| 1 | /* handy.h |
| 2 | * |
| 3 | * Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1999, |
| 4 | * 2000, 2001, 2002, by Larry Wall and others |
| 5 | * |
| 6 | * You may distribute under the terms of either the GNU General Public |
| 7 | * License or the Artistic License, as specified in the README file. |
| 8 | * |
| 9 | */ |
| 10 | |
| 11 | #if !defined(__STDC__) |
| 12 | #ifdef NULL |
| 13 | #undef NULL |
| 14 | #endif |
| 15 | #ifndef I286 |
| 16 | # define NULL 0 |
| 17 | #else |
| 18 | # define NULL 0L |
| 19 | #endif |
| 20 | #endif |
| 21 | |
| 22 | #define Null(type) ((type)NULL) |
| 23 | |
| 24 | /* |
| 25 | =head1 Handy Values |
| 26 | |
| 27 | =for apidoc AmU||Nullch |
| 28 | Null character pointer. |
| 29 | |
| 30 | =for apidoc AmU||Nullsv |
| 31 | Null SV pointer. |
| 32 | |
| 33 | =cut |
| 34 | */ |
| 35 | |
| 36 | #define Nullch Null(char*) |
| 37 | #define Nullfp Null(PerlIO*) |
| 38 | #define Nullsv Null(SV*) |
| 39 | |
| 40 | #ifdef TRUE |
| 41 | #undef TRUE |
| 42 | #endif |
| 43 | #ifdef FALSE |
| 44 | #undef FALSE |
| 45 | #endif |
| 46 | #define TRUE (1) |
| 47 | #define FALSE (0) |
| 48 | |
| 49 | |
| 50 | /* XXX Configure ought to have a test for a boolean type, if I can |
| 51 | just figure out all the headers such a test needs. |
| 52 | Andy Dougherty August 1996 |
| 53 | */ |
| 54 | /* bool is built-in for g++-2.6.3 and later, which might be used |
| 55 | for extensions. <_G_config.h> defines _G_HAVE_BOOL, but we can't |
| 56 | be sure _G_config.h will be included before this file. _G_config.h |
| 57 | also defines _G_HAVE_BOOL for both gcc and g++, but only g++ |
| 58 | actually has bool. Hence, _G_HAVE_BOOL is pretty useless for us. |
| 59 | g++ can be identified by __GNUG__. |
| 60 | Andy Dougherty February 2000 |
| 61 | */ |
| 62 | #ifdef __GNUG__ /* GNU g++ has bool built-in */ |
| 63 | # ifndef HAS_BOOL |
| 64 | # define HAS_BOOL 1 |
| 65 | # endif |
| 66 | #endif |
| 67 | |
| 68 | /* The NeXT dynamic loader headers will not build with the bool macro |
| 69 | So declare them now to clear confusion. |
| 70 | */ |
| 71 | #if defined(NeXT) || defined(__NeXT__) |
| 72 | # undef FALSE |
| 73 | # undef TRUE |
| 74 | typedef enum bool { FALSE = 0, TRUE = 1 } bool; |
| 75 | # define ENUM_BOOL 1 |
| 76 | # ifndef HAS_BOOL |
| 77 | # define HAS_BOOL 1 |
| 78 | # endif /* !HAS_BOOL */ |
| 79 | #endif /* NeXT || __NeXT__ */ |
| 80 | |
| 81 | #ifndef HAS_BOOL |
| 82 | # if defined(UTS) || defined(VMS) |
| 83 | # define bool int |
| 84 | # else |
| 85 | # define bool char |
| 86 | # endif |
| 87 | # define HAS_BOOL 1 |
| 88 | #endif |
| 89 | |
| 90 | /* XXX A note on the perl source internal type system. The |
| 91 | original intent was that I32 be *exactly* 32 bits. |
| 92 | |
| 93 | Currently, we only guarantee that I32 is *at least* 32 bits. |
| 94 | Specifically, if int is 64 bits, then so is I32. (This is the case |
| 95 | for the Cray.) This has the advantage of meshing nicely with |
| 96 | standard library calls (where we pass an I32 and the library is |
| 97 | expecting an int), but the disadvantage that an I32 is not 32 bits. |
| 98 | Andy Dougherty August 1996 |
| 99 | |
| 100 | There is no guarantee that there is *any* integral type with |
| 101 | exactly 32 bits. It is perfectly legal for a system to have |
| 102 | sizeof(short) == sizeof(int) == sizeof(long) == 8. |
| 103 | |
