typedef U16TYPE U16;
typedef I32TYPE I32;
typedef U32TYPE U32;
-#ifdef PERL_CORE
-# ifdef HAS_QUAD
+
+#ifdef HAS_QUAD
typedef I64TYPE I64;
typedef U64TYPE U64;
-# endif
-#endif /* PERL_CORE */
+#endif
/* INT64_C/UINT64_C are C99 from <stdint.h> (so they will not be
* available in strict C89 mode), but they are nice, so let's define
# define PeRl_UINT64_C(c) CAT2(c,UI64)
# endif
# ifndef PeRl_INT64_C
-# define PeRl_INT64_C(c) ((I64TYPE)(c)) /* last resort */
-# define PeRl_UINT64_C(c) ((U64TYPE)(c))
+# define PeRl_INT64_C(c) ((I64)(c)) /* last resort */
+# define PeRl_UINT64_C(c) ((U64)(c))
# endif
/* In OS X the INT64_C/UINT64_C are defined with LL/ULL, which will
* not fly with C89-pedantic gcc, so let's undefine them first so that
the number of bytes to compare. Returns true or false. (A wrapper for
C<strncmp>).
+=for apidoc Am|bool|memEQ|char* s1|char* s2|STRLEN len
+Test two buffers (which may contain embedded C<NUL> characters, to see if they
+are equal. The C<len> parameter indicates the number of bytes to compare.
+Returns zero if equal, or non-zero if non-equal.
+
+=for apidoc Am|bool|memNE|char* s1|char* s2|STRLEN len
+Test two buffers (which may contain embedded C<NUL> characters, to see if they
+are not equal. The C<len> parameter indicates the number of bytes to compare.
+Returns zero if non-equal, or non-zero if equal.
+
=cut
*/
returns the same as C<isFOO_LC> for input code points less than 256, and
returns the hard-coded, not-affected-by-locale, Unicode results for larger ones.
-Variant C<isFOO_LC_utf8> is like C<isFOO_LC_uvchr>, but the input is a pointer to a
-(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>). The
+Variant C<isFOO_LC_utf8> is like C<isFOO_LC_uvchr>, but the input is a pointer
+to a (known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>). The
classification of just the first (possibly multi-byte) character in the string
is tested.
Returns a boolean indicating whether the specified character is a
whitespace character. This is analogous
to what C<m/\s/> matches in a regular expression. Starting in Perl 5.18
-(experimentally), this also matches what C<m/[[:space:]]/> does.
-("Experimentally" means that this change may be backed out in 5.22 if
-field experience indicates that it was unwise.) Prior to 5.18, only the
+this also matches what C<m/[[:space:]]/> does. Prior to 5.18, only the
locale forms of this macro (the ones with C<LC> in their names) matched
precisely what C<m/[[:space:]]/> does. In those releases, the only difference,
in the non-locale variants, was that C<isSPACE()> did not match a vertical tab.
=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<isSPACE()> macros. ("Experimentally" means that this change
-may be backed out in 5.22 if field experience indicates that it
-was unwise.)
+Starting in 5.18, this is identical in all its forms to the
+corresponding C<isSPACE()> macros.
The locale forms of this macro are identical to their corresponding
C<isSPACE()> forms in all Perl releases. In releases prior to 5.18, the
non-locale forms differ from their C<isSPACE()> forms only in that the
Otherwise they are identical. Thus this macro is analogous to what
C<m/[[:space:]]/> matches in a regular expression.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uni>, C<isPSXSPC_utf8>, C<isPSXSPC_LC>,
-C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8>.
+variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uni>, C<isPSXSPC_utf8>,
+C<isPSXSPC_LC>, C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8>.
=for apidoc Am|bool|isUPPER|char ch
Returns a boolean indicating whether the specified character is an
C<toLOWER_A> is equivalent.
=for apidoc Am|U8|toLOWER_L1|U8 ch
-Converts the specified Latin1 character to lowercase. The results are undefined if
-the input doesn't fit in a byte.
