ -744,14 +922,26 @@ point's representation. * let's be conservative and do as Unicode says. */ #define PERL_UNICODE_MAX 0x10FFFF -#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_ABOVE_31_BIT 0x0008 /* Above 0x7FFF_FFFF */ -#define UNICODE_DISALLOW_SURROGATE 0x0010 -#define UNICODE_DISALLOW_NONCHAR 0x0020 -#define UNICODE_DISALLOW_SUPER 0x0040 -#define UNICODE_DISALLOW_ABOVE_31_BIT 0x0080 +#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_PERL_EXTENDED 0x0008 /* Above 0x7FFF_FFFF */ +#define UNICODE_WARN_ABOVE_31_BIT UNICODE_WARN_PERL_EXTENDED +#define UNICODE_DISALLOW_SURROGATE 0x0010 +#define UNICODE_DISALLOW_NONCHAR 0x0020 +#define UNICODE_DISALLOW_SUPER 0x0040 +#define UNICODE_DISALLOW_PERL_EXTENDED 0x0080 + +#ifdef PERL_CORE +# define UNICODE_ALLOW_ABOVE_IV_MAX 0x0100 +#endif +#define UNICODE_DISALLOW_ABOVE_31_BIT UNICODE_DISALLOW_PERL_EXTENDED + +#define UNICODE_GOT_SURROGATE UNICODE_DISALLOW_SURROGATE +#define UNICODE_GOT_NONCHAR UNICODE_DISALLOW_NONCHAR +#define UNICODE_GOT_SUPER UNICODE_DISALLOW_SUPER +#define UNICODE_GOT_PERL_EXTENDED UNICODE_DISALLOW_PERL_EXTENDED + #define UNICODE_WARN_ILLEGAL_C9_INTERCHANGE \ (UNICODE_WARN_SURROGATE|UNICODE_WARN_SUPER) #define UNICODE_WARN_ILLEGAL_INTERCHANGE \ @@ -790,7 +980,6 @@ point's representation. && UNICODE_IS_END_PLANE_NONCHAR_GIVEN_NOT_SUPER(uv))) #define UNICODE_IS_SUPER(uv) ((UV) (uv) > PERL_UNICODE_MAX) -#define UNICODE_IS_ABOVE_31_BIT(uv) ((UV) (uv) > 0x7FFFFFFF) #define LATIN_SMALL_LETTER_SHARP_S LATIN_SMALL_LETTER_SHARP_S_NATIVE #define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS \ @@ -820,7 +1009,13 @@ point's representation. #define UNI_DISPLAY_ISPRINT 0x0001 #define UNI_DISPLAY_BACKSLASH 0x0002 -#define UNI_DISPLAY_QQ (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH) +#define UNI_DISPLAY_BACKSPACE 0x0004 /* Allow \b when also + UNI_DISPLAY_BACKSLASH */ +#define UNI_DISPLAY_QQ (UNI_DISPLAY_ISPRINT \ + |UNI_DISPLAY_BACKSLASH \ + |UNI_DISPLAY_BACKSPACE) + +/* Character classes could also allow \b, but not patterns in general */ #define UNI_DISPLAY_REGEX (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH) #define ANYOF_FOLD_SHARP_S(node, input, end) \ @@ -832,94 +1027,54 @@ point's representation. #define SHARP_S_SKIP 2 -/* If you want to exclude surrogates, and beyond legal Unicode, see the blame - * log for earlier versions which gave details for these */ - -/* A helper macro for isUTF8_CHAR, so use that one, and not this one. This is - * retained solely for backwards compatibility and may be deprecated and - * removed in a future Perl version. - * - * regen/regcharclass.pl generates is_UTF8_CHAR_utf8() macros for up to these - * number of bytes. So this has to be coordinated with that file */ -#ifdef EBCDIC -# define IS_UTF8_CHAR_FAST(n) ((n) <= 3) -#else -# define IS_UTF8_CHAR_FAST(n) ((n) <= 4) -#endif - -#ifndef EBCDIC -/* A helper macro for isUTF8_CHAR, so use that one instead of this. This was - * generated by regen/regcharclass.pl, and then moved here. Then it was - * hand-edited to add some LIKELY() calls, presuming that malformations are - * unlikely. The lines that generated it were then commented out. This was - * done because it takes on the order of 10 minutes to generate, and is never - * going to change, unless the generated code is improved, and figuring out - * there the LIKELYs would be hard. - * - * The EBCDIC versions have been cut to not cover all of legal Unicode, - * otherwise they take too long to generate; besides there is a separate one - * for each code page, so they are in regcharclass.h instead of here */ -/* - UTF8_CHAR: Matches legal UTF-8 encoded characters from 2 through 4 bytes - - 0x80 - 