| 104 | Similarly, there is no guarantee that I16 and U16 have exactly 16 |
| 105 | bits. |
| 106 | |
| 107 | For dealing with issues that may arise from various 32/64-bit |
| 108 | systems, we will ask Configure to check out |
| 109 | |
| 110 | SHORTSIZE == sizeof(short) |
| 111 | INTSIZE == sizeof(int) |
| 112 | LONGSIZE == sizeof(long) |
| 113 | LONGLONGSIZE == sizeof(long long) (if HAS_LONG_LONG) |
| 114 | PTRSIZE == sizeof(void *) |
| 115 | DOUBLESIZE == sizeof(double) |
| 116 | LONG_DOUBLESIZE == sizeof(long double) (if HAS_LONG_DOUBLE). |
| 117 | |
| 118 | */ |
| 119 | |
| 120 | #ifdef I_INTTYPES /* e.g. Linux has int64_t without <inttypes.h> */ |
| 121 | # include <inttypes.h> |
| 122 | # ifdef INT32_MIN_BROKEN |
| 123 | # undef INT32_MIN |
| 124 | # define INT32_MIN (-2147483647-1) |
| 125 | # endif |
| 126 | # ifdef INT64_MIN_BROKEN |
| 127 | # undef INT64_MIN |
| 128 | # define INT64_MIN (-9223372036854775807LL-1) |
| 129 | # endif |
| 130 | #endif |
| 131 | |
| 132 | typedef I8TYPE I8; |
| 133 | typedef U8TYPE U8; |
| 134 | typedef I16TYPE I16; |
| 135 | typedef U16TYPE U16; |
| 136 | typedef I32TYPE I32; |
| 137 | typedef U32TYPE U32; |
| 138 | #ifdef PERL_CORE |
| 139 | # ifdef HAS_QUAD |
| 140 | typedef I64TYPE I64; |
| 141 | typedef U64TYPE U64; |
| 142 | # endif |
| 143 | #endif /* PERL_CORE */ |
| 144 | |
| 145 | #if defined(HAS_QUAD) && defined(USE_64_BIT_INT) |
| 146 | # ifndef UINT64_C /* usually from <inttypes.h> */ |
| 147 | # if defined(HAS_LONG_LONG) && QUADKIND == QUAD_IS_LONG_LONG |
| 148 | # define INT64_C(c) CAT2(c,LL) |
| 149 | # define UINT64_C(c) CAT2(c,ULL) |
| 150 | # else |
| 151 | # if LONGSIZE == 8 && QUADKIND == QUAD_IS_LONG |
| 152 | # define INT64_C(c) CAT2(c,L) |
| 153 | # define UINT64_C(c) CAT2(c,UL) |
| 154 | # else |
| 155 | # define INT64_C(c) ((I64TYPE)(c)) |
| 156 | # define UINT64_C(c) ((U64TYPE)(c)) |
| 157 | # endif |
| 158 | # endif |
| 159 | # endif |
| 160 | #endif |
| 161 | |
| 162 | /* Mention I8SIZE, U8SIZE, I16SIZE, U16SIZE, I32SIZE, U32SIZE, |
| 163 | I64SIZE, and U64SIZE here so that metaconfig pulls them in. */ |
| 164 | |
| 165 | #if defined(UINT8_MAX) && defined(INT16_MAX) && defined(INT32_MAX) |
| 166 | |
| 167 | /* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type. |
| 168 | Please search CHAR_MAX in perl.h for further details. */ |
| 169 | #define U8_MAX UINT8_MAX |
| 170 | #define U8_MIN UINT8_MIN |
| 171 | |
| 172 | #define I16_MAX INT16_MAX |
| 173 | #define I16_MIN INT16_MIN |
| 174 | #define U16_MAX UINT16_MAX |
| 175 | #define U16_MIN UINT16_MIN |
| 176 | |
| 177 | #define I32_MAX INT32_MAX |
| 178 | #define I32_MIN INT32_MIN |
| 179 | #ifndef UINT32_MAX_BROKEN /* e.g. HP-UX with gcc messes this up */ |
| 180 | # define U32_MAX UINT32_MAX |
| 181 | #else |
| 182 | # define U32_MAX 4294967295U |
| 183 | #endif |
| 184 | #define U32_MIN UINT32_MIN |
| 185 | |
| 186 | #else |
| 187 | |
| 188 | /* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type. |
| 189 | Please search CHAR_MAX in perl.h for further details. */ |
| 190 | #define U8_MAX PERL_UCHAR_MAX |
| 191 | #define U8_MIN PERL_UCHAR_MIN |
| 192 | |
| 193 | #define I16_MAX PERL_SHORT_MAX |
| 194 | #define I16_MIN PERL_SHORT_MIN |
| 195 | #define U16_MAX PERL_USHORT_MAX |
| 196 | #define U16_MIN PERL_USHORT_MIN |
| 197 | |
| 198 | #if LONGSIZE > 4 |
| 199 | # define I32_MAX PERL_INT_MAX |
| 200 | # define I32_MIN PERL_INT_MIN |