+Converts the specified Latin1 character to lowercase. The results are
+undefined if the input doesn't fit in a byte.
=for apidoc Am|U8|toLOWER_LC|U8 ch
Converts the specified character to lowercase using the current locale's rules,
=for apidoc Am|U8|toTITLE|U8 ch
Converts the specified character to titlecase. If the input is anything but an
ASCII lowercase character, that input character itself is returned. Variant
-C<toTITLE_A> is equivalent. (There is no C<toTITLE_L1> for the full Latin1 range,
-as the full generality of L</toTITLE_uni> is needed there. Titlecase is not a
-concept used in locale handling, so there is no functionality for that.)
+C<toTITLE_A> is equivalent. (There is no C<toTITLE_L1> for the full Latin1
+range, as the full generality of L</toTITLE_uni> is needed there. Titlecase is
+not a concept used in locale handling, so there is no functionality for that.)
=for apidoc Am|UV|toTITLE_uni|UV cp|U8* s|STRLEN* lenp
Converts the Unicode code point C<cp> to its titlecase version, and
* 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_SPACE 10 /* \s, [:space:] */
# 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 _CC_CNTRL 13 /* [:cntrl:] */
+# define _CC_ASCII 14 /* [:ascii:] */
+# define _CC_VERTSPACE 15 /* \v */
# define _HIGHEST_REGCOMP_DOT_H_SYNC _CC_VERTSPACE
/* 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_NONLATIN1_SIMPLE_FOLD 20
-# define _CC_QUOTEMETA 21
-# define _CC_NON_FINAL_FOLD 22
-# define _CC_IS_IN_SOME_FOLD 23
-# define _CC_MNEMONIC_CNTRL 24
-/* Unused: 25-31
+# define _CC_IDFIRST 16
+# define _CC_CHARNAME_CONT 17
+# define _CC_NONLATIN1_FOLD 18
+# define _CC_NONLATIN1_SIMPLE_FOLD 19
+# define _CC_QUOTEMETA 20
+# define _CC_NON_FINAL_FOLD 21
+# define _CC_IS_IN_SOME_FOLD 22
+# define _CC_MNEMONIC_CNTRL 23
+/* Unused: 24-31
* 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
_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,
#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 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
};
#endif
+START_EXTERN_C
# ifdef DOINIT
EXTCONST U32 PL_charclass[] = {
# include "l1_char_class_tab.h"
# else /* ! DOINIT */
EXTCONST U32 PL_charclass[];
# endif
+END_EXTERN_C
/* The 1U keeps Solaris from griping when shifting sets the uppermost bit */
# define _CC_mask(classnum) (1U << (classnum))
/* For internal core Perl use only: the base macro for defining macros like
* isALPHA_A. The foo_A version makes sure that both the desired bit and
* the ASCII bit are present */
-# define _generic_isCC_A(c, classnum) (FITS_IN_8_BITS(c) \
- && ((PL_charclass[(U8) (c)] & _CC_mask_A(classnum)) \
- == _CC_mask_A(classnum)))
+# define _generic_isCC_A(c, classnum) (FITS_IN_8_BITS(c) \
+ && ((PL_charclass[(U8) (c)] & _CC_mask_A(classnum)) \
+ == _CC_mask_A(classnum)))
# define isALPHA_A(c) _generic_isCC_A(c, _CC_ALPHA)
# define isALPHANUMERIC_A(c) _generic_isCC_A(c, _CC_ALPHANUMERIC)
# define isGRAPH_A(c) _generic_isCC_A(c, _CC_GRAPH)
# define isLOWER_A(c) _generic_isCC_A(c, _CC_LOWER)
# define isPRINT_A(c) _generic_isCC_A(c, _CC_PRINT)
-# define isPSXSPC_A(c) _generic_isCC_A(c, _CC_PSXSPC)
# define isPUNCT_A(c) _generic_isCC_A(c, _CC_PUNCT)
# define isSPACE_A(c) _generic_isCC_A(c, _CC_SPACE)
# define isUPPER_A(c) _generic_isCC_A(c, _CC_UPPER)
# define isWORDCHAR_A(c) _generic_isCC_A(c, _CC_WORDCHAR)
-# define isXDIGIT_A(c) _generic_isCC(c, _CC_XDIGIT) /* No non-ASCII xdigits */
+# define isXDIGIT_A(c) _generic_isCC(c, _CC_XDIGIT) /* No non-ASCII xdigits
+ */
# define isIDFIRST_A(c) _generic_isCC_A(c, _CC_IDFIRST)
# define isALPHA_L1(c) _generic_isCC(c, _CC_ALPHA)
# define isALPHANUMERIC_L1(c) _generic_isCC(c, _CC_ALPHANUMERIC)
# define isGRAPH_L1(c) _generic_isCC(c, _CC_GRAPH)
# define isLOWER_L1(c) _generic_isCC(c, _CC_LOWER)
# define isPRINT_L1(c) _generic_isCC(c, _CC_PRINT)
-# define isPSXSPC_L1(c) _generic_isCC(c, _CC_PSXSPC)
+# define isPSXSPC_L1(c) isSPACE_L1(c)
# define isPUNCT_L1(c) _generic_isCC(c, _CC_PUNCT)
# define isSPACE_L1(c) _generic_isCC(c, _CC_SPACE)
# define isUPPER_L1(c) _generic_isCC(c, _CC_UPPER)
# define _isQUOTEMETA(c) _generic_isCC(c, _CC_QUOTEMETA)
# define _IS_NON_FINAL_FOLD_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
- _generic_isCC(c, _CC_NON_FINAL_FOLD)
+ _generic_isCC(c, _CC_NON_FINAL_FOLD)
# define _IS_IN_SOME_FOLD_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
- _generic_isCC(c, _CC_IS_IN_SOME_FOLD)
+ _generic_isCC(c, _CC_IS_IN_SOME_FOLD)
# define _IS_MNEMONIC_CNTRL_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
_generic_isCC(c, _CC_MNEMONIC_CNTRL)
#else /* else we don't have perl.h H_PERL */
# if ! defined(EBCDIC) && ! defined(NATIVE_TO_LATIN1)
# define NATIVE_TO_LATIN1(ch) (ch)
# endif
-# define isPSXSPC_A(c) isSPACE_A(c) /* XXX Assumes SPACE matches '\v' */
# define isALPHA_L1(c) (isUPPER_L1(c) || isLOWER_L1(c))
# define isALPHANUMERIC_L1(c) (isALPHA_L1(c) || isDIGIT_A(c))
# define isBLANK_L1(c) (isBLANK_A(c) \
# define isPRINT_L1(c) (isPRINT_A(c) \
|| (FITS_IN_8_BITS(c) \
&& NATIVE_TO_LATIN1((U8) c) >= 0xA0))
-# define isPSXSPC_L1(c) isSPACE_L1(c)
# define isPUNCT_L1(c) (isPUNCT_A(c) \
|| (FITS_IN_8_BITS(c) \
&& (NATIVE_TO_LATIN1((U8) c) == 0xA1 \
#define isIDFIRST(c) isIDFIRST_A(c)
#define isLOWER(c) isLOWER_A(c)
#define isPRINT(c) isPRINT_A(c)
+#define isPSXSPC_A(c) isSPACE_A(c)
#define isPSXSPC(c) isPSXSPC_A(c)
+#define isPSXSPC_L1(c) isSPACE_L1(c)
#define isPUNCT(c) isPUNCT_A(c)
#define isSPACE(c) isSPACE_A(c)
#define isUPPER(c) isUPPER_A(c)
(! FITS_IN_8_BITS(c) \
? (c) \
: ((! IN_UTF8_CTYPE_LOCALE) \
- ? (cast)function((cast)(c)) \
+ ? (cast)function((cast)(c)) \
: ((((U8)(c)) == MICRO_SIGN) \
? GREEK_CAPITAL_LETTER_MU \
: ((((U8)(c)) == LATIN_SMALL_LETTER_Y_WITH_DIAERESIS) \
* Not all possible weirdnesses are checked for, just the ones that were
* detected on actual Microsoft code pages */
-# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, iscntrl)
-# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, isspace)
-
-# define isALPHA_LC(c) (_generic_LC(c, _CC_ALPHA, isalpha) && isALPHANUMERIC_LC(c))
-# define isALPHANUMERIC_LC(c) (_generic_LC(c, _CC_ALPHANUMERIC, isalnum) && ! isPUNCT_LC(c))
-# define isDIGIT_LC(c) (_generic_LC(c, _CC_DIGIT, isdigit) && isALPHANUMERIC_LC(c))
-# define isGRAPH_LC(c) (_generic_LC(c, _CC_GRAPH, isgraph) && isPRINT_LC(c))
-# define isIDFIRST_LC(c) (((c) == '_') || (_generic_LC(c, _CC_IDFIRST, isalpha) && ! isPUNCT_LC(c)))
-# define isLOWER_LC(c) (_generic_LC(c, _CC_LOWER, islower) && isALPHA_LC(c))
-# define isPRINT_LC(c) (_generic_LC(c, _CC_PRINT, isprint) && ! isCNTRL_LC(c))
-# define isPUNCT_LC(c) (_generic_LC(c, _CC_PUNCT, ispunct) && ! isCNTRL_LC(c))
-# define isUPPER_LC(c) (_generic_LC(c, _CC_UPPER, isupper) && isALPHA_LC(c))
+# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, iscntrl)
+# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, isspace)
+
+# define isALPHA_LC(c) (_generic_LC(c, _CC_ALPHA, isalpha) \
+ && isALPHANUMERIC_LC(c))
+# define isALPHANUMERIC_LC(c) (_generic_LC(c, _CC_ALPHANUMERIC, isalnum) && \
+ ! isPUNCT_LC(c))
+# define isDIGIT_LC(c) (_generic_LC(c, _CC_DIGIT, isdigit) && \
+ isALPHANUMERIC_LC(c))
+# define isGRAPH_LC(c) (_generic_LC(c, _CC_GRAPH, isgraph) && isPRINT_LC(c))
+# define isIDFIRST_LC(c) (((c) == '_') \
+ || (_generic_LC(c, _CC_IDFIRST, isalpha) && ! isPUNCT_LC(c)))
+# define isLOWER_LC(c) (_generic_LC(c, _CC_LOWER, islower) && isALPHA_LC(c))
+# define isPRINT_LC(c) (_generic_LC(c, _CC_PRINT, isprint) && ! isCNTRL_LC(c))
+# define isPUNCT_LC(c) (_generic_LC(c, _CC_PUNCT, ispunct) && ! isCNTRL_LC(c))
+# define isUPPER_LC(c) (_generic_LC(c, _CC_UPPER, isupper) && isALPHA_LC(c))
# define isWORDCHAR_LC(c) (((c) == '_') || isALPHANUMERIC_LC(c))
-# define isXDIGIT_LC(c) (_generic_LC(c, _CC_XDIGIT, isxdigit) && isALPHANUMERIC_LC(c))
+# define isXDIGIT_LC(c) (_generic_LC(c, _CC_XDIGIT, isxdigit) \
+ && isALPHANUMERIC_LC(c))
# define toLOWER_LC(c) _generic_toLOWER_LC((c), tolower, U8)
# define toUPPER_LC(c) _generic_toUPPER_LC((c), toupper, U8)
#else /* The final fallback position */
-# define isALPHA_LC(c) (isascii(c) && isalpha(c))
-# define isALPHANUMERIC_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 isALPHA_LC(c) (isascii(c) && isalpha(c))
+# define isALPHANUMERIC_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 isSPACE_LC(c) (isascii(c) && isspace(c))
-# define isUPPER_LC(c) (isascii(c) && isupper(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 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 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))
#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 isPSXSPC_uni(c) isSPACE_uni(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 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 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, \
+#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, \
+#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 isPSXSPC_LC_uvchr(c) isSPACE_LC_uvchr(c)
