X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=handy.h;h=2aa02b7fc2ff962405474036c7b48a7c2062f518;hb=78b9063ba31cc2a48b78683b758601c04e4eb340;hp=0904bebba5b15666c485c7b8dfc0c512bc9a6508;hpb=4eb8286e4c6ac94fdae21a64c54a936bc836983e;p=p5sagit%2Fp5-mst-13.2.git diff --git a/handy.h b/handy.h index 0904beb..2aa02b7 100644 --- a/handy.h +++ b/handy.h @@ -1,6 +1,7 @@ /* handy.h * - * Copyright (c) 1991-1999, Larry Wall + * Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1999, + * 2000, 2001, 2002, 2004, 2005 by Larry Wall and others * * You may distribute under the terms of either the GNU General Public * License or the Artistic License, as specified in the README file. @@ -19,6 +20,19 @@ #endif #define Null(type) ((type)NULL) + +/* +=head1 Handy Values + +=for apidoc AmU||Nullch +Null character pointer. + +=for apidoc AmU||Nullsv +Null SV pointer. + +=cut +*/ + #define Nullch Null(char*) #define Nullfp Null(PerlIO*) #define Nullsv Null(SV*) @@ -37,24 +51,24 @@ just figure out all the headers such a test needs. Andy Dougherty August 1996 */ -/* bool is built-in for g++-2.6.3, which might be used for an extension. - If the extension includes <_G_config.h> before this file then - _G_HAVE_BOOL will be properly set. If, however, the extension includes - this file first, then you will have to manually set -DHAS_BOOL in - your command line to avoid a conflict. +/* bool is built-in for g++-2.6.3 and later, which might be used + for extensions. <_G_config.h> defines _G_HAVE_BOOL, but we can't + be sure _G_config.h will be included before this file. _G_config.h + also defines _G_HAVE_BOOL for both gcc and g++, but only g++ + actually has bool. Hence, _G_HAVE_BOOL is pretty useless for us. + g++ can be identified by __GNUG__. + Andy Dougherty February 2000 */ -#ifdef _G_HAVE_BOOL -# if _G_HAVE_BOOL +#ifdef __GNUG__ /* GNU g++ has bool built-in */ # ifndef HAS_BOOL -# define HAS_BOOL 1 +# define HAS_BOOL 1 # endif -# endif #endif /* The NeXT dynamic loader headers will not build with the bool macro So declare them now to clear confusion. */ -#ifdef NeXT +#if defined(NeXT) || defined(__NeXT__) # undef FALSE # undef TRUE typedef enum bool { FALSE = 0, TRUE = 1 } bool; @@ -62,7 +76,7 @@ # ifndef HAS_BOOL # define HAS_BOOL 1 # endif /* !HAS_BOOL */ -#endif /* NeXT */ +#endif /* NeXT || __NeXT__ */ #ifndef HAS_BOOL # if defined(UTS) || defined(VMS) @@ -70,6 +84,7 @@ # else # define bool char # endif +# define HAS_BOOL 1 #endif /* XXX A note on the perl source internal type system. The @@ -89,8 +104,9 @@ Similarly, there is no guarantee that I16 and U16 have exactly 16 bits. - For dealing with issues that may arise from various 32/64-bit - systems, we will ask Configure to check out + For dealing with issues that may arise from various 32/64-bit + systems, we will ask Configure to check out + SHORTSIZE == sizeof(short) INTSIZE == sizeof(int) LONGSIZE == sizeof(long) @@ -98,63 +114,98 @@ PTRSIZE == sizeof(void *) DOUBLESIZE == sizeof(double) LONG_DOUBLESIZE == sizeof(long double) (if HAS_LONG_DOUBLE). - Most of these are currently unused, but they are mentioned here so - metaconfig will include the appropriate tests in Configure and - we can then start to consider how best to deal with long long - variables. - Andy