_struct.c 43.7 KB
Newer Older
1 2 3 4 5
/* struct module -- pack values into and (out of) strings */

/* New version supporting byte order, alignment and size options,
   character strings, and unsigned numbers */

6 7
#define PY_SSIZE_T_CLEAN

8 9 10 11 12
#include "Python.h"
#include "structseq.h"
#include "structmember.h"
#include <ctype.h>

13
static PyTypeObject PyStructType;
14 15 16 17 18 19

/* compatibility macros */
#if (PY_VERSION_HEX < 0x02050000)
typedef int Py_ssize_t;
#endif

20
/* If PY_STRUCT_OVERFLOW_MASKING is defined, the struct module will wrap all input
21 22 23 24 25 26
   numbers for explicit endians such that they fit in the given type, much
   like explicit casting in C. A warning will be raised if the number did
   not originally fit within the range of the requested type. If it is
   not defined, then all range errors and overflow will be struct.error
   exceptions. */

27
#define PY_STRUCT_OVERFLOW_MASKING 1
28

29
#ifdef PY_STRUCT_OVERFLOW_MASKING
30 31 32 33
static PyObject *pylong_ulong_mask = NULL;
static PyObject *pyint_zero = NULL;
#endif

34 35 36 37 38 39 40 41 42 43 44
/* If PY_STRUCT_FLOAT_COERCE is defined, the struct module will allow float
   arguments for integer formats with a warning for backwards
   compatibility. */

#define PY_STRUCT_FLOAT_COERCE 1

#ifdef PY_STRUCT_FLOAT_COERCE
#define FLOAT_COERCE "integer argument expected, got float"
#endif


45 46 47
/* The translation function for each format character is table driven */
typedef struct _formatdef {
	char format;
48 49
	Py_ssize_t size;
	Py_ssize_t alignment;
50 51 52 53 54 55 56 57
	PyObject* (*unpack)(const char *,
			    const struct _formatdef *);
	int (*pack)(char *, PyObject *,
		    const struct _formatdef *);
} formatdef;

typedef struct _formatcode {
	const struct _formatdef *fmtdef;
58 59
	Py_ssize_t offset;
	Py_ssize_t size;
60 61 62 63 64 65
} formatcode;

/* Struct object interface */

typedef struct {
	PyObject_HEAD
66 67
	Py_ssize_t s_size;
	Py_ssize_t s_len;
68 69 70 71 72
	formatcode *s_codes;
	PyObject *s_format;
	PyObject *weakreflist; /* List of weak references */
} PyStructObject;

73

Bob Ippolito's avatar
Bob Ippolito committed
74
#define PyStruct_Check(op) PyObject_TypeCheck(op, &PyStructType)
75
#define PyStruct_CheckExact(op) (Py_Type(op) == &PyStructType)
76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106


/* Exception */

static PyObject *StructError;


/* Define various structs to figure out the alignments of types */


typedef struct { char c; short x; } st_short;
typedef struct { char c; int x; } st_int;
typedef struct { char c; long x; } st_long;
typedef struct { char c; float x; } st_float;
typedef struct { char c; double x; } st_double;
typedef struct { char c; void *x; } st_void_p;

#define SHORT_ALIGN (sizeof(st_short) - sizeof(short))
#define INT_ALIGN (sizeof(st_int) - sizeof(int))
#define LONG_ALIGN (sizeof(st_long) - sizeof(long))
#define FLOAT_ALIGN (sizeof(st_float) - sizeof(float))
#define DOUBLE_ALIGN (sizeof(st_double) - sizeof(double))
#define VOID_P_ALIGN (sizeof(st_void_p) - sizeof(void *))

/* We can't support q and Q in native mode unless the compiler does;
   in std mode, they're 8 bytes on all platforms. */
#ifdef HAVE_LONG_LONG
typedef struct { char c; PY_LONG_LONG x; } s_long_long;
#define LONG_LONG_ALIGN (sizeof(s_long_long) - sizeof(PY_LONG_LONG))
#endif

107 108 109 110 111 112 113 114 115
#ifdef HAVE_C99_BOOL
#define BOOL_TYPE _Bool
typedef struct { char c; _Bool x; } s_bool;
#define BOOL_ALIGN (sizeof(s_bool) - sizeof(BOOL_TYPE))
#else
#define BOOL_TYPE char
#define BOOL_ALIGN 0
#endif

116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135
#define STRINGIFY(x)    #x

#ifdef __powerc
#pragma options align=reset
#endif

/* Helper to get a PyLongObject by hook or by crook.  Caller should decref. */

static PyObject *
get_pylong(PyObject *v)
{
	PyNumberMethods *m;

	assert(v != NULL);
	if (PyInt_Check(v))
		return PyLong_FromLong(PyInt_AS_LONG(v));
	if (PyLong_Check(v)) {
		Py_INCREF(v);
		return v;
	}
136
	m = Py_Type(v)->tp_as_number;
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
	if (m != NULL && m->nb_long != NULL) {
		v = m->nb_long(v);
		if (v == NULL)
			return NULL;
		if (PyLong_Check(v))
			return v;
		Py_DECREF(v);
	}
	PyErr_SetString(StructError,
			"cannot convert argument to long");
	return NULL;
}

/* Helper routine to get a Python integer and raise the appropriate error
   if it isn't one */

static int
get_long(PyObject *v, long *p)
{
	long x = PyInt_AsLong(v);
	if (x == -1 && PyErr_Occurred()) {
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172
#ifdef PY_STRUCT_FLOAT_COERCE
		if (PyFloat_Check(v)) {
			PyObject *o;
			int res;
			PyErr_Clear();
			if (PyErr_WarnEx(PyExc_DeprecationWarning, FLOAT_COERCE, 2) < 0)
				return -1;
			o = PyNumber_Int(v);
			if (o == NULL)
				return -1;
			res = get_long(o, p);
			Py_DECREF(o);
			return res;
		}
#endif
173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
		if (PyErr_ExceptionMatches(PyExc_TypeError))
			PyErr_SetString(StructError,
					"required argument is not an integer");
		return -1;
	}
	*p = x;
	return 0;
}


/* Same, but handling unsigned long */

static int
get_ulong(PyObject *v, unsigned long *p)
{
	if (PyLong_Check(v)) {
		unsigned long x = PyLong_AsUnsignedLong(v);
		if (x == (unsigned long)(-1) && PyErr_Occurred())
			return -1;
		*p = x;
		return 0;
	}
195 196 197 198 199 200
	if (get_long(v, (long *)p) < 0)
		return -1;
	if (((long)*p) < 0) {
		PyErr_SetString(StructError,
				"unsigned argument is < 0");
		return -1;
201
	}
202
	return 0;
203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246
}

#ifdef HAVE_LONG_LONG

/* Same, but handling native long long. */

static int
get_longlong(PyObject *v, PY_LONG_LONG *p)
{
	PY_LONG_LONG x;

	v = get_pylong(v);
	if (v == NULL)
		return -1;
	assert(PyLong_Check(v));
	x = PyLong_AsLongLong(v);
	Py_DECREF(v);
	if (x == (PY_LONG_LONG)-1 && PyErr_Occurred())
		return -1;
	*p = x;
	return 0;
}

/* Same, but handling native unsigned long long. */

static int
get_ulonglong(PyObject *v, unsigned PY_LONG_LONG *p)
{
	unsigned PY_LONG_LONG x;

	v = get_pylong(v);
	if (v == NULL)
		return -1;
	assert(PyLong_Check(v));
	x = PyLong_AsUnsignedLongLong(v);
	Py_DECREF(v);
	if (x == (unsigned PY_LONG_LONG)-1 && PyErr_Occurred())
		return -1;
	*p = x;
	return 0;
}

#endif

247
#ifdef PY_STRUCT_OVERFLOW_MASKING
248 249 250 251

/* Helper routine to get a Python integer and raise the appropriate error
   if it isn't one */

252 253
#define INT_OVERFLOW "struct integer overflow masking is deprecated"

254 255 256 257
static int
get_wrapped_long(PyObject *v, long *p)
{
	if (get_long(v, p) < 0) {
Neal Norwitz's avatar
Neal Norwitz committed
258 259
		if (PyLong_Check(v) &&
		    PyErr_ExceptionMatches(PyExc_OverflowError)) {
260 261 262
			PyObject *wrapped;
			long x;
			PyErr_Clear();
263 264 265 266 267 268 269 270 271 272 273 274 275 276 277
#ifdef PY_STRUCT_FLOAT_COERCE
			if (PyFloat_Check(v)) {
				PyObject *o;
				int res;
				PyErr_Clear();
				if (PyErr_WarnEx(PyExc_DeprecationWarning, FLOAT_COERCE, 2) < 0)
					return -1;
				o = PyNumber_Int(v);
				if (o == NULL)
					return -1;
				res = get_wrapped_long(o, p);
				Py_DECREF(o);
				return res;
			}
#endif
278
			if (PyErr_WarnEx(PyExc_DeprecationWarning, INT_OVERFLOW, 2) < 0)
279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
				return -1;
			wrapped = PyNumber_And(v, pylong_ulong_mask);
			if (wrapped == NULL)
				return -1;
			x = (long)PyLong_AsUnsignedLong(wrapped);
			Py_DECREF(wrapped);
			if (x == -1 && PyErr_Occurred())
				return -1;
			*p = x;
		} else {
			return -1;
		}
	}
	return 0;
}