0x1FFFFF -*/ -/*** GENERATED CODE ***/ -#define is_UTF8_CHAR_utf8_no_length_checks(s) \ -( ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) ? \ - ( LIKELY( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 ) \ -: ( 0xE0 == ((U8*)s)[0] ) ? \ - ( LIKELY( ( ( ((U8*)s)[1] & 0xE0 ) == 0xA0 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ -: ( 0xE1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xEF ) ? \ - ( LIKELY( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ -: ( 0xF0 == ((U8*)s)[0] ) ? \ - ( LIKELY( ( ( 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 ) && LIKELY( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ) && LIKELY( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) && LIKELY( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 ) -#endif +#define is_utf8_char_buf(buf, buf_end) isUTF8_CHAR(buf, buf_end) +#define bytes_from_utf8(s, lenp, is_utf8p) \ + bytes_from_utf8_loc(s, lenp, is_utf8p, 0) /* -=for apidoc Am|STRLEN|isUTF8_CHAR|const U8 *s|const U8 *e +=for apidoc Am|STRLEN|isUTF8_CHAR_flags|const U8 *s|const U8 *e| const U32 flags Evaluates to non-zero if the first few bytes of the string starting at C and -looking no further than S> are well-formed UTF-8 that represents some -code point; otherwise it evaluates to 0. If non-zero, the value gives how many -many bytes starting at C comprise the code point's representation. +looking no further than S> are well-formed UTF-8, as extended by Perl, +that represents some code point, subject to the restrictions given by C; +otherwise it evaluates to 0. If non-zero, the value gives how many bytes +starting at C comprise the code point's representation. Any bytes remaining +before C, but beyond the ones needed to form the first code point in C, +are not examined. -The code point can be any that will fit in a UV on this machine, using Perl's -extension to official UTF-8 to represent those higher than the Unicode maximum -of 0x10FFFF. That means that this macro is used to efficiently decide if the -next few bytes in C is legal UTF-8 for a single character. Use -L(), L(), and -L() to check entire strings. +If C is 0, this gives the same results as C>; +if C is C, this gives the same results +as C>; +and if C is C, this gives +the same results as C>. +Otherwise C may be any combination of the C> flags +understood by C>, with the same meanings. -Note that it is deprecated to use code points higher than what will fit in an -IV. This macro does not raise any warnings for such code points, treating them -as valid. +The three alternative macros are for the most commonly needed validations; they +are likely to run somewhat faster than this more general one, as they can be +inlined into your code. -Note also that a UTF-8 INVARIANT character (i.e. ASCII on non-EBCDIC machines) -is a valid UTF-8 character. +Use L, L, and +L to check entire strings. =cut */ -#define isUTF8_CHAR(s, e) (UNLIKELY((e) <= (s)) \ - ? 0 \ - : (UTF8_IS_INVARIANT(*s)) \ - ? 1 \ - : UNLIKELY(((e) - (s)) < UTF8SKIP(s)) \ - ? 0 \ - : LIKELY(IS_UTF8_CHAR_FAST(UTF8SKIP(s))) \ - ? is_UTF8_CHAR_utf8_no_length_checks(s) \ - : _is_utf8_char_slow(s, UTF8SKIP(s))) - -#define is_utf8_char_buf(buf, buf_end) isUTF8_CHAR(buf, buf_end) +#define isUTF8_CHAR_flags(s, e, flags) \ + (UNLIKELY((e) <= (s)) \ + ? 0 \ + : (UTF8_IS_INVARIANT(*s)) \ + ? 1 \ + : UNLIKELY(((e) - (s)) < UTF8SKIP(s)) \ + ? 0 \ + : is_utf8_char_helper(s, e, flags)) /* Do not use; should be deprecated. Use isUTF8_CHAR() instead; this is * retained solely for backwards compatibility */ #define IS_UTF8_CHAR(p, n) (isUTF8_CHAR(p, (p) + (n)) == n) -#endif /* H_UTF8 */ +#endif /* PERL_UTF8_H_ */ /* * ex: set ts=8 sts=4 sw=4 et: