X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/feeab5a94c530ce7c446d29e3616565c85a50a35..7d2b61dd6d5e3e16130e52e4f1549c2a79196700:/handy.h diff --git a/handy.h b/handy.h index 5636bcc..26d7366 100644 --- a/handy.h +++ b/handy.h @@ -8,6 +8,9 @@ * */ +#ifndef HANDY_H /* Guard against nested #inclusion */ +#define HANDY_H + #if !defined(__STDC__) #ifdef NULL #undef NULL @@ -109,11 +112,10 @@ Null SV pointer. (No longer available when C is defined.) # define HAS_BOOL 1 #endif -/* a simple (bool) cast may not do the right thing: if bool is defined - * as char for example, then the cast from int is implementation-defined - * (bool)!!(cbool) in a ternary triggers a bug in xlc on AIX - */ - +/* cast-to-bool. A simple (bool) cast may not do the right thing: if bool is + * defined as char for example, then the cast from int is + * implementation-defined (bool)!!(cbool) in a ternary triggers a bug in xlc on + * AIX */ #define cBOOL(cbool) ((cbool) ? (bool)1 : (bool)0) /* Try to figure out __func__ or __FUNCTION__ equivalent, if any. @@ -339,12 +341,13 @@ string/length pair. =cut */ -/* concatenating with "" ensures that only literal strings are accepted as argument */ +/* concatenating with "" ensures that only literal strings are accepted as + * argument */ #define STR_WITH_LEN(s) ("" s ""), (sizeof(s)-1) -/* note that STR_WITH_LEN() can't be used as argument to macros or functions that - * under some configurations might be macros, which means that it requires the full - * Perl_xxx(aTHX_ ...) form for any API calls where it's used. +/* note that STR_WITH_LEN() can't be used as argument to macros or functions + * that under some configurations might be macros, which means that it requires + * the full Perl_xxx(aTHX_ ...) form for any API calls where it's used. */ /* STR_WITH_LEN() shortcuts */ @@ -470,98 +473,247 @@ C). /* =head1 Character classes -There are three variants for all the functions in this section. The base ones -operate using the character set of the platform Perl is running on. The ones -with an C<_A> suffix operate on the ASCII character set, and the ones with an -C<_L1> suffix operate on the full Latin1 character set. All are unaffected by -locale and by C. - -For ASCII platforms, the base function with no suffix and the one with the -C<_A> suffix are identical. The function with the C<_L1> suffix imposes the -Latin-1 character set onto the platform. That is, the code points that are -ASCII are unaffected, since ASCII is a subset of Latin-1. But the non-ASCII -code points are treated as if they are Latin-1 characters. For example, -C will return true when called with the code point 0xA0, which is -the Latin-1 NO-BREAK SPACE. - -For EBCDIC platforms, the base function with no suffix and the one with the -C<_L1> suffix should be identical, since, as of this writing, the EBCDIC code -pages that Perl knows about all are equivalent to Latin-1. The function that -ends in an C<_A> suffix will not return true unless the specified character also -has an ASCII equivalent. +This section is about functions (really macros) that classify characters +into types, such as punctuation versus alphabetic, etc. Most of these are +analogous to regular expression character classes. (See +L.) There are several variants for +each class. (Not all macros have all variants; each item below lists the +ones valid for it.) None are affected by C, and only the ones +with C in the name are affected by the current locale. + +The base function, e.g., C, takes an octet (either a C or a +C) as input and returns a boolean as to whether or not the character +represented by that octet is (or on non-ASCII platforms, corresponds to) an +ASCII character in the named class based on platform, Unicode, and Perl rules. +If the input is a number that doesn't fit in an octet, FALSE is returned. + +Variant C (e.g., C) is identical to the base function +with no suffix C<"_A">. + +Variant C imposes the Latin-1 (or EBCDIC equivlalent) character set +onto the platform. That is, the code points that are ASCII are unaffected, +since ASCII is a subset of Latin-1. But the non-ASCII code points are treated +as if they are Latin-1 characters. For example, C will return +true when called with the code point 0xDF, which is a word character in both +ASCII and EBCDIC (though it represent different characters in each). + +Variant C is like the C variant, but accepts any UV code +point as input. If the code point is larger than 255, Unicode rules are used +to determine if it is in the character class. For example, +C returns TRUE, since 0x100 is LATIN CAPITAL LETTER A +WITH MACRON in Unicode, and is a word character. + +Variant C is like C, but the input is a pointer to a +(known to be well-formed) UTF-8 encoded string (C or C). The +classification of just the first (possibly multi-byte) character in the string +is tested. + +Variant C is like the C and C variants, but uses +the C library function that gives the named classification instead of +hard-coded rules. For example, C returns the result of calling +C. This means that the result is based on the current locale, which +is what C in the name stands for. FALSE is always returned if the input +won't fit into an octet. + +Variant C is like C, but is defined on any UV. It +returns the same as C for input code points less than 256, and +returns the hard-coded, not-affected-by-locale, Unicode results for larger ones. + +Variant C is like C, but the input is a pointer to a +(known to be well-formed) UTF-8 encoded string (C or C). The +classification of just the first (possibly multi-byte) character in the string +is tested. =for apidoc Am|bool|isALPHA|char ch Returns a boolean indicating whether the specified character is an -alphabetic character in the platform's native character set. +alphabetic character, analogous to C. +See the L for an explanation of variants +C, C, C, C, C, +C, and C. + +=for apidoc Am|bool|isALPHANUMERIC|char ch +Returns a boolean indicating whether the specified character is a either an +alphabetic character or decimal digit, analogous to C. See the L for an explanation of variants -C and C. +C, C, C, +C, C, C, and +C. =for apidoc Am|bool|isASCII|char ch Returns a boolean indicating whether the specified character is one of the 128 -characters in the ASCII character set. On non-ASCII platforms, it is if this +characters in the ASCII character set, analogous to C. +On non-ASCII platforms, it returns TRUE iff this character corresponds to an ASCII character. Variants C and C are identical to C. +See the L for an explanation of variants +C, C, C, C, and +C. Note, however, that some platforms do not have the C +library routine C. In these cases, the variants whose names contain +C are the same as the corresponding ones without. + +=for apidoc Am|bool|isBLANK|char ch +Returns a boolean indicating whether the specified character is a +character considered to be a blank, analogous to C. +See the L for an explanation of variants +C, C, C, C, C, +C, and C. Note, however, that some +platforms do not have the C library routine C. In these cases, the +variants whose names contain C are the same as the corresponding ones +without. + +=for apidoc Am|bool|isCNTRL|char ch +Returns a boolean indicating whether the specified character is a +control character, analogous to C. +See the L for an explanation of variants +C, C, C, C, C, +C, and C +On EBCDIC platforms, you almost always want to use the C variant. =for apidoc Am|bool|isDIGIT|char ch Returns a boolean indicating whether the specified character is a -digit in the platform's native character set. +digit, analogous to C. Variants C and C are identical to C. +See the L for an explanation of variants +C, C, C, C, and +C. + +=for apidoc Am|bool|isGRAPH|char ch +Returns a boolean indicating whether the specified character is a +graphic character, analogous to C. +See the L for an explanation of variants +C, C, C, C, C, +C, and C. =for apidoc Am|bool|isLOWER|char ch Returns a boolean indicating whether the specified character is a -lowercase character in the platform's native character set. +lowercase character, analogous to C. See the L for an explanation of variants -C and C. +C, C, C, C, C, +C, and C. =for apidoc Am|bool|isOCTAL|char ch Returns a boolean indicating whether the specified character is an -octal digit, [0-7] in the platform's native character set. -Variants C and C are identical to C. +octal digit, [0-7]. +The only two variants are C and C; each is identical to +C. + +=for apidoc Am|bool|isPUNCT|char ch +Returns a boolean indicating whether the specified character is a +punctuation character, analogous to C. +Note that the definition of what is punctuation isn't as +straightforward as one might desire. See L for details. +See the L for an explanation of variants +C, C, C, C, C, +C, and C. =for apidoc Am|bool|isSPACE|char ch Returns a boolean indicating whether the specified character is a -whitespace character in the platform's native character set. This is the same -as what C<\s> matches in a regular expression. +whitespace character. This is analogous +to what C matches in a regular expression. Starting in Perl 5.18 +(experimentally), this also matches what C does. +("Experimentally" means that this change may be backed out in 5.20 or 5.22 if +field experience indicates that it was unwise.) Prior to 5.18, only the +locale forms of this macro (the ones with C in their names) matched +precisely what C does. In those releases, the only difference, +in the non-locale variants, was that C did not match a vertical tab. +(See L for a macro that matches a vertical tab in all releases.) See the L for an explanation of variants -C and C. +C, C, C, C, C, +C, and C. + +=for apidoc Am|bool|isPSXSPC|char ch +(short for Posix Space) +Starting in 5.18, this is identical (experimentally) in all its forms to the +corresponding C macros. ("Experimentally" means that this change +may be backed out in 5.20 or 5.22 if field experience indicates that it +was unwise.) +The locale forms of this macro are identical to their corresponding +C forms in all Perl releases. In releases prior to 5.18, the +non-locale forms differ from their C forms only in that the +C forms don't match a Vertical Tab, and the C forms do. +Otherwise they are identical. Thus this macro is analogous to what +C matches in a regular expression. +See the L for an explanation of variants +C, C, C, C, C, +C, and C. =for apidoc Am|bool|isUPPER|char ch Returns a boolean indicating whether the specified character is an -uppercase character in the platform's native character set. +uppercase character, analogous to C. See the L for an explanation of variants -C and C. +C, C, C, C, C, +C, and C. -=for apidoc Am|bool|isWORDCHAR|char ch +=for apidoc Am|bool|isPRINT|char ch Returns a boolean indicating whether the specified character is a -character that is any of: alphabetic, numeric, or an underscore. This is the -same as what C<\w> matches in a regular expression. -C is a synonym provided for backward compatibility. Note that it -does not have the standard C language meaning of alphanumeric, since it matches -an underscore and the standard meaning does not. +printable character, analogous to C. +See the L for an explanation of variants +C, C, C, C, C, +C, and C. + +=for apidoc Am|bool|isWORDCHAR|char ch +Returns a boolean indicating whether the specified character is a character +that is a word character, analogous to what C and C match +in a regular expression. A word character is an alphabetic character, a +decimal digit, a connecting punctuation character (such as an underscore), or +a "mark" character that attaches to one of those (like some sort of accent). +C is a synonym provided for backward compatibility, even though a +word character includes more than the standard C language meaning of +alphanumeric. See the L for an explanation of variants -C and C. +C, C, C, C, +C, C, and C. =for apidoc Am|bool|isXDIGIT|char ch Returns a boolean indicating whether the specified character is a hexadecimal -digit, [0-9A-Fa-f]. Variants C and C are -identical to C. +digit. In the ASCII range these are C<[0-9A-Fa-f]>. Variants C +and C are identical to C. +See the L for an explanation of variants +C, C, C, C, and +C. + +=for apidoc Am|bool|isIDFIRST|char ch +Returns a boolean indicating whether the specified character can be the first +character of an identifier. This is very close to, but not quite the same as +the official Unicode property C. The difference is that this +returns true only if the input character also matches L. +See the L for an explanation of variants +C, C, C, C, +C, C, and C. + +=for apidoc Am|bool|isIDCONT|char ch +Returns a boolean