static int
get_wrapped_ulong(PyObject *v, unsigned long *p)
{
	long x = (long)PyLong_AsUnsignedLong(v);
	if (x == -1 && PyErr_Occurred()) {
		PyObject *wrapped;
		PyErr_Clear();
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
#ifdef PY_STRUCT_FLOAT_COERCE
		if (PyFloat_Check(v)) {
			PyObject *o;
			int res;
			PyErr_Clear();
			if (PyErr_WarnEx(PyExc_DeprecationWarning, FLOAT_COERCE, 2) < 0)
				return -1;
			o = PyNumber_Int(v);
			if (o == NULL)
				return -1;
			res = get_wrapped_ulong(o, p);
			Py_DECREF(o);
			return res;
		}
#endif
317 318 319
		wrapped = PyNumber_And(v, pylong_ulong_mask);
		if (wrapped == NULL)
			return -1;
320
		if (PyErr_WarnEx(PyExc_DeprecationWarning, INT_OVERFLOW, 2) < 0) {
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348
			Py_DECREF(wrapped);
			return -1;
		}
		x = (long)PyLong_AsUnsignedLong(wrapped);
		Py_DECREF(wrapped);
		if (x == -1 && PyErr_Occurred())
			return -1;
	}
	*p = (unsigned long)x;
	return 0;
}

#define RANGE_ERROR(x, f, flag, mask) \
	do { \
		if (_range_error(f, flag) < 0) \
			return -1; \
		else \
			(x) &= (mask); \
	} while (0)

#else

#define get_wrapped_long get_long
#define get_wrapped_ulong get_ulong
#define RANGE_ERROR(x, f, flag, mask) return _range_error(f, flag)

#endif

349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374
/* Floating point helpers */

static PyObject *
unpack_float(const char *p,  /* start of 4-byte string */
             int le)	     /* true for little-endian, false for big-endian */
{
	double x;

	x = _PyFloat_Unpack4((unsigned char *)p, le);
	if (x == -1.0 && PyErr_Occurred())
		return NULL;
	return PyFloat_FromDouble(x);
}

static PyObject *
unpack_double(const char *p,  /* start of 8-byte string */
              int le)         /* true for little-endian, false for big-endian */
{
	double x;

	x = _PyFloat_Unpack8((unsigned char *)p, le);
	if (x == -1.0 && PyErr_Occurred())
		return NULL;
	return PyFloat_FromDouble(x);
}

375 376
/* Helper to format the range error exceptions */
static int
Armin Rigo's avatar
Armin Rigo committed
377
_range_error(const formatdef *f, int is_unsigned)
378
{
379 380 381
	/* ulargest is the largest unsigned value with f->size bytes.
	 * Note that the simpler:
	 *     ((size_t)1 << (f->size * 8)) - 1
382 383 384 385
	 * doesn't work when f->size == sizeof(size_t) because C doesn't
	 * define what happens when a left shift count is >= the number of
	 * bits in the integer being shifted; e.g., on some boxes it doesn't
	 * shift at all when they're equal.
386 387 388 389
	 */
	const size_t ulargest = (size_t)-1 >> ((SIZEOF_SIZE_T - f->size)*8);
	assert(f->size >= 1 && f->size <= SIZEOF_SIZE_T);
	if (is_unsigned)
390
		PyErr_Format(StructError,
391
			"'%c' format requires 0 <= number <= %zu",
392
			f->format,
393 394 395
			ulargest);
	else {
		const Py_ssize_t largest = (Py_ssize_t)(ulargest >> 1);
396
		PyErr_Format(StructError,
397
			"'%c' format requires %zd <= number <= %zd",
398
			f->format,
399
			~ largest,
400 401
			largest);
	}
402
#ifdef PY_STRUCT_OVERFLOW_MASKING
403 404 405 406 407 408 409 410 411 412 413 414
	{
		PyObject *ptype, *pvalue, *ptraceback;
		PyObject *msg;
		int rval;
		PyErr_Fetch(&ptype, &pvalue, &ptraceback);
		assert(pvalue != NULL);
		msg = PyObject_Str(pvalue);
		Py_XDECREF(ptype);
		Py_XDECREF(pvalue);
		Py_XDECREF(ptraceback);
		if (msg == NULL)
			return -1;
415 416
		rval = PyErr_WarnEx(PyExc_DeprecationWarning,
				    PyString_AS_STRING(msg), 2);
417 418 419 420 421
		Py_DECREF(msg);
		if (rval == 0)
			return 0;
	}
#endif
422 423 424 425
	return -1;
}


426 427 428

/* A large number of small routines follow, with names of the form

429
   [bln][up]_TYPE
430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492

   [bln] distiguishes among big-endian, little-endian and native.
   [pu] distiguishes between pack (to struct) and unpack (from struct).
   TYPE is one of char, byte, ubyte, etc.
*/

/* Native mode routines. ****************************************************/
/* NOTE:
   In all n[up]_<type> routines handling types larger than 1 byte, there is
   *no* guarantee that the p pointer is properly aligned for each type,
   therefore memcpy is called.  An intermediate variable is used to
   compensate for big-endian architectures.
   Normally both the intermediate variable and the memcpy call will be
   skipped by C optimisation in little-endian architectures (gcc >= 2.91
   does this). */

static PyObject *
nu_char(const char *p, const formatdef *f)
{
	return PyString_FromStringAndSize(p, 1);
}

static PyObject *
nu_byte(const char *p, const formatdef *f)
{
	return PyInt_FromLong((long) *(signed char *)p);
}

static PyObject *
nu_ubyte(const char *p, const formatdef *f)
{
	return PyInt_FromLong((long) *(unsigned char *)p);
}

static PyObject *
nu_short(const char *p, const formatdef *f)
{
	short x;
	memcpy((char *)&x, p, sizeof x);
	return PyInt_FromLong((long)x);
}

static PyObject *
nu_ushort(const char *p, const formatdef *f)
{
	unsigned short x;
	memcpy((char *)&x, p, sizeof x);
	return PyInt_FromLong((long)x);
}

static PyObject *
nu_int(const char *p, const formatdef *f)
{
	int x;
	memcpy((char *)&x, p, sizeof x);
	return PyInt_FromLong((long)x);
}

static PyObject *
nu_uint(const char *p, const formatdef *f)
{
	unsigned int x;
	memcpy((char *)&x, p, sizeof x);
493 494 495 496
#if (SIZEOF_LONG > SIZEOF_INT)
	return PyInt_FromLong((long)x);
#else
	if (x <= ((unsigned int)LONG_MAX))
497
		return PyInt_FromLong((long)x);
498
	return PyLong_FromUnsignedLong((unsigned long)x);
499
#endif
500 501 502 503 504 505 506 507 508 509 510 511 512 513 514
}

static PyObject *
nu_long(const char *p, const formatdef *f)
{
	long x;
	memcpy((char *)&x, p, sizeof x);
	return PyInt_FromLong(x);
}

static PyObject *
nu_ulong(const char *p, const formatdef *f)
{
	unsigned long x;
	memcpy((char *)&x, p, sizeof x);
515
	if (x <= LONG_MAX)
516
		return PyInt_FromLong((long)x);
517 518 519 520 521 522 523 524 525 526 527 528 529
	return PyLong_FromUnsignedLong(x);
}

/* Native mode doesn't support q or Q unless the platform C supports
   long long (or, on Windows, __int64). */

#ifdef HAVE_LONG_LONG

static PyObject *
nu_longlong(const char *p, const formatdef *f)
{
	PY_LONG_LONG x;
	memcpy((char *)&x, p, sizeof x);
530
	if (x >= LONG_MIN && x <= LONG_MAX)
531
		return PyInt_FromLong(Py_SAFE_DOWNCAST(x, PY_LONG_LONG, long));
532 533 534 535 536 537 538 539
	return PyLong_FromLongLong(x);
}

static PyObject *
nu_ulonglong(const char *p, const formatdef *f)
{
	unsigned PY_LONG_LONG x;
	memcpy((char *)&x, p, sizeof x);
540
	if (x <= LONG_MAX)
541
		return PyInt_FromLong(Py_SAFE_DOWNCAST(x, unsigned PY_LONG_LONG, long));
542 543 544 545 546
	return PyLong_FromUnsignedLongLong(x);
}

#endif

547 548 549 550 551 552 553 554 555
static PyObject *
nu_bool(const char *p, const formatdef *f)
{
	BOOL_TYPE x;
	memcpy((char *)&x, p, sizeof x);
	return PyBool_FromLong(x != 0);
}


556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587
static PyObject *
nu_float(const char *p, const formatdef *f)
{
	float x;
	memcpy((char *)&x, p, sizeof x);
	return PyFloat_FromDouble((double)x);
}

static PyObject *
nu_double(const char *p, const formatdef *f)
{
	double x;
	memcpy((char *)&x, p, sizeof x);
	return PyFloat_FromDouble(x);
}

static PyObject *
nu_void_p(const char *p, const formatdef *f)
{
	void *x;
	memcpy((char *)&x, p, sizeof x);
	return PyLong_FromVoidPtr(x);
}

static int
np_byte(char *p, PyObject *v, const formatdef *f)
{
	long x;
	if (get_long(v, &x) < 0)
		return -1;
	if (x < -128 || x > 127){
		PyErr_SetString(StructError,
588
				"byte format requires -128 <= number <= 127");
589 590 591 592 593 594 595 596 597 598 599 600 601 602
		return -1;
	}
	*p = (char)x;
	return 0;
}

static int
np_ubyte(char *p, PyObject *v, const formatdef *f)
{
	long x;
	if (get_long(v, &x) < 0)
		return -1;
	if (x < 0 || x > 255){
		PyErr_SetString(StructError,
603
				"ubyte format requires 0 <= number <= 255");
604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631
		return -1;
	}
	*p = (char)x;
	return 0;
}

static int
np_char(char *p, PyObject *v, const formatdef *f)
{
	if (!PyString_Check(v) || PyString_Size(v) != 1) {
		PyErr_SetString(StructError,
				"char format require string of length 1");
		return -1;
	}
	*p = *PyString_AsString(v);
	return 0;
}

static int
np_short(char *p, PyObject *v, const formatdef *f)
{
	long x;
	short y;
	if (get_long(v, &x) < 0)
		return -1;
	if (x < SHRT_MIN || x > SHRT_MAX){
		PyErr_SetString(StructError,
				"short format requires " STRINGIFY(SHRT_MIN)
632
				" <= number <= " STRINGIFY(SHRT_MAX));
633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648
		return -1;
	}
	y = (short)x;
	memcpy(p, (char *)&y, sizeof y);
	return 0;
}

static int
np_ushort(char *p, PyObject *v, const formatdef *f)
{
	long x;
	unsigned short y;
	if (get_long(v, &x) < 0)
		return -1;
	if (x < 0 || x > USHRT_MAX){
		PyErr_SetString(StructError,
649
				"short format requires 0 <= number <= " STRINGIFY(USHRT_MAX));
650 651 652 653 654 655 656 657 658 659 660 661 662 663
		return -1;
	}
	y = (unsigned short)x;
	memcpy(p, (char *)&y, sizeof y);
	return 0;
}

static int
np_int(char *p, PyObject *v, const formatdef *f)
{
	long x;
	int y;
	if (get_long(v, &x) < 0)
		return -1;
664
#if (SIZEOF_LONG > SIZEOF_INT)
665
	if ((x < ((long)INT_MIN)) || (x > ((long)INT_MAX)))
666
		return _range_error(f, 0);
667
#endif
668 669 670 671 672 673 674 675 676 677 678
	y = (int)x;
	memcpy(p, (char *)&y, sizeof y);
	return 0;
}

static int
np_uint(char *p, PyObject *v, const formatdef *f)
{
	unsigned long x;
	unsigned int y;
	if (get_ulong(v, &x) < 0)
679
		return _range_error(f, 1);
680
	y = (unsigned int)x;
681
#if (SIZEOF_LONG > SIZEOF_INT)
682
	if (x > ((unsigned long)UINT_MAX))
683
		return _range_error(f, 1);
684
#endif
685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703
	memcpy(p, (char *)&y, sizeof y);
	return 0;
}

static int
np_long(char *p, PyObject *v, const formatdef *f)
{
	long x;
	if (get_long(v, &x) < 0)
		return -1;
	memcpy(p, (char *)&x, sizeof x);
	return 0;
}

static int
np_ulong(char *p, PyObject *v, const formatdef *f)
{
	unsigned long x;
	if (get_ulong(v, &x) < 0)
704
		return _range_error(f, 1);
705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731
	memcpy(p, (char *)&x, sizeof x);
	return 0;
}

#ifdef HAVE_LONG_LONG

static int
np_longlong(char *p, PyObject *v, const formatdef *f)
{
	PY_LONG_LONG x;
	if (get_longlong(v, &x) < 0)
		return -1;
	memcpy(p, (char *)&x, sizeof x);
	return 0;
}

static int
np_ulonglong(char *p, PyObject *v, const formatdef *f)
{
	unsigned PY_LONG_LONG x;
	if (get_ulonglong(v, &x) < 0)
		return -1;
	memcpy(p, (char *)&x, sizeof x);
	return 0;
}
#endif