| 201 | # define U32_MAX PERL_UINT_MAX |
| 202 | # define U32_MIN PERL_UINT_MIN |
| 203 | #else |
| 204 | # define I32_MAX PERL_LONG_MAX |
| 205 | # define I32_MIN PERL_LONG_MIN |
| 206 | # define U32_MAX PERL_ULONG_MAX |
| 207 | # define U32_MIN PERL_ULONG_MIN |
| 208 | #endif |
| 209 | |
| 210 | #endif |
| 211 | |
| 212 | /* log(2) is pretty close to 0.30103, just in case anyone is grepping for it */ |
| 213 | #define BIT_DIGITS(N) (((N)*146)/485 + 1) /* log2(10) =~ 146/485 */ |
| 214 | #define TYPE_DIGITS(T) BIT_DIGITS(sizeof(T) * 8) |
| 215 | #define TYPE_CHARS(T) (TYPE_DIGITS(T) + 2) /* sign, NUL */ |
| 216 | |
| 217 | #define Ctl(ch) ((ch) & 037) |
| 218 | |
| 219 | /* |
| 220 | =head1 Miscellaneous Functions |
| 221 | |
| 222 | =for apidoc Am|bool|strNE|char* s1|char* s2 |
| 223 | Test two strings to see if they are different. Returns true or |
| 224 | false. |
| 225 | |
| 226 | =for apidoc Am|bool|strEQ|char* s1|char* s2 |
| 227 | Test two strings to see if they are equal. Returns true or false. |
| 228 | |
| 229 | =for apidoc Am|bool|strLT|char* s1|char* s2 |
| 230 | Test two strings to see if the first, C<s1>, is less than the second, |
| 231 | C<s2>. Returns true or false. |
| 232 | |
| 233 | =for apidoc Am|bool|strLE|char* s1|char* s2 |
| 234 | Test two strings to see if the first, C<s1>, is less than or equal to the |
| 235 | second, C<s2>. Returns true or false. |
| 236 | |
| 237 | =for apidoc Am|bool|strGT|char* s1|char* s2 |
| 238 | Test two strings to see if the first, C<s1>, is greater than the second, |
| 239 | C<s2>. Returns true or false. |
| 240 | |
| 241 | =for apidoc Am|bool|strGE|char* s1|char* s2 |
| 242 | Test two strings to see if the first, C<s1>, is greater than or equal to |
| 243 | the second, C<s2>. Returns true or false. |
| 244 | |
| 245 | =for apidoc Am|bool|strnNE|char* s1|char* s2|STRLEN len |
| 246 | Test two strings to see if they are different. The C<len> parameter |
| 247 | indicates the number of bytes to compare. Returns true or false. (A |
| 248 | wrapper for C<strncmp>). |
| 249 | |
| 250 | =for apidoc Am|bool|strnEQ|char* s1|char* s2|STRLEN len |
| 251 | Test two strings to see if they are equal. The C<len> parameter indicates |
| 252 | the number of bytes to compare. Returns true or false. (A wrapper for |
| 253 | C<strncmp>). |
| 254 | |
| 255 | =cut |
| 256 | */ |
| 257 | |
| 258 | #define strNE(s1,s2) (strcmp(s1,s2)) |
| 259 | #define strEQ(s1,s2) (!strcmp(s1,s2)) |
| 260 | #define strLT(s1,s2) (strcmp(s1,s2) < 0) |
| 261 | #define strLE(s1,s2) (strcmp(s1,s2) <= 0) |
| 262 | #define strGT(s1,s2) (strcmp(s1,s2) > 0) |
| 263 | #define strGE(s1,s2) (strcmp(s1,s2) >= 0) |
| 264 | #define strnNE(s1,s2,l) (strncmp(s1,s2,l)) |
| 265 | #define strnEQ(s1,s2,l) (!strncmp(s1,s2,l)) |
| 266 | |
| 267 | #ifdef HAS_MEMCMP |
| 268 | # define memNE(s1,s2,l) (memcmp(s1,s2,l)) |
| 269 | # define memEQ(s1,s2,l) (!memcmp(s1,s2,l)) |
| 270 | #else |
| 271 | # define memNE(s1,s2,l) (bcmp(s1,s2,l)) |
| 272 | # define memEQ(s1,s2,l) (!bcmp(s1,s2,l)) |
| 273 | #endif |
| 274 | |
| 275 | /* |
| 276 | * Character classes. |
| 277 | * |
| 278 | * Unfortunately, the introduction of locales means that we |
| 279 | * can't trust isupper(), etc. to tell the truth. And when |
| 280 | * it comes to /\w+/ with tainting enabled, we *must* be able |
| 281 | * to trust our character classes. |
| 282 | * |
| 283 | * Therefore, the default tests in the text of Perl will be |
| 284 | * independent of locale. Any code that wants to depend on |
| 285 | * the current locale will use the tests that begin with "lc". |
| 286 | */ |
| 287 | |
| 288 | #ifdef HAS_SETLOCALE /* XXX Is there a better test for this? */ |
| 289 | # ifndef CTYPE256 |
| 290 | # define CTYPE256 |
| 291 | # endif |
| 292 | #endif |
| 293 | |
| 294 | /* |
| 295 | |
| 296 | =head1 Character classes |
| 297 | |
| 298 | =for apidoc Am|bool|isALNUM|char ch |
| 299 | Returns a boolean indicating whether the C C<char> is an ASCII alphanumeric |
| 300 | character (including underscore) or digit. |
| 301 | |
| 302 | =for apidoc Am|bool|isALPHA|char ch |
| 303 | Returns a boolean indicating whether the C C<char> is an ASCII alphabetic |
| 304 | character. |
| 305 | |
| 306 | =for apidoc Am|bool|isSPACE|char ch |
| 307 | Returns a boolean indicating whether the C C<char> is whitespace. |
| 308 | |
| 309 | =for apidoc Am|bool|isDIGIT|char ch |
| 310 | Returns a boolean indicating whether the C C<char> is an ASCII |
| 311 | digit. |
| 312 | |
| 313 | =for apidoc Am|bool|isUPPER|char ch |
| 314 | Returns a boolean indicating whether the C C<char> is an uppercase |
| 315 | character. |
| 316 | |
| 317 | =for apidoc Am|bool|isLOWER|char ch |
| 318 | Returns a boolean indicating whether the C C<char> is a lowercase |
| 319 | character. |
| 320 | |
| 321 | =for apidoc Am|char|toUPPER|char ch |
| 322 | Converts the specified character to uppercase. |
| 323 | |
| 324 | =for apidoc Am|char|toLOWER|char ch |
| 325 | Converts the specified character to lowercase. |
| 326 | |
| 327 | =cut |
| 328 | */ |
| 329 | |
| 330 | #define isALNUM(c) (isALPHA(c) || isDIGIT(c) || (c) == '_') |
| 331 | #define isIDFIRST(c) (isALPHA(c) || (c) == '_') |
| 332 | #define isALPHA(c) (isUPPER(c) || isLOWER(c)) |
| 333 | #define isSPACE(c) \ |
| 334 | ((c) == ' ' || (c) == '\t' || (c) == '\n' || (c) =='\r' || (c) == '\f') |
| 335 | #define isPSXSPC(c) (isSPACE(c) || (c) == '\v') |
| 336 | #define isBLANK(c) ((c) == ' ' || (c) == '\t') |
| 337 | #define isDIGIT(c) ((c) >= '0' && (c) <= '9') |
| 338 | #ifdef EBCDIC |
| 339 | /* In EBCDIC we do not do locales: therefore() isupper() is fine. */ |
| 340 | # define isUPPER(c) isupper(c) |
| 341 | # define isLOWER(c) islower(c) |
| 342 | # define isALNUMC(c) isalnum(c) |
| 343 | # define isASCII(c) isascii(c) |
| 344 | # define isCNTRL(c) iscntrl(c) |
| 345 | # define isGRAPH(c) isgraph(c) |
| 346 | # define isPRINT(c) isprint(c) |
| 347 | # define isPUNCT(c) ispunct(c) |
| 348 | # define isXDIGIT(c) isxdigit(c) |
| 349 | # define toUPPER(c) toupper(c) |
| 350 | # define toLOWER(c) tolower(c) |
| 351 | #else |
| 352 | # define isUPPER(c) ((c) >= 'A' && (c) <= 'Z') |
| 353 | # define isLOWER(c) ((c) >= 'a' && (c) <= 'z') |
| 354 | # define isALNUMC(c) (isALPHA(c) || isDIGIT(c)) |
| 355 | # define isASCII(c) ((c) <= 127) |
| 356 | # define isCNTRL(c) ((c) < ' ' || (c) == 127) |
| 357 | # define isGRAPH(c) (isALNUM(c) || isPUNCT(c)) |
| 358 | # define isPRINT(c) (((c) > 32 && (c) < 127) || (c) == ' ') |
| 359 | # define isPUNCT(c) (((c) >= 33 && (c) <= 47) || ((c) >= 58 && (c) <= 64) || ((c) >= 91 && (c) <= 96) || ((c) >= 123 && (c) <= 126)) |
| 360 | # define isXDIGIT(c) (isdigit(c) || ((c) >= 'a' && (c) <= 'f') || ((c) >= 'A' && (c) <= 'F')) |
| 361 | # define toUPPER(c) (isLOWER(c) ? (c) - ('a' - 'A') : (c)) |
| 362 | # define toLOWER(c) (isUPPER(c) ? (c) + ('a' - 'A') : (c)) |
| 363 | #endif |
| 364 | |
| 365 | #ifdef USE_NEXT_CTYPE |
| 366 | |
| 367 | # define isALNUM_LC(c) \ |
| 368 | (NXIsAlNum((unsigned int)(c)) || (char)(c) == '_') |
| 369 | # define isIDFIRST_LC(c) \ |
| 370 | (NXIsAlpha((unsigned int)(c)) || (char)(c) == '_') |
| 371 | # define isALPHA_LC(c) NXIsAlpha((unsigned int)(c)) |
| 372 | # define isSPACE_LC(c) NXIsSpace((unsigned int)(c)) |
| 373 | # define isDIGIT_LC(c) NXIsDigit((unsigned int)(c)) |
| 374 | # define isUPPER_LC(c) NXIsUpper((unsigned int)(c)) |
| 375 | # define isLOWER_LC(c) NXIsLower((unsigned int)(c)) |
| 376 | # define isALNUMC_LC(c) NXIsAlNum((unsigned int)(c)) |
| 377 | # define isCNTRL_LC(c) NXIsCntrl((unsigned int)(c)) |
| 378 | # define isGRAPH_LC(c) NXIsGraph((unsigned int)(c)) |
| 379 | # define isPRINT_LC(c) NXIsPrint((unsigned int)(c)) |
| 380 | # define isPUNCT_LC(c) NXIsPunct((unsigned int)(c)) |
| 381 | # define toUPPER_LC(c) NXToUpper((unsigned int)(c)) |
| 382 | # define toLOWER_LC(c) NXToLower((unsigned int)(c)) |
| 383 | |
| 384 | #else /* !USE_NEXT_CTYPE */ |
| 385 | |
| 386 | # if defined(CTYPE256) || (!defined(isascii) && !defined(HAS_ISASCII)) |
| 387 | |
| 388 | # define isALNUM_LC(c) (isalnum((unsigned char)(c)) || (char)(c) == '_') |
| 389 | # define isIDFIRST_LC(c) (isalpha((unsigned char)(c)) || (char)(c) == '_') |
| 390 | # define isALPHA_LC(c) isalpha((unsigned char)(c)) |
| 391 | # define isSPACE_LC(c) isspace((unsigned char)(c)) |
| 392 | # define isDIGIT_LC(c) isdigit((unsigned char)(c)) |
| 393 | # define isUPPER_LC(c) isupper((unsigned char)(c)) |
| 394 | # define isLOWER_LC(c) islower((unsigned char)(c)) |
| 395 | # define isALNUMC_LC(c) isalnum((unsigned char)(c)) |
| 396 | # define isCNTRL_LC(c) iscntrl((unsigned char)(c)) |
| 397 | # define isGRAPH_LC(c) isgraph((unsigned char)(c)) |
| 398 | # define isPRINT_LC(c) isprint((unsigned char)(c)) |
| 399 | # define isPUNCT_LC(c) ispunct((unsigned char)(c)) |
| 400 | # define toUPPER_LC(c) toupper((unsigned char)(c)) |
| 401 | # define toLOWER_LC(c) tolower((unsigned char)(c)) |
| 402 | |
| 403 | # else |
| 404 | |
| 405 | # define isALNUM_LC(c) (isascii(c) && (isalnum(c) || (c) == '_')) |
| 406 | # define isIDFIRST_LC(c) (isascii(c) && (isalpha(c) || (c) == '_')) |
| 407 | # define isALPHA_LC(c) (isascii(c) && isalpha(c)) |
| 408 | # define isSPACE_LC(c) (isascii(c) && isspace(c)) |
| 409 | # define isDIGIT_LC(c) (isascii(c) && isdigit(c)) |
| 410 | # define isUPPER_LC(c) (isascii(c) && isupper(c)) |
| 411 | # define isLOWER_LC(c) (isascii(c) && islower(c)) |
| 412 | # define isALNUMC_LC(c) (isascii(c) && isalnum(c)) |
| 413 | # define isCNTRL_LC(c) (isascii(c) && iscntrl(c)) |
| 414 | # define isGRAPH_LC(c) (isascii(c) && isgraph(c)) |
| 415 | # define isPRINT_LC(c) (isascii(c) && isprint(c)) |
| 416 | # define isPUNCT_LC(c) (isascii(c) && ispunct(c)) |
| 417 | # define toUPPER_LC(c) toupper(c) |
| 418 | # define toLOWER_LC(c) tolower(c) |
| 419 | |
| 420 | # endif |
| 421 | #endif /* USE_NEXT_CTYPE */ |
| 422 | |
| 423 | #define isPSXSPC_LC(c) (isSPACE_LC(c) || (c) == '\v') |
| 424 | #define isBLANK_LC(c) isBLANK(c) /* could be wrong */ |
| 425 | |
| 426 | #define isALNUM_uni(c) is_uni_alnum(c) |
| 427 | #define isIDFIRST_uni(c) is_uni_idfirst(c) |
| 428 | #define isALPHA_uni(c) is_uni_alpha(c) |