Dougherty April 1998 + */ +#ifdef I_INTTYPES /* e.g. Linux has int64_t without */ +# include +# ifdef INT32_MIN_BROKEN +# undef INT32_MIN +# define INT32_MIN (-2147483647-1) +# endif +# ifdef INT64_MIN_BROKEN +# undef INT64_MIN +# define INT64_MIN (-9223372036854775807LL-1) +# endif +#endif + +typedef I8TYPE I8; +typedef U8TYPE U8; +typedef I16TYPE I16; +typedef U16TYPE U16; +typedef I32TYPE I32; +typedef U32TYPE U32; +#ifdef PERL_CORE +# ifdef HAS_QUAD +typedef I64TYPE I64; +typedef U64TYPE U64; +# endif +#endif /* PERL_CORE */ + +#if defined(HAS_QUAD) && defined(USE_64_BIT_INT) +# ifndef UINT64_C /* usually from */ +# if defined(HAS_LONG_LONG) && QUADKIND == QUAD_IS_LONG_LONG +# define INT64_C(c) CAT2(c,LL) +# define UINT64_C(c) CAT2(c,ULL) +# else +# if LONGSIZE == 8 && QUADKIND == QUAD_IS_LONG +# define INT64_C(c) CAT2(c,L) +# define UINT64_C(c) CAT2(c,UL) +# else +# define INT64_C(c) ((I64TYPE)(c)) +# define UINT64_C(c) ((U64TYPE)(c)) +# endif +# endif +# endif +#endif + +/* HMB H.Merijn Brand - a placeholder for preparing Configure patches */ +#if defined(LIBM_LIB_VERSION) +/* Not (yet) used at top level, but mention them for metaconfig */ +#endif + +/* Mention I8SIZE, U8SIZE, I16SIZE, U16SIZE, I32SIZE, U32SIZE, + I64SIZE, and U64SIZE here so that metaconfig pulls them in. */ + #if defined(UINT8_MAX) && defined(INT16_MAX) && defined(INT32_MAX) -typedef int8_t I8; -typedef uint8_t U8; /* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type. Please search CHAR_MAX in perl.h for further details. */ #define U8_MAX UINT8_MAX #define U8_MIN UINT8_MIN -typedef int16_t I16; -typedef uint16_t U16; #define I16_MAX INT16_MAX #define I16_MIN INT16_MIN #define U16_MAX UINT16_MAX #define U16_MIN UINT16_MIN -typedef int32_t I32; -typedef uint32_t U32; #define I32_MAX INT32_MAX #define I32_MIN INT32_MIN -#define U32_MAX UINT32_MAX +#ifndef UINT32_MAX_BROKEN /* e.g. HP-UX with gcc messes this up */ +# define U32_MAX UINT32_MAX +#else +# define U32_MAX 4294967295U +#endif #define U32_MIN UINT32_MIN #else -typedef char I8; -typedef unsigned char U8; /* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type. Please search CHAR_MAX in perl.h for further details. */ #define U8_MAX PERL_UCHAR_MAX #define U8_MIN PERL_UCHAR_MIN -/* Beware. SHORTSIZE > 2 in Cray C90ties. */ -typedef short I16; -typedef unsigned short U16; #define I16_MAX PERL_SHORT_MAX #define I16_MIN PERL_SHORT_MIN #define U16_MAX PERL_USHORT_MAX #define U16_MIN PERL_USHORT_MIN #if LONGSIZE > 4 - typedef int I32; - typedef unsigned int U32; # define I32_MAX PERL_INT_MAX # define I32_MIN PERL_INT_MIN # define U32_MAX PERL_UINT_MAX # define U32_MIN PERL_UINT_MIN #else - typedef long I32; - typedef unsigned long U32; # define I32_MAX PERL_LONG_MAX # define I32_MIN PERL_LONG_MIN # define U32_MAX PERL_ULONG_MAX @@ -163,12 +214,52 @@ typedef unsigned short U16; #endif +/* log(2) is pretty close to 0.30103, just in case anyone is grepping for it */ #define BIT_DIGITS(N) (((N)*146)/485 + 1) /* log2(10) =~ 146/485 */ #define TYPE_DIGITS(T) BIT_DIGITS(sizeof(T) * 8) #define TYPE_CHARS(T) (TYPE_DIGITS(T) + 2) /* sign, NUL */ #define Ctl(ch) ((ch) & 037) +/* +=head1 Miscellaneous Functions + +=for apidoc Am|bool|strNE|char* s1|char* s2 +Test two strings to see if they are