732 733 734 735 736 737 738 739 740 741

static int
np_bool(char *p, PyObject *v, const formatdef *f)
{
	BOOL_TYPE y; 
	y = PyObject_IsTrue(v);
	memcpy(p, (char *)&y, sizeof y);
	return 0;
}

742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801
static int
np_float(char *p, PyObject *v, const formatdef *f)
{
	float x = (float)PyFloat_AsDouble(v);
	if (x == -1 && PyErr_Occurred()) {
		PyErr_SetString(StructError,
				"required argument is not a float");
		return -1;
	}
	memcpy(p, (char *)&x, sizeof x);
	return 0;
}

static int
np_double(char *p, PyObject *v, const formatdef *f)
{
	double x = PyFloat_AsDouble(v);
	if (x == -1 && PyErr_Occurred()) {
		PyErr_SetString(StructError,
				"required argument is not a float");
		return -1;
	}
	memcpy(p, (char *)&x, sizeof(double));
	return 0;
}

static int
np_void_p(char *p, PyObject *v, const formatdef *f)
{
	void *x;

	v = get_pylong(v);
	if (v == NULL)
		return -1;
	assert(PyLong_Check(v));
	x = PyLong_AsVoidPtr(v);
	Py_DECREF(v);
	if (x == NULL && PyErr_Occurred())
		return -1;
	memcpy(p, (char *)&x, sizeof x);
	return 0;
}

static formatdef native_table[] = {
	{'x',	sizeof(char),	0,		NULL},
	{'b',	sizeof(char),	0,		nu_byte,	np_byte},
	{'B',	sizeof(char),	0,		nu_ubyte,	np_ubyte},
	{'c',	sizeof(char),	0,		nu_char,	np_char},
	{'s',	sizeof(char),	0,		NULL},
	{'p',	sizeof(char),	0,		NULL},
	{'h',	sizeof(short),	SHORT_ALIGN,	nu_short,	np_short},
	{'H',	sizeof(short),	SHORT_ALIGN,	nu_ushort,	np_ushort},
	{'i',	sizeof(int),	INT_ALIGN,	nu_int,		np_int},
	{'I',	sizeof(int),	INT_ALIGN,	nu_uint,	np_uint},
	{'l',	sizeof(long),	LONG_ALIGN,	nu_long,	np_long},
	{'L',	sizeof(long),	LONG_ALIGN,	nu_ulong,	np_ulong},
#ifdef HAVE_LONG_LONG
	{'q',	sizeof(PY_LONG_LONG), LONG_LONG_ALIGN, nu_longlong, np_longlong},
	{'Q',	sizeof(PY_LONG_LONG), LONG_LONG_ALIGN, nu_ulonglong,np_ulonglong},
#endif
802
	{'t',	sizeof(BOOL_TYPE),	BOOL_ALIGN,	nu_bool,	np_bool},
803 804 805
	{'f',	sizeof(float),	FLOAT_ALIGN,	nu_float,	np_float},
	{'d',	sizeof(double),	DOUBLE_ALIGN,	nu_double,	np_double},
	{'P',	sizeof(void *),	VOID_P_ALIGN,	nu_void_p,	np_void_p},
806 807 808 809 810 811 812 813 814
	{0}
};

/* Big-endian routines. *****************************************************/

static PyObject *
bu_int(const char *p, const formatdef *f)
{
	long x = 0;
815
	Py_ssize_t i = f->size;
816
	const unsigned char *bytes = (const unsigned char *)p;
817
	do {
818
		x = (x<<8) | *bytes++;
819 820 821
	} while (--i > 0);
	/* Extend the sign bit. */
	if (SIZEOF_LONG > f->size)
822
		x |= -(x & (1L << ((8 * f->size) - 1)));
823 824 825 826 827 828 829
	return PyInt_FromLong(x);
}

static PyObject *
bu_uint(const char *p, const formatdef *f)
{
	unsigned long x = 0;
830
	Py_ssize_t i = f->size;
831
	const unsigned char *bytes = (const unsigned char *)p;
832
	do {
833
		x = (x<<8) | *bytes++;
834
	} while (--i > 0);
835
	if (x <= LONG_MAX)
836
		return PyInt_FromLong((long)x);
837
	return PyLong_FromUnsignedLong(x);
838 839 840 841 842
}