| 429 | #define isSPACE_uni(c) is_uni_space(c) |
| 430 | #define isDIGIT_uni(c) is_uni_digit(c) |
| 431 | #define isUPPER_uni(c) is_uni_upper(c) |
| 432 | #define isLOWER_uni(c) is_uni_lower(c) |
| 433 | #define isALNUMC_uni(c) is_uni_alnumc(c) |
| 434 | #define isASCII_uni(c) is_uni_ascii(c) |
| 435 | #define isCNTRL_uni(c) is_uni_cntrl(c) |
| 436 | #define isGRAPH_uni(c) is_uni_graph(c) |
| 437 | #define isPRINT_uni(c) is_uni_print(c) |
| 438 | #define isPUNCT_uni(c) is_uni_punct(c) |
| 439 | #define isXDIGIT_uni(c) is_uni_xdigit(c) |
| 440 | #define toUPPER_uni(c,s,l) to_uni_upper(c,s,l) |
| 441 | #define toTITLE_uni(c,s,l) to_uni_title(c,s,l) |
| 442 | #define toLOWER_uni(c,s,l) to_uni_lower(c,s,l) |
| 443 | #define toFOLD_uni(c,s,l) to_uni_fold(c,s,l) |
| 444 | |
| 445 | #define isPSXSPC_uni(c) (isSPACE_uni(c) ||(c) == '\f') |
| 446 | #define isBLANK_uni(c) isBLANK(c) /* could be wrong */ |
| 447 | |
| 448 | #define isALNUM_LC_uvchr(c) (c < 256 ? isALNUM_LC(c) : is_uni_alnum_lc(c)) |
| 449 | #define isIDFIRST_LC_uvchr(c) (c < 256 ? isIDFIRST_LC(c) : is_uni_idfirst_lc(c)) |
| 450 | #define isALPHA_LC_uvchr(c) (c < 256 ? isALPHA_LC(c) : is_uni_alpha_lc(c)) |
| 451 | #define isSPACE_LC_uvchr(c) (c < 256 ? isSPACE_LC(c) : is_uni_space_lc(c)) |
| 452 | #define isDIGIT_LC_uvchr(c) (c < 256 ? isDIGIT_LC(c) : is_uni_digit_lc(c)) |
| 453 | #define isUPPER_LC_uvchr(c) (c < 256 ? isUPPER_LC(c) : is_uni_upper_lc(c)) |
| 454 | #define isLOWER_LC_uvchr(c) (c < 256 ? isLOWER_LC(c) : is_uni_lower_lc(c)) |
| 455 | #define isALNUMC_LC_uvchr(c) (c < 256 ? isALNUMC_LC(c) : is_uni_alnumc_lc(c)) |
| 456 | #define isCNTRL_LC_uvchr(c) (c < 256 ? isCNTRL_LC(c) : is_uni_cntrl_lc(c)) |
| 457 | #define isGRAPH_LC_uvchr(c) (c < 256 ? isGRAPH_LC(c) : is_uni_graph_lc(c)) |
| 458 | #define isPRINT_LC_uvchr(c) (c < 256 ? isPRINT_LC(c) : is_uni_print_lc(c)) |
| 459 | #define isPUNCT_LC_uvchr(c) (c < 256 ? isPUNCT_LC(c) : is_uni_punct_lc(c)) |
| 460 | |
| 461 | #define isPSXSPC_LC_uni(c) (isSPACE_LC_uni(c) ||(c) == '\f') |
| 462 | #define isBLANK_LC_uni(c) isBLANK(c) /* could be wrong */ |
| 463 | |
| 464 | #define isALNUM_utf8(p) is_utf8_alnum(p) |
| 465 | /* The ID_Start of Unicode is quite limiting: it assumes a L-class |
| 466 | * character (meaning that you cannot have, say, a CJK character). |
| 467 | * Instead, let's allow ID_Continue but not digits. */ |
| 468 | #define isIDFIRST_utf8(p) (is_utf8_idcont(p) && !is_utf8_digit(p)) |
| 469 | #define isALPHA_utf8(p) is_utf8_alpha(p) |
| 470 | #define isSPACE_utf8(p) is_utf8_space(p) |
| 471 | #define isDIGIT_utf8(p) is_utf8_digit(p) |
| 472 | #define isUPPER_utf8(p) is_utf8_upper(p) |
| 473 | #define isLOWER_utf8(p) is_utf8_lower(p) |
| 474 | #define isALNUMC_utf8(p) is_utf8_alnumc(p) |
| 475 | #define isASCII_utf8(p) is_utf8_ascii(p) |
| 476 | #define isCNTRL_utf8(p) is_utf8_cntrl(p) |
| 477 | #define isGRAPH_utf8(p) is_utf8_graph(p) |
| 478 | #define isPRINT_utf8(p) is_utf8_print(p) |
| 479 | #define isPUNCT_utf8(p) is_utf8_punct(p) |
| 480 | #define isXDIGIT_utf8(p) is_utf8_xdigit(p) |
| 481 | #define toUPPER_utf8(p,s,l) to_utf8_upper(p,s,l) |
| 482 | #define toTITLE_utf8(p,s,l) to_utf8_title(p,s,l) |
| 483 | #define toLOWER_utf8(p,s,l) to_utf8_lower(p,s,l) |
| 484 | |
| 485 | #define isPSXSPC_utf8(c) (isSPACE_utf8(c) ||(c) == '\f') |
| 486 | #define isBLANK_utf8(c) isBLANK(c) /* could be wrong */ |
| 487 | |