#define isPUNCT_LC_uvchr(c) _generic_LC_swash_uvchr(isPUNCT_LC, _CC_PUNCT, c)
-#define isSPACE_LC_uvchr(c) _generic_LC_uvchr(isSPACE_LC, \
+#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, \
+#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 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))
+#define isBLANK_LC_uni(c) isBLANK_LC_uvchr(UNI_TO_NATIVE(c))
/* For internal core Perl use only: the base macros for defining macros like
* isALPHA_utf8. These are like the earlier defined macros, but take an input
*((p)+1 )), \
classnum) \
: utf8)
-/* Like the above, but calls 'above_latin1(p)' to get the utf8 value. 'above_latin1'
- * can be a macro */
+/* 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 an
* 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
+#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 isBLANK_utf8(p) _generic_func_utf8(_CC_BLANK, is_HORIZWS_high, p)
#ifdef EBCDIC
/* Because all controls are UTF-8 invariants in EBCDIC, we can use this
* 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_func_utf8(_CC_IDFIRST, \
+#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, \
+#define isLOWER_utf8(p) _generic_swash_utf8(_CC_LOWER, p)
+#define isPRINT_utf8(p) _generic_swash_utf8(_CC_PRINT, p)
+#define isPSXSPC_utf8(p) isSPACE_utf8(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 _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, \
+#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 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)
+#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)
+#define isXDIGIT_LC_utf8(p) _generic_LC_func_utf8(isXDIGIT_LC, \
+ is_XDIGIT_high, p)
/* 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 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 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_utf8(p) isALPHANUMERIC_utf8(p)
#define isALNUMC_LC_utf8(p) isALPHANUMERIC_LC_utf8(p)
/* On EBCDIC platforms, CTRL-@ is 0, CTRL-A is 1, etc, just like on ASCII,
* The conversion works both ways, so toCTRL('D') is 4, and toCTRL(4) is D,
* etc. */
#ifndef EBCDIC
-# define toCTRL(c) (__ASSERT_(FITS_IN_8_BITS(c)) toUPPER(c) ^ 64)
+# define toCTRL(c) (__ASSERT_(FITS_IN_8_BITS(c)) toUPPER(((U8)(c))) ^ 64)
#else
-# define toCTRL(c) (__ASSERT_(FITS_IN_8_BITS(c)) \
- ((isPRINT_A(c)) \
- ? (UNLIKELY((c) == '?') \
- ? QUESTION_MARK_CTRL \
- : (NATIVE_TO_LATIN1(toUPPER(c)) ^ 64)) \
- : (UNLIKELY((c) == QUESTION_MARK_CTRL) \
- ? '?' \
- : (LATIN1_TO_NATIVE((c) ^ 64)))))
+# define toCTRL(c) (__ASSERT_(FITS_IN_8_BITS(c)) \
+ ((isPRINT_A(c)) \
+ ? (UNLIKELY((c) == '?') \
+ ? QUESTION_MARK_CTRL \
+ : (NATIVE_TO_LATIN1(toUPPER((U8) (c))) ^ 64)) \
+ : (UNLIKELY((c) == QUESTION_MARK_CTRL) \
+ ? '?' \
+ : (LATIN1_TO_NATIVE(((U8) (c)) ^ 64)))))
#endif
/* Line numbers are unsigned, 32 bits. */
#define MEM_SIZE_MAX ((MEM_SIZE)~0)
-/* The +0.0 in MEM_WRAP_CHECK_ is an attempt to foil
- * overly eager compilers that will bleat about e.g.