static PyObject *
bu_longlong(const char *p, const formatdef *f)
{
843
#ifdef HAVE_LONG_LONG
844
	PY_LONG_LONG x = 0;
845
	Py_ssize_t i = f->size;
846
	const unsigned char *bytes = (const unsigned char *)p;
847
	do {
848
		x = (x<<8) | *bytes++;
849 850 851
	} while (--i > 0);
	/* Extend the sign bit. */
	if (SIZEOF_LONG_LONG > f->size)
852
		x |= -(x & ((PY_LONG_LONG)1 << ((8 * f->size) - 1)));
853
	if (x >= LONG_MIN && x <= LONG_MAX)
854 855 856
		return PyInt_FromLong(Py_SAFE_DOWNCAST(x, PY_LONG_LONG, long));
	return PyLong_FromLongLong(x);
#else
857 858 859 860
	return _PyLong_FromByteArray((const unsigned char *)p,
				      8,
				      0, /* little-endian */
				      1  /* signed */);
861
#endif
862 863 864 865 866
}

static PyObject *
bu_ulonglong(const char *p, const formatdef *f)
{
867
#ifdef HAVE_LONG_LONG
868
	unsigned PY_LONG_LONG x = 0;
869
	Py_ssize_t i = f->size;
870
	const unsigned char *bytes = (const unsigned char *)p;
871
	do {
872
		x = (x<<8) | *bytes++;
873
	} while (--i > 0);
874
	if (x <= LONG_MAX)
875 876 877
		return PyInt_FromLong(Py_SAFE_DOWNCAST(x, unsigned PY_LONG_LONG, long));
	return PyLong_FromUnsignedLongLong(x);
#else
878 879 880 881
	return _PyLong_FromByteArray((const unsigned char *)p,
				      8,
				      0, /* little-endian */
				      0  /* signed */);
882
#endif
883 884 885 886 887 888 889 890 891 892 893 894 895 896
}

static PyObject *
bu_float(const char *p, const formatdef *f)
{
	return unpack_float(p, 0);
}

static PyObject *
bu_double(const char *p, const formatdef *f)
{
	return unpack_double(p, 0);
}

897 898 899 900 901 902 903 904
static PyObject *
bu_bool(const char *p, const formatdef *f)
{
	char x;
	memcpy((char *)&x, p, sizeof x);
	return PyBool_FromLong(x != 0);
}

905 906 907 908
static int
bp_int(char *p, PyObject *v, const formatdef *f)
{
	long x;
909
	Py_ssize_t i;
910
	if (get_wrapped_long(v, &x) < 0)
911 912
		return -1;
	i = f->size;
913 914
	if (i != SIZEOF_LONG) {
		if ((i == 2) && (x < -32768 || x > 32767))
915
			RANGE_ERROR(x, f, 0, 0xffffL);
916
#if (SIZEOF_LONG != 4)
917
		else if ((i == 4) && (x < -2147483648L || x > 2147483647L))
918 919
			RANGE_ERROR(x, f, 0, 0xffffffffL);
#endif
920
#ifdef PY_STRUCT_OVERFLOW_MASKING
921 922
		else if ((i == 1) && (x < -128 || x > 127))
			RANGE_ERROR(x, f, 0, 0xffL);
923
#endif
924
	}
925 926 927 928 929 930 931 932 933 934 935
	do {
		p[--i] = (char)x;
		x >>= 8;
	} while (i > 0);
	return 0;
}

static int
bp_uint(char *p, PyObject *v, const formatdef *f)
{
	unsigned long x;
936
	Py_ssize_t i;
937
	if (get_wrapped_ulong(v, &x) < 0)
938 939
		return -1;
	i = f->size;
940 941 942 943
	if (i != SIZEOF_LONG) {
		unsigned long maxint = 1;
		maxint <<= (unsigned long)(i * 8);
		if (x >= maxint)
944
			RANGE_ERROR(x, f, 1, maxint - 1);
945
	}
946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008
	do {
		p[--i] = (char)x;
		x >>= 8;
	} while (i > 0);
	return 0;
}

static int
bp_longlong(char *p, PyObject *v, const formatdef *f)
{
	int res;
	v = get_pylong(v);
	if (v == NULL)
		return -1;
	res = _PyLong_AsByteArray((PyLongObject *)v,
			   	  (unsigned char *)p,
				  8,
				  0, /* little_endian */
				  1  /* signed */);
	Py_DECREF(v);
	return res;
}

static int
bp_ulonglong(char *p, PyObject *v, const formatdef *f)
{
	int res;
	v = get_pylong(v);
	if (v == NULL)
		return -1;
	res = _PyLong_AsByteArray((PyLongObject *)v,
			   	  (unsigned char *)p,
				  8,
				  0, /* little_endian */
				  0  /* signed */);
	Py_DECREF(v);
	return res;
}