| 488 | #define isALNUM_LC_utf8(p) isALNUM_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 489 | #define isIDFIRST_LC_utf8(p) isIDFIRST_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 490 | #define isALPHA_LC_utf8(p) isALPHA_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 491 | #define isSPACE_LC_utf8(p) isSPACE_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 492 | #define isDIGIT_LC_utf8(p) isDIGIT_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 493 | #define isUPPER_LC_utf8(p) isUPPER_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 494 | #define isLOWER_LC_utf8(p) isLOWER_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 495 | #define isALNUMC_LC_utf8(p) isALNUMC_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 496 | #define isCNTRL_LC_utf8(p) isCNTRL_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 497 | #define isGRAPH_LC_utf8(p) isGRAPH_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 498 | #define isPRINT_LC_utf8(p) isPRINT_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 499 | #define isPUNCT_LC_utf8(p) isPUNCT_LC_uvchr(utf8_to_uvchr(p, 0)) |
| 500 | |
| 501 | #define isPSXSPC_LC_utf8(c) (isSPACE_LC_utf8(c) ||(c) == '\f') |
| 502 | #define isBLANK_LC_utf8(c) isBLANK(c) /* could be wrong */ |
| 503 | |
| 504 | #ifdef EBCDIC |
| 505 | # ifdef PERL_IMPLICIT_CONTEXT |
| 506 | # define toCTRL(c) Perl_ebcdic_control(aTHX_ c) |
| 507 | # else |
| 508 | # define toCTRL Perl_ebcdic_control |
| 509 | # endif |
| 510 | #else |
| 511 | /* This conversion works both ways, strangely enough. */ |
| 512 | # define toCTRL(c) (toUPPER(c) ^ 64) |
| 513 | #endif |
| 514 | |
| 515 | /* Line numbers are unsigned, 32 bits. */ |
| 516 | typedef U32 line_t; |
| 517 | #ifdef lint |
| 518 | #define NOLINE ((line_t)0) |
| 519 | #else |
| 520 | #define NOLINE ((line_t) 4294967295UL) |
| 521 | #endif |
| 522 | |
| 523 | |
| 524 | /* |
| 525 | =head1 SV Manipulation Functions |
| 526 | |
| 527 | =for apidoc Am|SV*|NEWSV|int id|STRLEN len |
| 528 | Creates a new SV. A non-zero C<len> parameter indicates the number of |
| 529 | bytes of preallocated string space the SV should have. An extra byte for a |
| 530 | tailing NUL is also reserved. (SvPOK is not set for the SV even if string |
| 531 | space is allocated.) The reference count for the new SV is set to 1. |
| 532 | C<id> is an integer id between 0 and 1299 (used to identify leaks). |
| 533 | |
| 534 | =head1 Memory Management |
| 535 | |
| 536 | =for apidoc Am|void|New|int id|void* ptr|int nitems|type |
| 537 | The XSUB-writer's interface to the C C<malloc> function. |
| 538 | |
| 539 | =for apidoc Am|void|Newc|int id|void* ptr|int nitems|type|cast |
| 540 | The XSUB-writer's interface to the C C<malloc> function, with |
| 541 | cast. |
| 542 | |
| 543 | =for apidoc Am|void|Newz|int id|void* ptr|int nitems|type |
| 544 | The XSUB-writer's interface to the C C<malloc> function. The allocated |
| 545 | memory is zeroed with C<memzero>. |
| 546 | |
| 547 | =for apidoc Am|void|Renew|void* ptr|int nitems|type |
| 548 | The XSUB-writer's interface to the C C<realloc> function. |
| 549 | |
| 550 | =for apidoc Am|void|Renewc|void* ptr|int nitems|type|cast |
| 551 | The XSUB-writer's interface to the C C<realloc> function, with |
| 552 | cast. |
| 553 | |
| 554 | =for apidoc Am|void|Safefree|void* ptr |
| 555 | The XSUB-writer's interface to the C C<free> function. |
| 556 | |