indicating whether the specified character can be the +second or succeeding character of an identifier. This is very close to, but +not quite the same as the official Unicode property C. The +difference is that this returns true only if the input character also matches +L. See the L for an +explanation of variants C, C, C, +C, C, C, and +C. + +=head1 Miscellaneous Functions =for apidoc Am|U8|READ_XDIGIT|char str* -Returns the value of a hex digit and advances the string pointer. +Returns the value of an ASCII-range hex digit and advances the string pointer. Behaviour is only well defined when isXDIGIT(*str) is true. =head1 Character case changing =for apidoc Am|char|toUPPER|char ch -Converts the specified character to uppercase in the platform's native -character set, if possible; otherwise returns the input character itself. +Converts the specified character to uppercase, if possible; otherwise returns +the input character itself. Only ASCII characters are changed. Variant +C is equivalent. =for apidoc Am|char|toLOWER|char ch -Converts the specified character to lowercase in the platform's native -character set, if possible; otherwise returns the input character itself. +Converts the specified character to lowercase, if possible; otherwise returns +the input character itself. Only ASCII characters are changed. Variant +C is equivalent. =cut +XXX Still undocumented isVERTWS_uni and _utf8, and the other toUPPER etc functions + Note that these macros are repeated in Devel::PPPort, so should also be patched there. The file as of this writing is cpan/Devel-PPPort/parts/inc/misc @@ -602,42 +754,116 @@ patched there. The file as of this writing is cpan/Devel-PPPort/parts/inc/misc /* ASCII range only */ #ifdef H_PERL /* If have access to perl.h, lookup in its table */ -/* Character class numbers. For internal core Perl use only. These are used - * in PL_charclass[] and the ones up through the one that corresponds to - * <_HIGHEST_REGCOMP_DOT_H_SYNC> are used by regcomp.h. These use names used - * in l1_char_class_tab.h but their actual definitions are here. If that has a - * name not used here, it won't compile. */ -# define _CC_WORDCHAR 0 -# define _CC_SPACE 1 -# define _CC_DIGIT 2 -# define _CC_ALNUMC 3 -# define _CC_ALPHA 4 -# define _CC_ASCII 5 -# define _CC_CNTRL 6 -# define _CC_GRAPH 7 -# define _CC_LOWER 8 -# define _CC_PRINT 9 -# define _CC_PUNCT 10 -# define _CC_UPPER 11 -# define _CC_XDIGIT 12 -# define _CC_PSXSPC 13 -# define _CC_BLANK 14 -# define _CC_VERTSPACE 15 +/* Character class numbers. For internal core Perl use only. The ones less + * than 32 are used in PL_charclass[] and the ones up through the one that + * corresponds to <_HIGHEST_REGCOMP_DOT_H_SYNC> are used by regcomp.h and + * related files. PL_charclass ones use names used in l1_char_class_tab.h but + * their actual definitions are here. If that file has a name not used here, + * it won't compile. + * + * The first group of these is ordered in what I (khw) estimate to be the + * frequency of their use. This gives a slight edge to exiting a loop earlier + * (in reginclass() in regexec.c) */ +# define _CC_WORDCHAR 0 /* \w and [:word:] */ +# define _CC_DIGIT 1 /* \d and [:digit:] */ +# define _CC_ALPHA 2 /* [:alpha:] */ +# define _CC_LOWER 3 /* [:lower:] */ +# define _CC_UPPER 4 /* [:upper:] */ +# define _CC_PUNCT 5 /* [:punct:] */ +# define _CC_PRINT 6 /* [:print:] */ +# define _CC_ALPHANUMERIC 7 /* [:alnum:] */ +# define _CC_GRAPH 8 /* [:graph:] */ +# define _CC_CASED 9 /* [:lower:] and [:upper:] under /i */ + +#define _FIRST_NON_SWASH_CC 10 +/* The character classes above are implemented with swashes. The second group + * (just below) contains the ones implemented without. These are also sorted + * in rough order of the frequency of their use, except that \v should be last, + * as it isn't a real Posix character class, and some (small) inefficiencies in + * regular expression handling would be introduced by putting it in the middle + * of those that are. Also, cntrl and ascii come after the others as it may be + * useful to group these which have no members that match above Latin1, (or + * above ASCII in the latter case) */ + +# define _CC_SPACE 10 /* \s */ +# define _CC_BLANK 11 /* [:blank:] */ +# define _CC_XDIGIT 12 /* [:xdigit:] */ +# define _CC_PSXSPC 13 /* [:space:] */ +# define _CC_CNTRL 14 /* [:cntrl:] */ +# define _CC_ASCII 15 /* [:ascii:] */ +# define _CC_VERTSPACE 16 /* \v */ + # define _HIGHEST_REGCOMP_DOT_H_SYNC _CC_VERTSPACE -# define _CC_IDFIRST 16 -# define _CC_CHARNAME_CONT 17 -# define _CC_NONLATIN1_FOLD 18 -# define _CC_QUOTEMETA 19 -# define _CC_NON_FINAL_FOLD 20 -# define _CC_IS_IN_SOME_FOLD 21 -/* Unused: 22-31 +/* The members of the third group below do not need to be coordinated with data + * structures in regcomp.[ch] and regexec.c */ +# define _CC_IDFIRST 17 +# define _CC_CHARNAME_CONT 18 +# define _CC_NONLATIN1_FOLD 19 +# define _CC_QUOTEMETA 20 +# define _CC_NON_FINAL_FOLD 21 +# define _CC_IS_IN_SOME_FOLD 22 +# define _CC_BACKSLASH_FOO_LBRACE_IS_META 31 /* temp, see mk_PL_charclass.pl */ +/* Unused: 23-30 * If more bits are needed, one could add a second word for non-64bit * QUAD_IS_INT systems, using some #ifdefs to distinguish between having a 2nd * word or not. The IS_IN_SOME_FOLD bit is the most easily expendable, as it * is used only for optimization (as of this writing), and differs in the * Latin1 range from the ALPHA bit only in two relatively unimportant - * characters: the masculine and feminine ordinal indicators */ + * characters: the masculine and feminine ordinal indicators, so removing it + * would just cause /i regexes which match them to run less efficiently */ + +#if defined(PERL_CORE) || defined(PERL_EXT) +/* An enum version of the character class numbers, to help compilers + * optimize */ +typedef enum { + _CC_ENUM_ALPHA = _CC_ALPHA, + _CC_ENUM_ALPHANUMERIC = _CC_ALPHANUMERIC, + _CC_ENUM_ASCII = _CC_ASCII, + _CC_ENUM_BLANK = _CC_BLANK, + _CC_ENUM_CASED = _CC_CASED, + _CC_ENUM_CNTRL = _CC_CNTRL, + _CC_ENUM_DIGIT = _CC_DIGIT, + _CC_ENUM_GRAPH = _CC_GRAPH, + _CC_ENUM_LOWER = _CC_LOWER, + _CC_ENUM_PRINT = _CC_PRINT, + _CC_ENUM_PSXSPC = _CC_PSXSPC, + _CC_ENUM_PUNCT = _CC_PUNCT, + _CC_ENUM_SPACE = _CC_SPACE, + _CC_ENUM_UPPER = _CC_UPPER, + _CC_ENUM_VERTSPACE = _CC_VERTSPACE, + _CC_ENUM_WORDCHAR = _CC_WORDCHAR, + _CC_ENUM_XDIGIT = _CC_XDIGIT +} _char_class_number; +#endif + +#define POSIX_SWASH_COUNT _FIRST_NON_SWASH_CC +#define POSIX_CC_COUNT (_HIGHEST_REGCOMP_DOT_H_SYNC + 1) + +#if defined(PERL_IN_UTF8_C) || defined(PERL_IN_REGCOMP_C) || defined(PERL_IN_REGEXEC_C) +# if _CC_WORDCHAR != 0 || _CC_DIGIT != 1 || _CC_ALPHA != 2 || _CC_LOWER != 3 \ + || _CC_UPPER != 4 || _CC_PUNCT != 5 || _CC_PRINT != 6 \ + || _CC_ALPHANUMERIC != 7 || _CC_GRAPH != 8 || _CC_CASED != 9 + #error Need to adjust order of swash_property_names[] +# endif + +/* This is declared static in each of the few files that this is #defined for + * to keep them from being publicly accessible. Hence there is a small amount + * of wasted space */ + +static const char* const swash_property_names[] = { + "XPosixWord", + "XPosixDigit", + "XPosixAlpha", + "XPosixLower", + "XPosixUpper", + "XPosixPunct", + "XPosixPrint", + "XPosixAlnum", + "XPosixGraph", + "Cased" +}; +#endif # ifdef DOINIT EXTCONST U32 PL_charclass[] = { @@ -651,7 +877,7 @@ EXTCONST U32 PL_charclass[]; /* The 1U keeps Solaris from griping when shifting sets the uppermost bit */ # define _CC_mask(classnum) (1U << (classnum)) # define _generic_isCC(c, classnum) cBOOL(FITS_IN_8_BITS(c) \ - && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_mask(classnum))) + && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_mask(classnum))) /* The mask for the _A versions of the macros; it just adds in the bit for * ASCII. */ @@ -663,8 +889,8 @@ EXTCONST U32 PL_charclass[]; && ((PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_mask_A(classnum)) \ == _CC_mask_A(classnum))) -# define isALNUMC_A(c) _generic_isCC_A(c, _CC_ALNUMC) # define isALPHA_A(c) _generic_isCC_A(c, _CC_ALPHA) +# define isALPHANUMERIC_A(c) _generic_isCC_A(c, _CC_ALPHANUMERIC) # define isBLANK_A(c) _generic_isCC_A(c, _CC_BLANK) # define isCNTRL_A(c) _generic_isCC_A(c, _CC_CNTRL) # define isDIGIT_A(c) _generic_isCC(c, _CC_DIGIT) @@ -690,8 +916,8 @@ EXTCONST U32 PL_charclass[]; _generic_isCC(c, _CC_IS_IN_SOME_FOLD) #else /* No perl.h. */ # ifdef EBCDIC -# define isALNUMC_A(c) (isASCII(c) && isALNUMC(c)) # define isALPHA_A(c) (isASCII(c) && isALPHA(c)) +# define isALPHANUMERIC_A(c) (isASCII(c) && isALPHANUMERIC(c)) # define isBLANK_A(c) (isASCII(c) && isBLANK(c)) # define isCNTRL_A(c) (isASCII(c) && isCNTRL(c)) # define isDIGIT_A(c) (isASCII(c) && isDIGIT(c)) @@ -706,28 +932,37 @@ EXTCONST U32 PL_charclass[]; # define isWORDCHAR_A(c) (isASCII(c) && isWORDCHAR(c)) # define isXDIGIT_A(c) (isASCII(c) && isXDIGIT(c)) # else /* ASCII platform, no perl.h */ -# define isALNUMC_A(c) (isALPHA_A(c) || isDIGIT_A(c)) # define isALPHA_A(c) (isUPPER_A(c) || isLOWER_A(c)) +# define isALPHANUMERIC_A(c) (isALPHA_A(c) || isDIGIT_A(c)) # define isBLANK_A(c) ((c) == ' ' || (c) == '\t') -# define isCNTRL_A(c) (FITS_IN_8_BITS(c) && ((U8) (c) < ' ' || (c) == 127)) +# define isCNTRL_A(c) (FITS_IN_8_BITS(c) && ((U8) (c) < ' ' || (c) == 127)) # define isDIGIT_A(c) ((c) <= '9' && (c) >= '0') # define isGRAPH_A(c) (isWORDCHAR_A(c) || isPUNCT_A(c)) # define isIDFIRST_A(c) (isALPHA_A(c) || (c) == '_') # define isLOWER_A(c) ((c) >= 'a' && (c) <= 'z') # define isPRINT_A(c) (((c) >= 32 && (c) < 127)) # define isPSXSPC_A(c) (isSPACE_A(c) || (c) == '\v') -# define isPUNCT_A(c) (((c) >= 33 && (c) <= 47) || ((c) >= 58 && (c) <= 64) || ((c) >= 91 && (c) <= 96) || ((c) >= 123 && (c) <= 126)) -# define isSPACE_A(c) ((c) == ' ' || (c) == '\t' || (c) == '\n' || (c) =='\r' || (c) == '\f') +# define isPUNCT_A(c) (((c) >= 33 && (c) <= 47) \ + || ((c) >= 58 && (c) <= 64) \ + || ((c) >= 91 && (c) <= 96) \ + || ((c) >= 123 && (c) <= 126)) +# define isSPACE_A(c) ((c) == ' ' \ + || (c) == '\t' \ + || (c) == '\n' \ + || (c) =='\r' \ + || (c) == '\f') # define isUPPER_A(c) ((c) <= 'Z' && (c) >= 'A') # define isWORDCHAR_A(c) (isALPHA_A(c) || isDIGIT_A(c) || (c) == '_') -# define isXDIGIT_A(c) (isDIGIT_A(c) || ((c) >= 'a' && (c) <= 'f') || ((c) <= 'F' && (c) >= 'A')) +# define isXDIGIT_A(c) (isDIGIT_A(c) \ + || ((c) >= 'a' && (c) <= 'f') \ + || ((c) <= 'F' && (c) >= 'A')) # endif #endif /* ASCII range definitions */ /* Latin1 definitions */ #ifdef H_PERL -# define isALNUMC_L1(c) _generic_isCC(c, _CC_ALNUMC) # define isALPHA_L1(c) _generic_isCC(c, _CC_ALPHA) +# define isALPHANUMERIC_L1(c) _generic_isCC(c, _CC_ALPHANUMERIC) # define isBLANK_L1(c) _generic_isCC(c, _CC_BLANK) /* continuation character for legal NAME in \N{NAME} */ @@ -749,23 +984,19 @@ EXTCONST U32 PL_charclass[]; * >= AA test to speed up ASCII-only tests at the expense of the others */ # define isALPHA_L1(c) (isALPHA(c) || (NATIVE_TO_UNI((U8) c) >= 0xAA \ && ((NATIVE_TO_UNI((U8) c) >= 0xC0 \ - && NATIVE_TO_UNI((U8) c) != 0xD7 && NATIVE_TO_UNI((U8) c) != 0xF7) \ + && NATIVE_TO_UNI((U8) c) != 0xD7 && NATIVE_TO_UNI((U8) c) != 0xF7) \ || NATIVE_TO_UNI((U8) c) == 0xAA \ || NATIVE_TO_UNI((U8) c) == 0xB5 \ || NATIVE_TO_UNI((U8) c) == 0xBA))) -# define isCHARNAME_CONT(c) (isALNUM_L1(c) || (c) == ' ' || (c) == '-' || (c) == '(' || (c) == ')' || (c) == ':' || NATIVE_TO_UNI((U8) c) == 0xA0) +# define isCHARNAME_CONT(c) (isWORDCHAR_L1(c) \ + || (c) == ' ' \ + || (c) == '-' \ + || (c) == '(' \ + || (c) == ')' \ + || (c) == ':' \ + || NATIVE_TO_UNI((U8) c) == 0xA0) #endif -/* Macros for backwards compatibility and for completeness when the ASCII and - * Latin1 values are identical */ -#define isALNUM(c) isWORDCHAR(c) -#define isALNUMU(c) isWORDCHAR_L1(c) -#define isALPHAU(c) isALPHA_L1(c) -#define isDIGIT_L1(c) isDIGIT_A(c) -#define isOCTAL(c) isOCTAL_A(c) -#define isOCTAL_L1(c) isOCTAL_A(c) -#define isXDIGIT_L1(c) isXDIGIT_A(c) - /* Macros that differ between EBCDIC and ASCII. Where C89 defines a function, * that is used in the EBCDIC form, because in EBCDIC we do not do locales: * therefore can use native functions. For those where C89 doesn't define a @@ -773,8 +1004,8 @@ EXTCONST U32 PL_charclass[]; * with Latin1, which the three currently recognized by Perl are. Some libc's * have an isblank(), but it's not guaranteed. */ #ifdef EBCDIC -# define isALNUMC(c) isalnum(c) # define isALPHA(c) isalpha(c) +# define isALPHANUMERIC(c) isalnum(c) # define isBLANK(c) ((c) == ' ' || (c) == '\t' || NATIVE_TO_UNI(c) == 0xA0) # define isCNTRL(c) iscntrl(c) # define isDIGIT(c) isdigit(c) @@ -792,7 +1023,7 @@ EXTCONST U32 PL_charclass[]; # define toLOWER(c) tolower(c) # define