different. Returns true or +false. + +=for apidoc Am|bool|strEQ|char* s1|char* s2 +Test two strings to see if they are equal. Returns true or false. + +=for apidoc Am|bool|strLT|char* s1|char* s2 +Test two strings to see if the first, C, is less than the second, +C. Returns true or false. + +=for apidoc Am|bool|strLE|char* s1|char* s2 +Test two strings to see if the first, C, is less than or equal to the +second, C. Returns true or false. + +=for apidoc Am|bool|strGT|char* s1|char* s2 +Test two strings to see if the first, C, is greater than the second, +C. Returns true or false. + +=for apidoc Am|bool|strGE|char* s1|char* s2 +Test two strings to see if the first, C, is greater than or equal to +the second, C. Returns true or false. + +=for apidoc Am|bool|strnNE|char* s1|char* s2|STRLEN len +Test two strings to see if they are different. The C parameter +indicates the number of bytes to compare. Returns true or false. (A +wrapper for C). + +=for apidoc Am|bool|strnEQ|char* s1|char* s2|STRLEN len +Test two strings to see if they are equal. The C parameter indicates +the number of bytes to compare. Returns true or false. (A wrapper for +C). + +=cut +*/ + #define strNE(s1,s2) (strcmp(s1,s2)) #define strEQ(s1,s2) (!strcmp(s1,s2)) #define strLT(s1,s2) (strcmp(s1,s2) < 0) @@ -205,23 +296,73 @@ typedef unsigned short U16; # endif #endif +/* + +=head1 Character classes + +=for apidoc Am|bool|isALNUM|char ch +Returns a boolean indicating whether the C C is an ASCII alphanumeric +character (including underscore) or digit. + +=for apidoc Am|bool|isALPHA|char ch +Returns a boolean indicating whether the C C is an ASCII alphabetic +character. + +=for apidoc Am|bool|isSPACE|char ch +Returns a boolean indicating whether the C C is whitespace. + +=for apidoc Am|bool|isDIGIT|char ch +Returns a boolean indicating whether the C C is an ASCII +digit. + +=for apidoc Am|bool|isUPPER|char ch +Returns a boolean indicating whether the C C is an uppercase +character. + +=for apidoc Am|bool|isLOWER|char ch +Returns a boolean indicating whether the C C is a lowercase +character. + +=for apidoc Am|char|toUPPER|char ch +Converts the specified character to uppercase. + +=for apidoc Am|char|toLOWER|char ch +Converts the specified character to lowercase. + +=cut +*/ + #define isALNUM(c) (isALPHA(c) || isDIGIT(c) || (c) == '_') #define isIDFIRST(c) (isALPHA(c) || (c) == '_') #define isALPHA(c) (isUPPER(c) || isLOWER(c)) #define isSPACE(c) \ ((c) == ' ' || (c) == '\t' || (c) == '\n' || (c) =='\r' || (c) == '\f') +#define isPSXSPC(c) (isSPACE(c) || (c) == '\v') +#define isBLANK(c) ((c) == ' ' || (c) == '\t') #define isDIGIT(c) ((c) >= '0' && (c) <= '9') #ifdef EBCDIC /* In EBCDIC we do not do locales: therefore() isupper() is fine. */ # define isUPPER(c) isupper(c) # define isLOWER(c) islower(c) +# define isALNUMC(c) isalnum(c) +# define isASCII(c) isascii(c) +# define isCNTRL(c) iscntrl(c) +# define isGRAPH(c) isgraph(c) # define isPRINT(c) isprint(c) +# define isPUNCT(c) ispunct(c) +# define isXDIGIT(c) isxdigit(c) # define toUPPER(c) toupper(c) # define toLOWER(c) tolower(c) #else # define isUPPER(c) ((c) >= 'A' && (c) <= 'Z') # define isLOWER(c) ((c) >= 'a' && (c) <= 'z') -# define isPRINT(c) (((c) > 32 && (c) < 127) || isSPACE(c)) +# define isALNUMC(c) (isALPHA(c) || isDIGIT(c)) +# define isASCII(c) ((c) <= 127) +# define isCNTRL(c) ((c) < ' ' || (c) == 127) +# define isGRAPH(c) (isALNUM(c) || isPUNCT(c)) +# define isPRINT(c) (((c) > 32 && (c) < 127) || (c) == ' ') +# define isPUNCT(c) (((c) >= 33 && (c) <= 47) || ((c) >= 58 && (c) <= 64) || ((c) >= 91 && (c) <= 96) || ((c) >= 123 && (c) <= 126)) +# define isXDIGIT(c) (isDIGIT(c) || ((c) >= 'a' && (c) <= 'f') || ((c) >= 'A' && (c) <= 'F')) # define toUPPER(c) (isLOWER(c) ? (c) - ('a' - 'A') : (c)) # define toLOWER(c) (isUPPER(c) ? (c) + ('a' - 'A') : (c)) #endif @@ -229,8 +370,7 @@ typedef unsigned short U16; #ifdef USE_NEXT_CTYPE # define isALNUM_LC(c) \ - (NXIsAlpha((unsigned int)(c)) || NXIsDigit((unsigned int)(c)) || \ - (char)(c) == '_') + (NXIsAlNum((unsigned int)(c)) || (char)(c) == '_') # define isIDFIRST_LC(c) \ (NXIsAlpha((unsigned int)(c)) || (char)(c) == '_') # define isALPHA_LC(c) NXIsAlpha((unsigned int)(c)) @@ -238,43 +378,56 @@ typedef unsigned short U16; # 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 isGRAPH_LC(c) NXIsGraph((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 toLOWER_LC(c) NXToLower((unsigned int)(c)) #else /* !USE_NEXT_CTYPE */ + # if defined(CTYPE256) || (!defined(isascii) && !defined(HAS_ISASCII)) -# define isALNUM_LC(c) \ - (isalpha((unsigned char)(c)) || \ - isdigit((unsigned char)(c)) || (char)(c) == '_') +# define isALNUM_LC(c) (isalnum((unsigned char)(c)) || (char)(c) == '_') # define isIDFIRST_LC(c) (isalpha((unsigned char)(c)) || (char)(c) == '_') # define isALPHA_LC(c) isalpha((unsigned char)(c)) # define isSPACE_LC(c) isspace((unsigned char)(c)) # define isDIGIT_LC(c) isdigit((unsigned char)(c)) # define isUPPER_LC(c) isupper((unsigned char)(c)) # define isLOWER_LC(c) islower((unsigned char)(c)) +# define isALNUMC_LC(c) isalnum((unsigned char)(c)) +# define isCNTRL_LC(c) iscntrl((unsigned char)(c)) +# define isGRAPH_LC(c) isgraph((unsigned char)(c)) # define isPRINT_LC(c) isprint((unsigned char)(c)) +# define isPUNCT_LC(c) ispunct((unsigned char)(c)) # define toUPPER_LC(c) toupper((unsigned char)(c)) # define toLOWER_LC(c) tolower((unsigned char)(c)) # else -# define isALNUM_LC(c) \ - (isascii(c) && (isalpha(c) || isdigit(c) || (c) == '_')) +# 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 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 isGRAPH_LC(c) (isascii(c) && isgraph(c)) # define isPRINT_LC(c) (isascii(c) && isprint(c)) +# define isPUNCT_LC(c) (isascii(c) && ispunct(c)) # define toUPPER_LC(c) toupper(c) # define toLOWER_LC(c) tolower(c) # endif #endif /* USE_NEXT_CTYPE */ +#define isPSXSPC_LC(c) (isSPACE_LC(c) || (c) == '\v') +#define isBLANK_LC(c) isBLANK(c) /* could be wrong */ + #define isALNUM_uni(c) is_uni_alnum(c) #define isIDFIRST_uni(c) is_uni_idfirst(c) #define isALPHA_uni(c) is_uni_alpha(c) @@ -282,117 +435,216 @@ typedef unsigned short U16; #define isDIGIT_uni(c) is_uni_digit(c) #define isUPPER_uni(c) is_uni_upper(c) #define isLOWER_uni(c) is_uni_lower(c) +#define isALNUMC_uni(c) is_uni_alnumc(c) +#define isASCII_uni(c) is_uni_ascii(c) +#define isCNTRL_uni(c) is_uni_cntrl(c) +#define isGRAPH_uni(c) is_uni_graph(c) #define isPRINT_uni(c) is_uni_print(c) -#define toUPPER_uni(c) to_uni_upper(c) -#define