| 557 | =for apidoc Am|void|Move|void* src|void* dest|int nitems|type |
| 558 | The XSUB-writer's interface to the C C<memmove> function. The C<src> is the |
| 559 | source, C<dest> is the destination, C<nitems> is the number of items, and C<type> is |
| 560 | the type. Can do overlapping moves. See also C<Copy>. |
| 561 | |
| 562 | =for apidoc Am|void|Copy|void* src|void* dest|int nitems|type |
| 563 | The XSUB-writer's interface to the C C<memcpy> function. The C<src> is the |
| 564 | source, C<dest> is the destination, C<nitems> is the number of items, and C<type> is |
| 565 | the type. May fail on overlapping copies. See also C<Move>. |
| 566 | |
| 567 | =for apidoc Am|void|Zero|void* dest|int nitems|type |
| 568 | |
| 569 | The XSUB-writer's interface to the C C<memzero> function. The C<dest> is the |
| 570 | destination, C<nitems> is the number of items, and C<type> is the type. |
| 571 | |
| 572 | =for apidoc Am|void|StructCopy|type src|type dest|type |
| 573 | This is an architecture-independent macro to copy one structure to another. |
| 574 | |
| 575 | =for apidoc Am|void|Poison|void* dest|int nitems|type |
| 576 | |
| 577 | Fill up memory with a pattern (byte 0xAB over and over again) that |
| 578 | hopefully catches attempts to access uninitialized memory. |
| 579 | |
| 580 | =cut */ |
| 581 | |
| 582 | #ifndef lint |
| 583 | |
| 584 | #define NEWSV(x,len) newSV(len) |
| 585 | |
| 586 | #define New(x,v,n,t) (v = (t*)safemalloc((MEM_SIZE)((n)*sizeof(t)))) |
| 587 | #define Newc(x,v,n,t,c) (v = (c*)safemalloc((MEM_SIZE)((n)*sizeof(t)))) |
| 588 | #define Newz(x,v,n,t) (v = (t*)safemalloc((MEM_SIZE)((n)*sizeof(t)))), \ |
| 589 | memzero((char*)(v), (n)*sizeof(t)) |
| 590 | #define Renew(v,n,t) \ |
| 591 | (v = (t*)saferealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t)))) |
| 592 | #define Renewc(v,n,t,c) \ |
| 593 | (v = (c*)saferealloc((Malloc_t)(v),(MEM_SIZE)((n)*sizeof(t)))) |
| 594 | #define Safefree(d) safefree((Malloc_t)(d)) |
| 595 | |
| 596 | #define Move(s,d,n,t) (void)memmove((char*)(d),(char*)(s), (n) * sizeof(t)) |
| 597 | #define Copy(s,d,n,t) (void)memcpy((char*)(d),(char*)(s), (n) * sizeof(t)) |
| 598 | #define Zero(d,n,t) (void)memzero((char*)(d), (n) * sizeof(t)) |
| 599 | |
| 600 | #define Poison(d,n,t) (void)memset((char*)(d), 0xAB, (n) * sizeof(t)) |
| 601 | |
| 602 | #else /* lint */ |
| 603 | |
| 604 | #define New(x,v,n,s) (v = Null(s *)) |
| 605 | #define Newc(x,v,n,s,c) (v = Null(s *)) |
| 606 | #define Newz(x,v,n,s) (v = Null(s *)) |
| 607 | #define Renew(v,n,s) (v = Null(s *)) |
| 608 | #define Move(s,d,n,t) |
| 609 | #define Copy(s,d,n,t) |
| 610 | #define Zero(d,n,t) |
| 611 | #define Poison(d,n,t) |
| 612 | #define Safefree(d) (d) = (d) |
| 613 | |
| 614 | #endif /* lint */ |
| 615 | |
| 616 | #ifdef USE_STRUCT_COPY |
| 617 | #define StructCopy(s,d,t) (*((t*)(d)) = *((t*)(s))) |
| 618 | #else |
| 619 | #define StructCopy(s,d,t) Copy(s,d,1,t) |
| 620 | #endif |
| 621 | |
| 622 | #define C_ARRAY_LENGTH(a) (sizeof(a)/sizeof((a)[0])) |
| 623 | |
| 624 | #ifdef NEED_VA_COPY |
| 625 | # ifdef va_copy |
| 626 | # define Perl_va_copy(s, d) va_copy(d, s) |
| 627 | # else |
| 628 | # if defined(__va_copy) |
| 629 | # define Perl_va_copy(s, d) __va_copy(d, s) |
| 630 | # else |
| 631 | # define Perl_va_copy(s, d) Copy(s, d, 1, va_list) |
| 632 | # endif |
| 633 | # endif |
| 634 | #endif |
| 635 | |