- * (U16)n > (size_t)~0/sizeof(U16) always being false. */
+
#ifdef PERL_MALLOC_WRAP
-#define MEM_WRAP_CHECK(n,t) \
- (void)(UNLIKELY(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t)) && (croak_memory_wrap(),0))
-#define MEM_WRAP_CHECK_1(n,t,a) \
- (void)(UNLIKELY(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t)) && (Perl_croak_nocontext("%s",(a)),0))
+
+/* This expression will be constant-folded at compile time. It checks
+ * whether or not the type of the count n is so small (e.g. U8 or U16, or
+ * U32 on 64-bit systems) that there's no way a wrap-around could occur.
+ * As well as avoiding the need for a run-time check in some cases, it's
+ * designed to avoid compiler warnings like:
+ * comparison is always false due to limited range of data type
+ */
+
+# define _MEM_WRAP_NEEDS_RUNTIME_CHECK(n,t) \
+ (sizeof(t) > ((MEM_SIZE)1 << 8*(sizeof(MEM_SIZE) - sizeof(n))))
+
+/* This is written in a slightly odd way to avoid various spurious
+ * compiler warnings. We *want* to write the expression as
+ * _MEM_WRAP_NEEDS_RUNTIME_CHECK(n,t) && (n > C)
+ * (for some compile-time constant C), but even when the LHS
+ * constant-folds to false at compile-time, g++ insists on emitting
+ * warnings about the RHS (e.g. "comparison is always false"), so instead
+ * we write it as
+ *
+ * (cond ? n : X) > C
+ *
+ * where X is a constant with X > C always false. Choosing a value for X
+ * is tricky. If 0, some compilers will complain about 0 > C always being
+ * false; if 1, Coverity complains when n happens to be the constant value
+ * '1', that cond ? 1 : 1 has the same value on both branches; so use C
+ * for X and hope that nothing else whines.
+ */
+
+# define _MEM_WRAP_WILL_WRAP(n,t) \
+ ((_MEM_WRAP_NEEDS_RUNTIME_CHECK(n,t) ? (MEM_SIZE)(n) : \
+ MEM_SIZE_MAX/sizeof(t)) > MEM_SIZE_MAX/sizeof(t))
+
+# define MEM_WRAP_CHECK(n,t) \
+ (void)(UNLIKELY(_MEM_WRAP_WILL_WRAP(n,t)) \
+ && (croak_memory_wrap(),0))
+
+# define MEM_WRAP_CHECK_1(n,t,a) \
+ (void)(UNLIKELY(_MEM_WRAP_WILL_WRAP(n,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)))
* - lots of ENV reads
*/
-PERL_EXPORT_C Malloc_t Perl_mem_log_alloc(const UV n, const UV typesize, const char *type_name, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
+PERL_CALLCONV Malloc_t Perl_mem_log_alloc(const UV n, const UV typesize, const char *type_name, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
-PERL_EXPORT_C Malloc_t Perl_mem_log_realloc(const UV n, const UV typesize, const char *type_name, Malloc_t oldalloc, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
+PERL_CALLCONV Malloc_t Perl_mem_log_realloc(const UV n, const UV typesize, const char *type_name, Malloc_t oldalloc, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
-PERL_EXPORT_C Malloc_t Perl_mem_log_free(Malloc_t oldalloc, const char *filename, const int linenumber, const char *funcname);
+PERL_CALLCONV Malloc_t Perl_mem_log_free(Malloc_t oldalloc, const char *filename, const int linenumber, const char *funcname);
# ifdef PERL_CORE
# ifndef PERL_MEM_LOG_NOIMPL
shortcut macro defined without -DPERL_CORE. Neither codesearch.google.com nor
CPAN::Unpack show any users outside the core. */
#ifdef PERL_CORE
-# define deprecate(s) Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), "Use of " s " is deprecated")
+# define deprecate(s) Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), \
+ "Use of " s " is deprecated")
#endif
/* Internal macros to deal with gids and uids */
#endif /* HANDY_H */
/*
- * Local variables:
- * c-indentation-style: bsd
- * c-basic-offset: 4
- * indent-tabs-mode: nil
- * End:
- *
* ex: set ts=8 sts=4 sw=4 et:
*/