toTITLE_uni(c) to_uni_title(c) -#define toLOWER_uni(c) to_uni_lower(c) - -#define isALNUM_LC_uni(c) (c < 256 ? isALNUM_LC(c) : is_uni_alnum_lc(c)) -#define isIDFIRST_LC_uni(c) (c < 256 ? isIDFIRST_LC(c) : is_uni_idfirst_lc(c)) -#define isALPHA_LC_uni(c) (c < 256 ? isALPHA_LC(c) : is_uni_alpha_lc(c)) -#define isSPACE_LC_uni(c) (c < 256 ? isSPACE_LC(c) : is_uni_space_lc(c)) -#define isDIGIT_LC_uni(c) (c < 256 ? isDIGIT_LC(c) : is_uni_digit_lc(c)) -#define isUPPER_LC_uni(c) (c < 256 ? isUPPER_LC(c) : is_uni_upper_lc(c)) -#define isLOWER_LC_uni(c) (c < 256 ? isLOWER_LC(c) : is_uni_lower_lc(c)) -#define isPRINT_LC_uni(c) (c < 256 ? isPRINT_LC(c) : is_uni_print_lc(c)) -#define toUPPER_LC_uni(c) (c < 256 ? toUPPER_LC(c) : to_uni_upper_lc(c)) -#define toTITLE_LC_uni(c) (c < 256 ? toUPPER_LC(c) : to_uni_title_lc(c)) -#define toLOWER_LC_uni(c) (c < 256 ? toLOWER_LC(c) : to_uni_lower_lc(c)) +#define isPUNCT_uni(c) is_uni_punct(c) +#define isXDIGIT_uni(c) is_uni_xdigit(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 isPSXSPC_uni(c) (isSPACE_uni(c) ||(c) == '\f') +#define isBLANK_uni(c) isBLANK(c) /* could be wrong */ + +#define isALNUM_LC_uvchr(c) (c < 256 ? isALNUM_LC(c) : is_uni_alnum_lc(c)) +#define isIDFIRST_LC_uvchr(c) (c < 256 ? isIDFIRST_LC(c) : is_uni_idfirst_lc(c)) +#define isALPHA_LC_uvchr(c) (c < 256 ? isALPHA_LC(c) : is_uni_alpha_lc(c)) +#define isSPACE_LC_uvchr(c) (c < 256 ? isSPACE_LC(c) : is_uni_space_lc(c)) +#define isDIGIT_LC_uvchr(c) (c < 256 ? isDIGIT_LC(c) : is_uni_digit_lc(c)) +#define isUPPER_LC_uvchr(c) (c < 256 ? isUPPER_LC(c) : is_uni_upper_lc(c)) +#define isLOWER_LC_uvchr(c) (c < 256 ? isLOWER_LC(c) : is_uni_lower_lc(c)) +#define isALNUMC_LC_uvchr(c) (c < 256 ? isALNUMC_LC(c) : is_uni_alnumc_lc(c)) +#define isCNTRL_LC_uvchr(c) (c < 256 ? isCNTRL_LC(c) : is_uni_cntrl_lc(c)) +#define isGRAPH_LC_uvchr(c) (c < 256 ? isGRAPH_LC(c) : is_uni_graph_lc(c)) +#define isPRINT_LC_uvchr(c) (c < 256 ? isPRINT_LC(c) : is_uni_print_lc(c)) +#define isPUNCT_LC_uvchr(c) (c < 256 ? isPUNCT_LC(c) : is_uni_punct_lc(c)) + +#define isPSXSPC_LC_uni(c) (isSPACE_LC_uni(c) ||(c) == '\f') +#define isBLANK_LC_uni(c) isBLANK(c) /* could be wrong */ #define isALNUM_utf8(p) is_utf8_alnum(p) -#define isIDFIRST_utf8(p) is_utf8_idfirst(p) +/* The ID_Start of Unicode is quite limiting: it assumes a L-class + * character (meaning that you cannot have, say, a CJK character). + * Instead, let's allow ID_Continue but not digits. */ +#define isIDFIRST_utf8(p) (is_utf8_idcont(p) && !is_utf8_digit(p)) #define isALPHA_utf8(p) is_utf8_alpha(p) #define isSPACE_utf8(p) is_utf8_space(p) #define isDIGIT_utf8(p) is_utf8_digit(p) #define isUPPER_utf8(p) is_utf8_upper(p) #define isLOWER_utf8(p) is_utf8_lower(p) +#define isALNUMC_utf8(p) is_utf8_alnumc(p) +#define isASCII_utf8(p) is_utf8_ascii(p) +#define isCNTRL_utf8(p) is_utf8_cntrl(p) +#define isGRAPH_utf8(p) is_utf8_graph(p) #define isPRINT_utf8(p) is_utf8_print(p) -#define toUPPER_utf8(p) to_utf8_upper(p) -#define toTITLE_utf8(p) to_utf8_title(p) -#define toLOWER_utf8(p) to_utf8_lower(p) - -#define isALNUM_LC_utf8(p) isALNUM_LC_uni(utf8_to_uv(p, 0)) -#define isIDFIRST_LC_utf8(p) isIDFIRST_LC_uni(utf8_to_uv(p, 0)) -#define isALPHA_LC_utf8(p) isALPHA_LC_uni(utf8_to_uv(p, 0)) -#define