toUPPER(c) toupper(c) #else /* Not EBCDIC: ASCII-only matching */ -# define isALNUMC(c) isALNUMC_A(c) /* Mnemonic: "C's alnum" = alpha + digit */ +# define isALPHANUMERIC(c) isALPHANUMERIC_A(c) # define isALPHA(c) isALPHA_A(c) # define isBLANK(c) isBLANK_A(c) # define isCNTRL(c) isCNTRL_A(c) @@ -817,6 +1048,8 @@ EXTCONST U32 PL_charclass[]; # define toUPPER(c) (isLOWER(c) ? (c) - ('a' - 'A') : (c)) #endif +#define toLOWER_A(c) toLOWER(c) +#define toUPPER_A(c) toUPPER(c) /* Use table lookup for speed; return error character for input * out-of-range */ @@ -824,6 +1057,8 @@ EXTCONST U32 PL_charclass[]; ? UNI_TO_NATIVE(PL_latin1_lc[ \ NATIVE_TO_UNI( (U8) (c)) ]) \ : UNICODE_REPLACEMENT) +#define toLOWER_L1(c) toLOWER_LATIN1(c) /* Synonym for consistency */ + /* Modified uc. Is correct uc except for three non-ascii chars which are * all mapped to one of them, and these need special handling; error * character for input out-of-range */ @@ -834,24 +1069,23 @@ EXTCONST U32 PL_charclass[]; #ifdef USE_NEXT_CTYPE -# define isALNUM_LC(c) \ - (NXIsAlNum((unsigned int)(c)) || (char)(c) == '_') -# define isIDFIRST_LC(c) \ - (NXIsAlpha((unsigned int)(c)) || (char)(c) == '_') +# define isALPHANUMERIC_LC(c) NXIsAlNum((unsigned int)(c)) # define isALPHA_LC(c) NXIsAlpha((unsigned int)(c)) # define isASCII_LC(c) isASCII((unsigned int)(c)) # define isBLANK_LC(c) isBLANK((unsigned int)(c)) -# define isSPACE_LC(c) NXIsSpace((unsigned int)(c)) -# define isDIGIT_LC(c) NXIsDigit((unsigned int)(c)) -# define isUPPER_LC(c) NXIsUpper((unsigned int)(c)) -# define isLOWER_LC(c) NXIsLower((unsigned int)(c)) -# define isALNUMC_LC(c) NXIsAlNum((unsigned int)(c)) # define isCNTRL_LC(c) NXIsCntrl((unsigned int)(c)) +# define isDIGIT_LC(c) NXIsDigit((unsigned int)(c)) # define isGRAPH_LC(c) NXIsGraph((unsigned int)(c)) +# define isIDFIRST_LC(c) (NXIsAlpha((unsigned int)(c)) || (char)(c) == '_') +# define isLOWER_LC(c) NXIsLower((unsigned int)(c)) # define isPRINT_LC(c) NXIsPrint((unsigned int)(c)) # define isPUNCT_LC(c) NXIsPunct((unsigned int)(c)) -# define toUPPER_LC(c) NXToUpper((unsigned int)(c)) +# define isSPACE_LC(c) NXIsSpace((unsigned int)(c)) +# define isUPPER_LC(c) NXIsUpper((unsigned int)(c)) +# define isWORDCHAR_LC(c) (NXIsAlNum((unsigned int)(c)) || (char)(c) == '_') +# define isXDIGIT_LC(c) NXIsXDigit((unsigned int)(c)) # define toLOWER_LC(c) NXToLower((unsigned int)(c)) +# define toUPPER_LC(c) NXToUpper((unsigned int)(c)) #else /* !USE_NEXT_CTYPE */ @@ -859,11 +1093,9 @@ EXTCONST U32 PL_charclass[]; /* Use foo_LC_uvchr() instead of these for beyond the Latin1 range */ -# define isALNUM_LC(c) (FITS_IN_8_BITS(c) \ - && (isalnum((unsigned char)(c)) || (char)(c) == '_')) -# define isIDFIRST_LC(c) (FITS_IN_8_BITS(c) \ - && (isalpha((unsigned char)(c)) || (char)(c) == '_')) # define isALPHA_LC(c) (FITS_IN_8_BITS(c) && isalpha((unsigned char)(c))) +# define isALPHANUMERIC_LC(c) (FITS_IN_8_BITS(c) \ + && isalnum((unsigned char)(c))) # ifdef HAS_ISASCII # define isASCII_LC(c) (FITS_IN_8_BITS(c) && isascii((unsigned char)(c))) # else @@ -874,112 +1106,137 @@ EXTCONST U32 PL_charclass[]; # else # define isBLANK_LC(c) (FITS_IN_8_BITS(c) && isBLANK((unsigned char)(c))) # endif -# define isSPACE_LC(c) (FITS_IN_8_BITS(c) && isspace((unsigned char)(c))) -# define isDIGIT_LC(c) (FITS_IN_8_BITS(c) && isdigit((unsigned char)(c))) -# define isUPPER_LC(c) (FITS_IN_8_BITS(c) && isupper((unsigned char)(c))) -# define isLOWER_LC(c) (FITS_IN_8_BITS(c) && islower((unsigned char)(c))) -# define isALNUMC_LC(c) (FITS_IN_8_BITS(c) && isalnum((unsigned char)(c))) # define isCNTRL_LC(c) (FITS_IN_8_BITS(c) && iscntrl((unsigned char)(c))) +# define isDIGIT_LC(c) (FITS_IN_8_BITS(c) && isdigit((unsigned char)(c))) # define isGRAPH_LC(c) (FITS_IN_8_BITS(c) && isgraph((unsigned char)(c))) +# define isIDFIRST_LC(c) (FITS_IN_8_BITS(c) \ + && (isalpha((unsigned char)(c)) || (char)(c) == '_')) +# define isLOWER_LC(c) (FITS_IN_8_BITS(c) && islower((unsigned char)(c))) # define isPRINT_LC(c) (FITS_IN_8_BITS(c) && isprint((unsigned char)(c))) # define isPUNCT_LC(c) (FITS_IN_8_BITS(c) && ispunct((unsigned char)(c))) -# define toUPPER_LC(c) (FITS_IN_8_BITS(c) ? toupper((unsigned char)(c)) : (c)) +# define isSPACE_LC(c) (FITS_IN_8_BITS(c) && isspace((unsigned char)(c))) +# define isUPPER_LC(c) (FITS_IN_8_BITS(c) && isupper((unsigned char)(c))) +# define isWORDCHAR_LC(c) (FITS_IN_8_BITS(c) \ + && (isalnum((unsigned char)(c)) || (char)(c) == '_')) +# define isXDIGIT_LC(c) (FITS_IN_8_BITS(c) && isxdigit((unsigned char)(c))) # define toLOWER_LC(c) (FITS_IN_8_BITS(c) ? tolower((unsigned char)(c)) : (c)) +# define toUPPER_LC(c) (FITS_IN_8_BITS(c) ? toupper((unsigned char)(c)) : (c)) # else -# define isALNUM_LC(c) (isascii(c) && (isalnum(c) || (c) == '_')) -# define isIDFIRST_LC(c) (isascii(c) && (isalpha(c) || (c) == '_')) # define isALPHA_LC(c) (isascii(c) && isalpha(c)) +# define isALPHANUMERIC_LC(c) (isascii(c) && isalnum(c)) # define isASCII_LC(c) isascii(c) # ifdef HAS_ISBLANK # define isBLANK_LC(c) (isascii(c) && isblank(c)) # else -# define isBLANK_LC(c) isBLANK(c) +# define isBLANK_LC(c) isBLANK_A(c) # endif -# define isSPACE_LC(c) (isascii(c) && isspace(c)) -# define isDIGIT_LC(c) (isascii(c) && isdigit(c)) -# define isUPPER_LC(c) (isascii(c) && isupper(c)) -# define isLOWER_LC(c) (isascii(c) && islower(c)) -# define isALNUMC_LC(c) (isascii(c) && isalnum(c)) # define isCNTRL_LC(c) (isascii(c) && iscntrl(c)) +# define isDIGIT_LC(c) (isascii(c) && isdigit(c)) # define isGRAPH_LC(c) (isascii(c) && isgraph(c)) +# define isIDFIRST_LC(c) (isascii(c) && (isalpha(c) || (c) == '_')) +# define isLOWER_LC(c) (isascii(c) && islower(c)) # define isPRINT_LC(c) (isascii(c) && isprint(c)) # define isPUNCT_LC(c) (isascii(c) && ispunct(c)) -# define toUPPER_LC(c) (isascii(c) ? toupper(c) : (c)) +# define isSPACE_LC(c) (isascii(c) && isspace(c)) +# define isUPPER_LC(c) (isascii(c) && isupper(c)) +# define isWORDCHAR_LC(c) (isascii(c) && (isalnum(c) || (c) == '_')) +# define isXDIGIT_LC(c) (isascii(c) && isxdigit(c)) # define toLOWER_LC(c) (isascii(c) ? tolower(c) : (c)) +# define toUPPER_LC(c) (isascii(c) ? toupper(c) : (c)) # endif #endif /* USE_NEXT_CTYPE */ -#define isPSXSPC_LC(c) (isSPACE_LC(c) || (c) == '\v') +#define isIDCONT(c) isWORDCHAR(c) +#define isIDCONT_A(c) isWORDCHAR_A(c) +#define isIDCONT_L1(c) isWORDCHAR_L1(c) +#define