X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/d9f92374c5f4b19ed46c29c6710922b80429de59..54db7d57c29c9259228a6a4176caa32e391c6d0b:/utf8.h diff --git a/utf8.h b/utf8.h index a6b2127..d3b55ee 100644 --- a/utf8.h +++ b/utf8.h @@ -62,13 +62,6 @@ #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)) @@ -270,6 +263,10 @@ Perl's extended UTF-8 means we can have start bytes up to FF. #error UTF8_MAXBYTES must be at least 12 #endif +/* ^? is defined to be DEL on ASCII systems. See the definition of toCTRL() + * for more */ +#define QUESTION_MARK_CTRL DEL_NATIVE + #define MAX_UTF8_TWO_BYTE 0x7FF #define UTF8_MAXBYTES_CASE UTF8_MAXBYTES @@ -418,8 +415,11 @@ Perl's extended UTF-8 means we can have start bytes up to FF. #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) + (((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 */ @@ -485,7 +485,9 @@ Perl's extended UTF-8 means we can have start bytes up to FF. * 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 - */ + * + * BE AWARE that this test doesn't rule out malformed code points, in + * particular overlongs */ #ifdef EBCDIC /* Both versions assume well-formed UTF8 */ # define UTF8_IS_SUPER(s) (NATIVE_UTF8_TO_I8(* (U8*) (s)) >= 0xF9 \ && (NATIVE_UTF8_TO_I8(* (U8*) (s)) > 0xF9 \ @@ -575,14 +577,18 @@ Perl's extended UTF-8 means we can have start bytes up to FF. (ANYOF_NONBITMAP(node)) && \ (ANYOF_FLAGS(node) & ANYOF_LOC_NONBITMAP_FOLD) && \ ((end) > (input) + 1) && \ - toFOLD((input)[0]) == 's' && \ - toFOLD((input)[1]) == 's') + isALPHA_FOLD_EQ((input)[0], 's')) + #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 */ -/* regen/regcharclass.pl generates is_UTF8_CHAR_utf8() macros for up to 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) @@ -591,51 +597,64 @@ Perl's extended UTF-8 means we can have start bytes up to FF. #endif #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 */ +/* A helper macro for isUTF8_CHAR, so use that one instead of this. 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, unless + * the generated code is improved. + * + * The EBCDIC versions have been cut to not cover all of legal Unicode, so + * don't take too long to generate, and there is a separate one for each code + * page, so they are in regcharclass.h instead of here */ /* - UTF8_CHAR: Matches utf8 from 1 to 4 bytes + UTF8_CHAR: Matches legal UTF-8 encoded characters from 2 through 4 bytes - 0x0 - 0x1FFFFF + 0x80 - 0x1FFFFF */ /*** 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 )\ -: ((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 )\ -: ((e)-(s) > 1) ? \ - ( ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) ? 1 \ - : ( ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) && ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ) ? 2 : 0 )\ -: ((e)-(s) > 0) ? \ - ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) \ -: 0 ) +#define is_UTF8_CHAR_utf8_no_length_checks(s) \ +( ( 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 ) #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) (is_UTF8_CHAR_utf8_safe(p, (p) + (n)) == n) +/* +=head1 Unicode Support + +=for apidoc Am|STRLEN|isUTF8_CHAR|const U8 *s|const U8 *e + +Returns the number of bytes beginning at C which form a legal UTF-8 (or +UTF-EBCDIC) encoded character, looking no further than C bytes into +C. Returns 0 if the sequence starting at C through C is not +well-formed UTF-8 + +Note that an INVARIANT character (i.e. ASCII on non-EBCDIC +machines) is a valid UTF-8 character. + +=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, e)) + +#define is_utf8_char_buf(buf, buf_end) isUTF8_CHAR(buf, buf_end) + +/* 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 */