isSPACE_LC_utf8(p) isSPACE_LC_uni(utf8_to_uv(p, 0)) -#define isDIGIT_LC_utf8(p) isDIGIT_LC_uni(utf8_to_uv(p, 0)) -#define isUPPER_LC_utf8(p) isUPPER_LC_uni(utf8_to_uv(p, 0)) -#define isLOWER_LC_utf8(p) isLOWER_LC_uni(utf8_to_uv(p, 0)) -#define isPRINT_LC_utf8(p) isPRINT_LC_uni(utf8_to_uv(p, 0)) -#define toUPPER_LC_utf8(p) toUPPER_LC_uni(utf8_to_uv(p, 0)) -#define toTITLE_LC_utf8(p) toTITLE_LC_uni(utf8_to_uv(p, 0)) -#define toLOWER_LC_utf8(p) toLOWER_LC_uni(utf8_to_uv(p, 0)) +#define isPUNCT_utf8(p) is_utf8_punct(p) +#define isXDIGIT_utf8(p) is_utf8_xdigit(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 toLOWER_utf8(p,s,l) to_utf8_lower(p,s,l) + +#define isPSXSPC_utf8(c) (isSPACE_utf8(c) ||(c) == '\f') +#define isBLANK_utf8(c) isBLANK(c) /* could be wrong */ + +#define isALNUM_LC_utf8(p) isALNUM_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isIDFIRST_LC_utf8(p) isIDFIRST_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isALPHA_LC_utf8(p) isALPHA_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isSPACE_LC_utf8(p) isSPACE_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isDIGIT_LC_utf8(p) isDIGIT_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isUPPER_LC_utf8(p) isUPPER_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isLOWER_LC_utf8(p) isLOWER_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isALNUMC_LC_utf8(p) isALNUMC_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isCNTRL_LC_utf8(p) isCNTRL_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isGRAPH_LC_utf8(p) isGRAPH_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isPRINT_LC_utf8(p) isPRINT_LC_uvchr(utf8_to_uvchr(p, 0)) +#define isPUNCT_LC_utf8(p) isPUNCT_LC_uvchr(utf8_to_uvchr(p, 0)) + +#define isPSXSPC_LC_utf8(c) (isSPACE_LC_utf8(c) ||(c) == '\f') +#define isBLANK_LC_utf8(c) isBLANK(c) /* could be wrong */ #ifdef EBCDIC -EXT int ebcdic_control _((int)); -# define toCTRL(c) ebcdic_control(c) +# ifdef PERL_IMPLICIT_CONTEXT +# define toCTRL(c) Perl_ebcdic_control(aTHX_ c) +# else +# define toCTRL Perl_ebcdic_control +# endif #else /* This conversion works both ways, strangely enough. */ # define toCTRL(c) (toUPPER(c) ^ 64) #endif -/* Line numbers are unsigned, 16 bits. */ -typedef U16 line_t; +/* Line numbers are unsigned, 32 bits. */ +typedef U32 line_t; #ifdef lint #define NOLINE ((line_t)0) #else -#define NOLINE ((line_t) 65535) +#define NOLINE ((line_t) 4294967295UL) #endif -/* This looks obsolete (IZ): +/* +=head1 SV Manipulation Functions + +=for apidoc Am|SV*|NEWSV|int id|STRLEN len +Creates a new SV. A non-zero C parameter indicates the number of +bytes of preallocated string space the SV should have. An extra byte for a +tailing NUL is also reserved. (SvPOK is not set for the SV even if string +space is allocated.) The reference count for the new SV is set to 1. +C is an integer id between 0 and 1299 (used to identify leaks). - XXX LEAKTEST doesn't really work in perl5. There are direct calls to - safemalloc() in the source, so LEAKTEST won't pick them up. - Further, if you try LEAKTEST, you'll also end up calling - Safefree, which might call safexfree() on some things that weren't - malloced with safexmalloc. The correct "fix" to this, if anyone - is interested, is to ensure that all calls go through the New and - Renew macros. - --Andy Dougherty August 1996 -*/ +=head1 Memory Management + +=for apidoc Am|void|New|int id|void* ptr|int nitems|type +The XSUB-writer's interface to the C C function. + +=for apidoc Am|void|Newc|int id|void* ptr|int nitems|type|cast +The XSUB-writer's interface to the C C function, with +cast. + +=for apidoc Am|void|Newz|int id|void* ptr|int nitems|type +The XSUB-writer's interface to the C C function. The allocated +memory is zeroed with C. + +=for apidoc Am|void|Renew|void* ptr|int nitems|type +The XSUB-writer's interface to the C C function. + +=for apidoc Am|void|Renewc|void* ptr|int nitems|type|cast +The XSUB-writer's interface to the C C function, with +cast. + +=for apidoc Am|void|Safefree|void* ptr +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. + +=for apidoc Am|void *|MoveD|void* src|void* dest|int nitems|type +Like C but returns dest. Useful for encouraging compilers to tail-call +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. + +=for apidoc Am|void *|CopyD|void* src|void* dest|int nitems|type + +Like C but returns dest. Useful for encouraging compilers to tail-call +optimise. + +=for apidoc Am|void|Zero|void* dest|int nitems|type + +The XSUB-writer's interface to the C C function. The C is the +destination, C is the number of items, and C is the type. + +=for apidoc Am|void *|ZeroD|void* dest|int nitems|type + +Like C but returns dest. Useful for encouraging compilers to tail-call +optimise. + +=for apidoc Am|void|StructCopy|type src|type dest|type +This is an architecture-independent macro to copy one structure to another. + +=for apidoc Am|void|Poison|void* dest|int nitems|type + +Fill up memory with a pattern (byte 0xAB over and over again) that +hopefully catches attempts to access uninitialized memory. + +=cut */ #ifndef lint #define NEWSV(x,len) newSV(len) -#ifndef LEAKTEST +#ifdef PERL_MALLOC_WRAP +#define MEM_WRAP_CHECK(n,t) \ + (void)((n)>((MEM_SIZE)~0)/sizeof(t)?(Perl_croak_nocontext(PL_memory_wrap),0):0) +#define MEM_WRAP_CHECK_1(n,t,a) \ + (void)((n)>((MEM_SIZE)~0)/sizeof(t)?(Perl_croak_nocontext(a),0):0) +#define MEM_WRAP_CHECK_2(n,t,a,b) \ + (void)((n)>((MEM_SIZE)~0)/sizeof(t)?(Perl_croak_nocontext(a,b),0):0) +#define MEM_WRAP_CHECK_(n,t) MEM_WRAP_CHECK(n,t), -#define New(x,v,n,t) (v = (t*)safemalloc((MEM_SIZE)((n)*sizeof(t)))) -#define Newc(x,v,n,t,c) (v = (c*)safemalloc((MEM_SIZE)((n)*sizeof(t)))) -#define Newz(x,v,n,t) (v = (t*)safemalloc((MEM_SIZE)((n)*sizeof(t)))), \ - memzero((char*)(v), (n)*sizeof(t)) -#define Renew(v,n,t) \ - (v = (t*)saferealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t)))) -#define Renewc(v,n,t,c) \ - (v = (c*)saferealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t)))) -#define Safefree(d) safefree((Malloc_t)(d)) +#else -#else /* LEAKTEST */ +#define MEM_WRAP_CHECK(n,t) +#define MEM_WRAP_CHECK_1(n,t,a) +#define MEM_WRAP_CHECK_2(n,t,a,b) +#define MEM_WRAP_CHECK_(n,t) -#define New(x,v,n,t) (v = (t*)safexmalloc((x),(MEM_SIZE)((n)*sizeof(t)))) -#define Newc(x,v,n,t,c) (v = (c*)safexmalloc((x),(MEM_SIZE)((n)*sizeof(t)))) -#define Newz(x,v,n,t) (v = (t*)safexmalloc((x),(MEM_SIZE)((n)*sizeof(t)))), \ - memzero((char*)(v), (n)*sizeof(t)) +#endif + + +#define New(x,v,n,t) (v = (MEM_WRAP_CHECK_(n,t) (t*)safemalloc((MEM_SIZE)((n)*sizeof(t))))) +#define