X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/0e06870bf080a38cda51c06c6612359afc2334e1..090f71652b598badef32b379c0f36c2c6e4a9542:/handy.h diff --git a/handy.h b/handy.h index 9d7e096..94798f4 100644 --- a/handy.h +++ b/handy.h @@ -1,6 +1,7 @@ /* handy.h * - * Copyright (c) 1991-2001, Larry Wall + * Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1999, + * 2000, 2001, 2002, 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. @@ -21,7 +22,9 @@ #define Null(type) ((type)NULL) /* -=for apidoc AmU||Nullch +=head1 Handy Values + +=for apidoc AmU||Nullch Null character pointer. =for apidoc AmU||Nullsv @@ -116,6 +119,14 @@ Null SV pointer. #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; @@ -165,7 +176,11 @@ typedef U64TYPE U64; #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 @@ -194,6 +209,7 @@ typedef U64TYPE U64; #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 */ @@ -201,6 +217,8 @@ typedef U64TYPE U64; #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. @@ -274,6 +292,9 @@ C). #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. @@ -332,9 +353,9 @@ Converts the specified character to lowercase. # define isLOWER(c) ((c) >= 'a' && (c) <= 'z') # define isALNUMC(c) (isALPHA(c) || isDIGIT(c)) # define isASCII(c) ((c) <= 127) -# define isCNTRL(c) ((c) < ' ') +# define isCNTRL(c) ((c) < ' ' || (c) == 127) # define isGRAPH(c) (isALNUM(c) || isPUNCT(c)) -# define isPRINT(c) (((c) > 32 && (c) < 127) || isSPACE(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)) @@ -416,34 +437,35 @@ Converts the specified character to lowercase. #define isPRINT_uni(c) is_uni_print(c) #define isPUNCT_uni(c) is_uni_punct(c) #define isXDIGIT_uni(c) is_uni_xdigit(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 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_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 isALNUMC_LC_uni(c) (c < 256 ? isALNUMC_LC(c) : is_uni_alnumc_lc(c)) -#define isCNTRL_LC_uni(c) (c < 256 ? isCNTRL_LC(c) : is_uni_cntrl_lc(c)) -#define isGRAPH_LC_uni(c) (c < 256 ? isGRAPH_LC(c) : is_uni_graph_lc(c)) -#define isPRINT_LC_uni(c) (c < 256 ? isPRINT_LC(c) : is_uni_print_lc(c)) -#define isPUNCT_LC_uni(c) (c < 256 ? isPUNCT_LC(c) : is_uni_punct_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 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) @@ -456,62 +478,52 @@ Converts the specified character to lowercase. #define isPRINT_utf8(p) is_utf8_print(p) #define isPUNCT_utf8(p) is_utf8_punct(p) #define isXDIGIT_utf8(p) is_utf8_xdigit(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 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_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isIDFIRST_LC_utf8(p) isIDFIRST_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isALPHA_LC_utf8(p) isALPHA_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isSPACE_LC_utf8(p) isSPACE_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isDIGIT_LC_utf8(p) isDIGIT_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isUPPER_LC_utf8(p) isUPPER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isLOWER_LC_utf8(p) isLOWER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isALNUMC_LC_utf8(p) isALNUMC_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isCNTRL_LC_utf8(p) isCNTRL_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isGRAPH_LC_utf8(p) isGRAPH_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isPRINT_LC_utf8(p) isPRINT_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define isPUNCT_LC_utf8(p) isPUNCT_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define toUPPER_LC_utf8(p) toUPPER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define toTITLE_LC_utf8(p) toTITLE_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) -#define toLOWER_LC_utf8(p) toLOWER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0)) +#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 /* - XXX LEAKTEST doesn't really work in perl5. There are direct calls to - safemalloc() in the source, so LEAKTEST won't pick them up. - (The main "offenders" are extensions.) - 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 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 @@ -519,6 +531,8 @@ 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). +=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. @@ -558,15 +572,17 @@ destination, C is the number of items, and C is the type. =for apidoc Am|void|StructCopy|type src|type dest|type This is an architecture-independent macro to copy one structure to another. -=cut -*/ +=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 - #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)))), \ @@ -577,32 +593,12 @@ This is an architecture-independent macro to copy one structure to another. (v = (c*)saferealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t)))) #define Safefree(d) safefree((Malloc_t)(d)) -#else /* LEAKTEST */ - -#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)) -#define Renew(v,n,t) \ - (v = (t*)safexrealloc((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)) - -#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]; - -#endif /* LEAKTEST */ - #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) (void)memset((char*)(d), 0xAB, (n) * sizeof(t)) + #else /* lint */ #define New(x,v,n,s) (v = Null(s *)) @@ -612,6 +608,7 @@ extern long lastxycount[MAXXCOUNT][MAXYCOUNT]; #define Move(s,d,n,t) #define Copy(s,d,n,t) #define Zero(d,n,t) +#define Poison(d,n,t) #define Safefree(d) (d) = (d) #endif /* lint */ @@ -622,13 +619,17 @@ extern long lastxycount[MAXXCOUNT][MAXYCOUNT]; #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) -# elif 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) +# 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