isIDCONT_LC(c) isWORDCHAR_LC(c) +#define isPSXSPC_LC(c) isSPACE_LC(c) /* For internal core Perl use only. If the input is Latin1, use the Latin1 - * macro; otherwise use the function. Won't compile if 'c' isn't unsigned, as - * won't match function prototype. The macros do bounds checking, so have + * macro; otherwise use the function 'above_latin1'. Won't compile if 'c' isn't unsigned, as + * won't match above_latin1 prototype. The macros do bounds checking, so have * duplicate checks here, so could create versions of the macros that don't, * but experiments show that gcc optimizes them out anyway. */ /* Note that all ignore 'use bytes' */ -#define _generic_uni(classnum, function, c) ((c) < 256 \ - ? _generic_isCC(c, classnum) \ - : function(c)) - -#define isWORDCHAR_uni(c) _generic_uni(_CC_WORDCHAR, is_uni_alnum, c) -#define isALNUM_uni(c) isWORDCHAR_uni(c) -#define isBLANK_uni(c) _generic_uni(_CC_BLANK, is_HORIZWS_cp_high, c) -#define isIDFIRST_uni(c) _generic_uni(_CC_IDFIRST, _is_uni_perl_idstart, c) -#define isALPHA_uni(c) _generic_uni(_CC_ALPHA, is_uni_alpha, c) -#define isSPACE_uni(c) _generic_uni(_CC_SPACE, is_XPERLSPACE_cp_high, c) -#define isVERTWS_uni(c) _generic_uni(_CC_VERTSPACE, is_VERTWS_cp_high, c) -#define isDIGIT_uni(c) _generic_uni(_CC_DIGIT, is_uni_digit, c) -#define isUPPER_uni(c) _generic_uni(_CC_UPPER, is_uni_upper, c) -#define isLOWER_uni(c) _generic_uni(_CC_LOWER, is_uni_lower, c) -#define isASCII_uni(c) isASCII(c) - -/* All controls are in Latin1 */ -#define isCNTRL_uni(c) isCNTRL_L1(c) - -#define isGRAPH_uni(c) _generic_uni(_CC_GRAPH, is_uni_graph, c) -#define isPRINT_uni(c) _generic_uni(_CC_PRINT, is_uni_print, c) -#define isPUNCT_uni(c) _generic_uni(_CC_PUNCT, is_uni_punct, c) -#define isXDIGIT_uni(c) _generic_uni(_CC_XDIGIT, is_XDIGIT_cp_high, c) - -/* Posix and regular space differ only in U+000B, which is in Latin1 */ -#define isPSXSPC_uni(c) _generic_uni(_CC_PSXSPC, \ - is_XPERLSPACE_cp_high, c) +#define _generic_uni(classnum, above_latin1, c) ((c) < 256 \ + ? _generic_isCC(c, classnum) \ + : above_latin1(c)) +#define _generic_swash_uni(classnum, c) ((c) < 256 \ + ? _generic_isCC(c, classnum) \ + : _is_uni_FOO(classnum, c)) +#define isALPHA_uni(c) _generic_swash_uni(_CC_ALPHA, c) +#define isALPHANUMERIC_uni(c) _generic_swash_uni(_CC_ALPHANUMERIC, c) +#define isASCII_uni(c) isASCII(c) +#define isBLANK_uni(c) _generic_uni(_CC_BLANK, is_HORIZWS_cp_high, c) +#define isCNTRL_uni(c) isCNTRL_L1(c) /* All controls are in Latin1 */ +#define isDIGIT_uni(c) _generic_swash_uni(_CC_DIGIT, c) +#define isGRAPH_uni(c) _generic_swash_uni(_CC_GRAPH, c) +#define isIDCONT_uni(c) _generic_uni(_CC_WORDCHAR, _is_uni_perl_idcont, c) +#define isIDFIRST_uni(c) _generic_uni(_CC_IDFIRST, _is_uni_perl_idstart, c) +#define isLOWER_uni(c) _generic_swash_uni(_CC_LOWER, c) +#define isPRINT_uni(c) _generic_swash_uni(_CC_PRINT, c) + +/* Posix and regular space are identical above Latin1 */ +#define isPSXSPC_uni(c) _generic_uni(_CC_PSXSPC, is_XPERLSPACE_cp_high, c) + +#define isPUNCT_uni(c) _generic_swash_uni(_CC_PUNCT, c) +#define isSPACE_uni(c) _generic_uni(_CC_SPACE, is_XPERLSPACE_cp_high, c) +#define isUPPER_uni(c) _generic_swash_uni(_CC_UPPER, c) +#define isVERTWS_uni(c) _generic_uni(_CC_VERTSPACE, is_VERTWS_cp_high, c) +#define isWORDCHAR_uni(c) _generic_swash_uni(_CC_WORDCHAR, c) +#define isXDIGIT_uni(c) _generic_uni(_CC_XDIGIT, is_XDIGIT_cp_high, c) -#define toUPPER_uni(c,s,l) to_uni_upper(c,s,l) -#define toTITLE_uni(c,s,l) to_uni_title(c,s,l) -#define toLOWER_uni(c,s,l) to_uni_lower(c,s,l) #define toFOLD_uni(c,s,l) to_uni_fold(c,s,l) +#define toLOWER_uni(c,s,l) to_uni_lower(c,s,l) +#define toTITLE_uni(c,s,l) to_uni_title(c,s,l) +#define toUPPER_uni(c,s,l) to_uni_upper(c,s,l) -#define _gnrc_is_LC_uvchr(latin1, above_latin1, c) \ - (c < 256 ? latin1(c) : above_latin1(NATIVE_TO_UNI(c))) -#define isALNUM_LC_uvchr(c) _gnrc_is_LC_uvchr(isALNUM_LC, \ - is_uni_alnum_lc, c) -#define isIDFIRST_LC_uvchr(c) _gnrc_is_LC_uvchr(isIDFIRST_LC, \ - is_uni_idfirst_lc, c) -#define isALPHA_LC_uvchr(c) _gnrc_is_LC_uvchr(isALPHA_LC, is_uni_alpha_lc, c) -#define isSPACE_LC_uvchr(c) _gnrc_is_LC_uvchr(isSPACE_LC, \ - is_XPERLSPACE_cp_high, c) -#define isDIGIT_LC_uvchr(c) _gnrc_is_LC_uvchr(isDIGIT_LC, is_uni_digit_lc, c) -#define isUPPER_LC_uvchr(c) _gnrc_is_LC_uvchr(isUPPER_LC, is_uni_upper_lc, c) -#define isLOWER_LC_uvchr(c) _gnrc_is_LC_uvchr(isLOWER_LC, is_uni_lower_lc, c) -#define isCNTRL_LC_uvchr(c) (c < 256 ? isCNTRL_LC(c) : 0) -#define isGRAPH_LC_uvchr(c) _gnrc_is_LC_uvchr(isGRAPH_LC, is_uni_graph_lc, c) -#define isPRINT_LC_uvchr(c) _gnrc_is_LC_uvchr(isPRINT_LC, is_uni_print_lc, c) -#define isPUNCT_LC_uvchr(c) _gnrc_is_LC_uvchr(isPUNCT_LC, is_uni_punct_lc, c) - -#define isBLANK_LC_uni(c) isBLANK(c) /* could be wrong */ +#define _generic_LC_uvchr(latin1, above_latin1, c) \ + (c < 256 ? latin1(c) : above_latin1(c)) +#define _generic_LC_swash_uvchr(latin1, classnum, c) \ + (c < 256 ? latin1(c) : _is_uni_FOO(classnum, c)) -/* For internal core Perl use only. If the input is in the Latin1 range, use +#define isALPHA_LC_uvchr(c) _generic_LC_swash_uvchr(isALPHA_LC, _CC_ALPHA, c) +#define isALPHANUMERIC_LC_uvchr(c) _generic_LC_swash_uvchr(isALPHANUMERIC_LC, \ + _CC_ALPHANUMERIC, c) +#define isASCII_LC_uvchr(c) isASCII_LC(c) +#define isBLANK_LC_uvchr(c) _generic_LC_uvchr(isBLANK_LC, is_HORIZWS_cp_high, c) +#define isCNTRL_LC_uvchr(c) (c < 256 ? isCNTRL_LC(c) : 0) +#define isDIGIT_LC_uvchr(c) _generic_LC_swash_uvchr(isDIGIT_LC, _CC_DIGIT, c) +#define isGRAPH_LC_uvchr(c) _generic_LC_swash_uvchr(isGRAPH_LC, _CC_GRAPH, c) +#define isIDCONT_LC_uvchr(c) _generic_LC_uvchr(isIDCONT_LC, \ + _is_uni_perl_idcont, c) +#define isIDFIRST_LC_uvchr(c) _generic_LC_uvchr(isIDFIRST_LC, \ + _is_uni_perl_idstart, c) +#define isLOWER_LC_uvchr(c) _generic_LC_swash_uvchr(isLOWER_LC, _CC_LOWER, c) +#define isPRINT_LC_uvchr(c) _generic_LC_swash_uvchr(isPRINT_LC, _CC_PRINT, c) +#define isPSXSPC_LC_uvchr(c) isSPACE_LC_uvchr(c) /* space is identical to posix + space under locale */ +#define isPUNCT_LC_uvchr(c) _generic_LC_swash_uvchr(isPUNCT_LC, _CC_PUNCT, c) +#define isSPACE_LC_uvchr(c) _generic_LC_uvchr(isSPACE_LC, \ + is_XPERLSPACE_cp_high, c) +#define isUPPER_LC_uvchr(c) _generic_LC_swash_uvchr(isUPPER_LC, _CC_UPPER, c) +#define isWORDCHAR_LC_uvchr(c) _generic_LC_swash_uvchr(isWORDCHAR_LC, \ + _CC_WORDCHAR, c) +#define isXDIGIT_LC_uvchr(c) _generic_LC_uvchr(isXDIGIT_LC, is_XDIGIT_cp_high, c) + + +#define isBLANK_LC_uni(c) isBLANK_LC_uvchr(UNI_TO_NATIVE(c)) + +/* Everything whose name begins with an underscore is for internal core Perl + * use only. */ + +/* If the input is in the Latin1 range, use * the Latin1 macro 'classnum' on 'p' which is a pointer to a UTF-8 string. * Otherwise use the value given by the 'utf8' parameter. This relies on the * fact that ASCII characters have the same representation whether utf8 or not. * Note that it assumes that the utf8 has been validated, and ignores 'use * bytes' */ -#define _generic_utf8_utf8(classnum, p, utf8) (UTF8_IS_INVARIANT(*(p)) \ +#define _generic_utf8(classnum, p, utf8) (UTF8_IS_INVARIANT(*(p)) \ ? _generic_isCC(*(p), classnum) \ : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \ ? _generic_isCC( \ @@ -987,12 +1244,45 @@ EXTCONST U32 PL_charclass[]; *((p)+1 )), \ classnum) \ : utf8) -/* Like the above, but calls 'function(p)' to get the utf8 value */ -#define _generic_utf8(classnum, function, p) \ - _generic_utf8_utf8(classnum, p, function(p)) - -#define isWORDCHAR_utf8(p) _generic_utf8(_CC_WORDCHAR, is_utf8_alnum, p) -#define isALNUM_utf8(p) isWORDCHAR_utf8(p) /* back compat */ +/* Like the above, but calls 'above_latin1(p)' to get the utf8 value. 'above_latin1' + * can be a macro */ +#define _generic_func_utf8(classnum, above_latin1, p) \ + _generic_utf8(classnum, p, above_latin1(p)) +/* Like the above, but passes classnum to _isFOO_utf8(), instead of having a + * 'above_latin1' parameter */ +#define _generic_swash_utf8(classnum, p) \ + _generic_utf8(classnum, p, _is_utf8_FOO(classnum, p)) + +/* Like the above, but should be used only when it is known that there are no + * characters in the range 128-255 which the class is TRUE for. Hence it can + * skip the tests for this range. 'above_latin1' should include its arguments */ +#define _generic_utf8_no_upper_latin1(classnum, p, above_latin1) \ + (UTF8_IS_INVARIANT(*(p)) \ + ? _generic_isCC(*(p), classnum) \ + : (UTF8_IS_ABOVE_LATIN1(*(p))) \ + ? above_latin1 \ + : 0) + +/* NOTE that some of these macros have very similar ones in regcharclass.h. + * For example, there is (at the time of this writing) an 'is_SPACE_utf8()' + * there, differing in name only by an underscore from the one here + * 'isSPACE_utf8(). The difference is that the ones here are probably more + * efficient and smaller, using an O(1) array lookup for Latin1-range code + * points; the regcharclass.h ones are implemented as a series of + * "if-else-if-else ..." */ + +#define isALPHA_utf8(p) _generic_swash_utf8(_CC_ALPHA, p) +#define isALPHANUMERIC_utf8(p) _generic_swash_utf8(_CC_ALPHANUMERIC, p) +#define isASCII_utf8(p) isASCII(*p) /* Because ASCII is invariant under + utf8, the non-utf8 macro works + */ +#define isBLANK_utf8(p) _generic_func_utf8(_CC_BLANK, is_HORIZWS_high, p) +#define isCNTRL_utf8(p) _generic_utf8(_CC_CNTRL, p, 0) +#define isDIGIT_utf8(p) _generic_utf8_no_upper_latin1(_CC_DIGIT, p, \ + _is_utf8_FOO(_CC_DIGIT, p)) +#define isGRAPH_utf8(p) _generic_swash_utf8(_CC_GRAPH, p) +#define isIDCONT_utf8(p) _generic_func_utf8(_CC_WORDCHAR, \ + _is_utf8_perl_idcont, p) /* To prevent S_scan_word in toke.c from hanging, we have to make sure that * IDFIRST is an alnum. See @@ -1000,49 +1290,88 @@ EXTCONST U32 PL_charclass[]; * ever wanted to know about. (In the ASCII range, there isn't a difference.) * This used to be not the XID version, but we decided to go with the more * modern Unicode definition */ -#define isIDFIRST_utf8(p) _generic_utf8(_CC_IDFIRST, \ - _is_utf8_perl_idstart, p) - -#define isIDCONT_utf8(p) _generic_utf8(_CC_WORDCHAR, is_utf8_xidcont, p) -#define isALPHA_utf8(p) _generic_utf8(_CC_ALPHA, is_utf8_alpha, p) -#define isBLANK_utf8(p) _generic_utf8(_CC_BLANK, is_HORIZWS_high, p) -#define isSPACE_utf8(p) _generic_utf8(_CC_SPACE, is_XPERLSPACE_high, p) -#define isVERTWS_utf8(p) _generic_utf8(_CC_VERTSPACE, is_VERTWS_high, p) -#define isDIGIT_utf8(p) _generic_utf8(_CC_DIGIT, is_utf8_digit, p) -#define isUPPER_utf8(p) _generic_utf8(_CC_UPPER, is_utf8_upper, p) -#define isLOWER_utf8(p) _generic_utf8(_CC_LOWER, is_utf8_lower, p) - -/* Because ASCII is invariant under utf8, the non-utf8 macro works */ -#define isASCII_utf8(p) isASCII(*p) - -#define isCNTRL_utf8(p) _generic_utf8_utf8(_CC_CNTRL, p, 0) -#define isGRAPH_utf8(p) _generic_utf8(_CC_GRAPH, is_utf8_graph, p) -#define isPRINT_utf8(p) _generic_utf8(_CC_PRINT, is_utf8_print, p) -#define isPUNCT_utf8(p) _generic_utf8(_CC_PUNCT, is_utf8_punct, p) -#define isXDIGIT_utf8(p) _generic_utf8(_CC_XDIGIT, is_XDIGIT_high, p) -#define toUPPER_utf8(p,s,l) to_utf8_upper(p,s,l) -#define toTITLE_utf8(p,s,l) to_utf8_title(p,s,l) +#define isIDFIRST_utf8(p) _generic_func_utf8(_CC_IDFIRST, \ + _is_utf8_perl_idstart, p) + +#define isLOWER_utf8(p) _generic_swash_utf8(_CC_LOWER, p) +#define isPRINT_utf8(p) _generic_swash_utf8(_CC_PRINT, p) + +/* Posix and regular space are identical above Latin1 */ +#define isPSXSPC_utf8(p) _generic_func_utf8(_CC_PSXSPC, is_XPERLSPACE_high, p) + +#define isPUNCT_utf8(p) _generic_swash_utf8(_CC_PUNCT, p) +#define isSPACE_utf8(p) _generic_func_utf8(_CC_SPACE, is_XPERLSPACE_high, p) +#define isUPPER_utf8(p) _generic_swash_utf8(_CC_UPPER, p) +#define isVERTWS_utf8(p) _generic_func_utf8(_CC_VERTSPACE, is_VERTWS_high, p) +#define isWORDCHAR_utf8(p) _generic_swash_utf8(_CC_WORDCHAR, p) +#define isXDIGIT_utf8(p) _generic_utf8_no_upper_latin1(_CC_XDIGIT, p, \ + is_XDIGIT_high(p)) + +#define toFOLD_utf8(p,s,l) to_utf8_fold(p,s,l) #define toLOWER_utf8(p,s,l) to_utf8_lower(p,s,l) +#define toTITLE_utf8(p,s,l) to_utf8_title(p,s,l) +#define toUPPER_utf8(p,s,l) to_utf8_upper(p,s,l) + +/* For internal core Perl use only. If the input is in the Latin1 range, use + * the macro 'macro' on 'p' which is a pointer to a UTF-8 string. Otherwise + * use the value given by the 'utf8' parameter. This relies on the fact that + * ASCII characters have the same representation whether utf8 or not. Note + * that it assumes that the utf8 has been validated, and ignores 'use bytes' */ +#define _generic_LC_utf8(macro, p, utf8) \ + (UTF8_IS_INVARIANT(*(p)) \ + ? macro(*(p)) \ + : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \ + ? macro(TWO_BYTE_UTF8_TO_UNI(*(p), *((p)+1))) \ + : utf8) + +#define _generic_LC_swash_utf8(macro, classnum, p) \ + _generic_LC_utf8(macro, p, _is_utf8_FOO(classnum, p)) +#define _generic_LC_func_utf8(macro, above_latin1, p) \ + _generic_LC_utf8(macro, p, above_latin1(p)) + +#define isALPHANUMERIC_LC_utf8(p) _generic_LC_swash_utf8(isALPHANUMERIC_LC, \ + _CC_ALPHANUMERIC, p) +#define isALPHA_LC_utf8(p) _generic_LC_swash_utf8(isALPHA_LC, _CC_ALPHA, p) +#define isASCII_LC_utf8(p) isASCII_LC(*p) +#define isBLANK_LC_utf8(p) _generic_LC_func_utf8(isBLANK_LC, is_HORIZWS_high, p) +#define isCNTRL_LC_utf8(p) _generic_LC_utf8(isCNTRL_LC, p, 0) +#define isDIGIT_LC_utf8(p) _generic_LC_swash_utf8(isDIGIT_LC, _CC_DIGIT, p) +#define isGRAPH_LC_utf8(p) _generic_LC_swash_utf8(isGRAPH_LC, _CC_GRAPH, p) +#define isIDCONT_LC_utf8(p) _generic_LC_func_utf8(isIDCONT_LC, _is_utf8_perl_idcont, p) +#define isIDFIRST_LC_utf8(p) _generic_LC_func_utf8(isIDFIRST_LC, _is_utf8_perl_idstart, p) +#define isLOWER_LC_utf8(p) _generic_LC_swash_utf8(isLOWER_LC, _CC_LOWER, p) +#define isPRINT_LC_utf8(p) _generic_LC_swash_utf8(isPRINT_LC, _CC_PRINT, p) +#define isPSXSPC_LC_utf8(p) isSPACE_LC_utf8(p) /* space is identical to posix + space under locale */ +#define isPUNCT_LC_utf8(p) _generic_LC_swash_utf8(isPUNCT_LC, _CC_PUNCT, p) +#define isSPACE_LC_utf8(p) _generic_LC_func_utf8(isSPACE_LC, is_XPERLSPACE_high, p) +#define isUPPER_LC_utf8(p) _generic_LC_swash_utf8(isUPPER_LC, _CC_UPPER, p) +#define isWORDCHAR_LC_utf8(p) _generic_LC_swash_utf8(isWORDCHAR_LC, \ + _CC_WORDCHAR, p) +#define isXDIGIT_LC_utf8(p) _generic_LC_func_utf8(isXDIGIT_LC, is_XDIGIT_high, p) -/* Posix and regular space differ only in U+000B, which is in ASCII (and hence - * Latin1 */ -#define isPSXSPC_utf8(p) _generic_utf8(_CC_PSXSPC, is_XPERLSPACE_high, p) - -#define isALNUM_LC_utf8(p) isALNUM_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isIDFIRST_LC_utf8(p) isIDFIRST_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isALPHA_LC_utf8(p) isALPHA_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isBLANK_LC_utf8(p) isBLANK_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isSPACE_LC_utf8(p) isSPACE_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isDIGIT_LC_utf8(p) isDIGIT_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isUPPER_LC_utf8(p) isUPPER_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isLOWER_LC_utf8(p) isLOWER_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isALNUMC_LC_utf8(p) isALNUMC_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isCNTRL_LC_utf8(p) isCNTRL_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isGRAPH_LC_utf8(p) isGRAPH_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isPRINT_LC_utf8(p) isPRINT_LC_uvchr(valid_utf8_to_uvchr(p, 0)) -#define isPUNCT_LC_utf8(p) isPUNCT_LC_uvchr(valid_utf8_to_uvchr(p, 0)) - -#define isPSXSPC_LC_utf8(c) (isSPACE_LC_utf8(c) ||(c) == '\f') +/* Macros for backwards compatibility and for completeness when the ASCII and + * Latin1 values are identical */ +#define isALPHAU(c) isALPHA_L1(c) +#define isDIGIT_L1(c) isDIGIT_A(c) +#define isOCTAL(c) isOCTAL_A(c) +#define isOCTAL_L1(c) isOCTAL_A(c) +#define isXDIGIT_L1(c) isXDIGIT_A(c) +#define isALNUM(c) isWORDCHAR(c) +#define isALNUMU(c) isWORDCHAR_L1(c) +#define isALNUM_LC(c) isWORDCHAR_LC(c) +#define isALNUM_uni(c) isWORDCHAR_uni(c) +#define isALNUM_LC_uvchr(c) isWORDCHAR_LC_uvchr(c) +#define isALNUM_utf8(p) isWORDCHAR_utf8(p) +#define isALNUM_LC_utf8(p) isWORDCHAR_LC_utf8(p) +#define isALNUMC_A(c) isALPHANUMERIC_A(c) /* Mnemonic: "C's alnum" */ +#define isALNUMC_L1(c) isALPHANUMERIC_L1(c) +#define isALNUMC(c) isALPHANUMERIC(c) +#define isALNUMC_LC(c) isALPHANUMERIC_LC(c) +#define isALNUMC_uni(c) isALPHANUMERIC_uni(c) +#define isALNUMC_LC_uvchr(c) isALPHANUMERIC_LC_uvchr(c) +#define isALNUMC_utf8(p) isALPHANUMERIC_utf8(p) +#define isALNUMC_LC_utf8(p) isALPHANUMERIC_LC_utf8(p) /* This conversion works both ways, strangely enough. On EBCDIC platforms, * CTRL-@ is 0, CTRL-A is 1, etc, just like on ASCII, except that they don't @@ -1101,8 +1430,8 @@ The XSUB-writer's interface to the C C function. =for apidoc Am|void|Move|void* src|void* dest|int nitems|type The XSUB-writer's interface to the C C function. The C is the -source, C is the destination, C is the number of items, and C is -the type. Can do overlapping moves. See also C. +source, C is the destination, C is the number of items, and +C is the type. Can do overlapping moves. See also C. =for apidoc Am|void *|MoveD|void* src|void* dest|int nitems|type Like C but returns dest. Useful for encouraging compilers to tail-call @@ -1110,8 +1439,8 @@ optimise. =for apidoc Am|void|Copy|void* src|void* dest|int nitems|type The XSUB-writer's interface to the C C function. The C is the -source, C is the destination, C is the number of items, and C is -the type. May fail on overlapping copies. See also C. +source, C is the destination, C is the number of items, and +C is the type. May fail on overlapping copies. See also C. =for apidoc Am|void *|CopyD|void* src|void* dest|int nitems|type @@ -1162,12 +1491,12 @@ PoisonWith(0xEF) for catching access to freed memory. * (U16)n > (size_t)~0/sizeof(U16) always being false. */ #ifdef PERL_MALLOC_WRAP #define MEM_WRAP_CHECK(n,t) \ - (void)(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t) && (croak_memory_wrap(),0)) + (void)(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t) && (Perl_croak_memory_wrap(),0)) #define MEM_WRAP_CHECK_1(n,t,a) \ (void)(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t) && (Perl_croak_nocontext("%s",(a)),0)) #define MEM_WRAP_CHECK_(n,t) MEM_WRAP_CHECK(n,t), -#define PERL_STRLEN_ROUNDUP(n) ((void)(((n) > MEM_SIZE_MAX - 2 * PERL_STRLEN_ROUNDUP_QUANTUM) ? (croak_memory_wrap(),0):0),((n-1+PERL_STRLEN_ROUNDUP_QUANTUM)&~((MEM_SIZE)PERL_STRLEN_ROUNDUP_QUANTUM-1))) +#define PERL_STRLEN_ROUNDUP(n) ((void)(((n) > MEM_SIZE_MAX - 2 * PERL_STRLEN_ROUNDUP_QUANTUM) ? (Perl_croak_memory_wrap(),0):0),((n-1+PERL_STRLEN_ROUNDUP_QUANTUM)&~((MEM_SIZE)PERL_STRLEN_ROUNDUP_QUANTUM-1))) #else #define MEM_WRAP_CHECK(n,t) @@ -1338,6 +1667,8 @@ void Perl_mem_log_del_sv(const SV *sv, const char *filename, const int linenumbe # define deprecate(s) Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), "Use of " s " is deprecated") #endif +#endif /* HANDY_H */ + /* * Local variables: * c-indentation-style: bsd