Newc(x,v,n,t,c) (v = (MEM_WRAP_CHECK_(n,t) (c*)safemalloc((MEM_SIZE)((n)*sizeof(t))))) +#define Newz(x,v,n,t) (v = (MEM_WRAP_CHECK_(n,t) (t*)safemalloc((MEM_SIZE)((n)*sizeof(t))))), \ + memzero((char*)(v), (n)*sizeof(t)) #define Renew(v,n,t) \ - (v = (t*)safexrealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t)))) + (v = (MEM_WRAP_CHECK_(n,t) (t*)saferealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t))))) #define Renewc(v,n,t,c) \ - (v = (c*)safexrealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t)))) -#define Safefree(d) safexfree((Malloc_t)(d)) + (v = (MEM_WRAP_CHECK_(n,t) (c*)saferealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t))))) +#define Safefree(d) safefree((Malloc_t)(d)) -#define MAXXCOUNT 1400 -#define MAXY_SIZE 80 -#define MAXYCOUNT 16 /* (MAXY_SIZE/4 + 1) */ -extern long xcount[MAXXCOUNT]; -extern long lastxcount[MAXXCOUNT]; -extern long xycount[MAXXCOUNT][MAXYCOUNT]; -extern long lastxycount[MAXXCOUNT][MAXYCOUNT]; +#define Move(s,d,n,t) (MEM_WRAP_CHECK_(n,t) (void)memmove((char*)(d),(const char*)(s), (n) * sizeof(t))) +#define Copy(s,d,n,t) (MEM_WRAP_CHECK_(n,t) (void)memcpy((char*)(d),(const char*)(s), (n) * sizeof(t))) +#define Zero(d,n,t) (MEM_WRAP_CHECK_(n,t) (void)memzero((char*)(d), (n) * sizeof(t))) -#endif /* LEAKTEST */ +#define MoveD(s,d,n,t) (MEM_WRAP_CHECK_(n,t) memmove((char*)(d),(const char*)(s), (n) * sizeof(t))) +#define CopyD(s,d,n,t) (MEM_WRAP_CHECK_(n,t) memcpy((char*)(d),(const char*)(s), (n) * sizeof(t))) +#ifdef HAS_MEMSET +#define ZeroD(d,n,t) (MEM_WRAP_CHECK_(n,t) memzero((char*)(d), (n) * sizeof(t))) +#else +/* Using bzero(), which returns void. */ +#define ZeroD(d,n,t) (MEM_WRAP_CHECK_(n,t) memzero((char*)(d), (n) * sizeof(t)),d) +#endif -#define Move(s,d,n,t) (void)memmove((char*)(d),(char*)(s), (n) * sizeof(t)) -#define Copy(s,d,n,t) (void)memcpy((char*)(d),(char*)(s), (n) * sizeof(t)) -#define Zero(d,n,t) (void)memzero((char*)(d), (n) * sizeof(t)) +#define Poison(d,n,t) (MEM_WRAP_CHECK_(n,t) (void)memset((char*)(d), 0xAB, (n) * sizeof(t))) #else /* lint */ @@ -403,6 +655,10 @@ extern long lastxycount[MAXXCOUNT][MAXYCOUNT]; #define Move(s,d,n,t) #define Copy(s,d,n,t) #define Zero(d,n,t) +#define MoveD(s,d,n,t) d +#define CopyD(s,d,n,t) d +#define ZeroD(d,n,t) d +#define Poison(d,n,t) #define Safefree(d) (d) = (d) #endif /* lint */ @@ -412,3 +668,34 @@ extern long lastxycount[MAXXCOUNT][MAXYCOUNT]; #else #define StructCopy(s,d,t) Copy(s,d,1,t) #endif + +#define C_ARRAY_LENGTH(a) (sizeof(a)/sizeof((a)[0])) + +#ifdef NEED_VA_COPY +# ifdef va_copy +# define Perl_va_copy(s, d) va_copy(d, s) +# else +# if defined(__va_copy) +# define Perl_va_copy(s, d) __va_copy(d, s) +# else +# define Perl_va_copy(s, d) Copy(s, d, 1, va_list) +# endif +# endif +#endif + +/* convenience debug macros */ +#ifdef USE_ITHREADS +#define pTHX_FORMAT "Perl interpreter: 0x%p" +#define pTHX__FORMAT ", Perl interpreter: 0x%p" +#define pTHX_VALUE_ (void *)my_perl, +#define pTHX_VALUE (void *)my_perl +#define pTHX__VALUE_ ,(void *)my_perl, +#define pTHX__VALUE ,(void *)my_perl +#else +#define pTHX_FORMAT +#define pTHX__FORMAT +#define pTHX_VALUE_ +#define pTHX_VALUE +#define pTHX__VALUE_ +#define pTHX__VALUE +#endif /* USE_ITHREADS */