static int
bp_float(char *p, PyObject *v, const formatdef *f)
{
	double x = PyFloat_AsDouble(v);
	if (x == -1 && PyErr_Occurred()) {
		PyErr_SetString(StructError,
				"required argument is not a float");
		return -1;
	}
	return _PyFloat_Pack4(x, (unsigned char *)p, 0);
}

static int
bp_double(char *p, PyObject *v, const formatdef *f)
{
	double x = PyFloat_AsDouble(v);
	if (x == -1 && PyErr_Occurred()) {
		PyErr_SetString(StructError,
				"required argument is not a float");
		return -1;
	}
	return _PyFloat_Pack8(x, (unsigned char *)p, 0);
}

1009 1010 1011 1012 1013 1014 1015 1016 1017
static int
bp_bool(char *p, PyObject *v, const formatdef *f)
{
	char y; 
	y = PyObject_IsTrue(v);
	memcpy(p, (char *)&y, sizeof y);
	return 0;
}

1018 1019
static formatdef bigendian_table[] = {
	{'x',	1,		0,		NULL},
1020 1021
#ifdef PY_STRUCT_OVERFLOW_MASKING
	/* Native packers do range checking without overflow masking. */
1022 1023 1024
	{'b',	1,		0,		nu_byte,	bp_int},
	{'B',	1,		0,		nu_ubyte,	bp_uint},
#else
1025 1026
	{'b',	1,		0,		nu_byte,	np_byte},
	{'B',	1,		0,		nu_ubyte,	np_ubyte},
1027
#endif
1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
	{'c',	1,		0,		nu_char,	np_char},
	{'s',	1,		0,		NULL},
	{'p',	1,		0,		NULL},
	{'h',	2,		0,		bu_int,		bp_int},
	{'H',	2,		0,		bu_uint,	bp_uint},
	{'i',	4,		0,		bu_int,		bp_int},
	{'I',	4,		0,		bu_uint,	bp_uint},
	{'l',	4,		0,		bu_int,		bp_int},
	{'L',	4,		0,		bu_uint,	bp_uint},
	{'q',	8,		0,		bu_longlong,	bp_longlong},
	{'Q',	8,		0,		bu_ulonglong,	bp_ulonglong},
1039
	{'t',	1,		0,		bu_bool,	bp_bool},
1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050
	{'f',	4,		0,		bu_float,	bp_float},
	{'d',	8,		0,		bu_double,	bp_double},
	{0}
};

/* Little-endian routines. *****************************************************/

static PyObject *
lu_int(const char *p, const formatdef *f)
{
	long x = 0;
1051
	Py_ssize_t i = f->size;
1052
	const unsigned char *bytes = (const unsigned char *)p;
1053
	do {
1054
		x = (x<<8) | bytes[--i];
1055 1056 1057
	} while (i > 0);
	/* Extend the sign bit. */
	if (SIZEOF_LONG > f->size)
1058
		x |= -(x & (1L << ((8 * f->size) - 1)));
1059 1060 1061 1062 1063 1064 1065
	return PyInt_FromLong(x);
}

static PyObject *
lu_uint(const char *p, const formatdef *f)
{
	unsigned long x = 0;
1066
	Py_ssize_t i = f->size;
1067
	const unsigned char *bytes = (const unsigned char *)p;
1068
	do {
1069
		x = (x<<8) | bytes[--i];
1070
	} while (i > 0);
1071
	if (x <= LONG_MAX)
1072
		return PyInt_FromLong((long)x);
1073
	return PyLong_FromUnsignedLong((long)x);
1074 1075 1076 1077 1078
}

static PyObject *
lu_longlong(const char *p, const formatdef *f)
{
1079
#ifdef HAVE_LONG_LONG
1080
	PY_LONG_LONG x = 0;
1081
	Py_ssize_t i = f->size;
1082
	const unsigned char *bytes = (const unsigned char *)p;
1083
	do {
1084
		x = (x<<8) | bytes[--i];
1085 1086 1087
	} while (i > 0);
	/* Extend the sign bit. */
	if (SIZEOF_LONG_LONG > f->size)
1088
		x |= -(x & ((PY_LONG_LONG)1 << ((8 * f->size) - 1)));
1089
	if (x >= LONG_MIN && x <= LONG_MAX)
1090 1091 1092
		return PyInt_FromLong(Py_SAFE_DOWNCAST(x, PY_LONG_LONG, long));
	return PyLong_FromLongLong(x);
#else
1093 1094 1095 1096
	return _PyLong_FromByteArray((const unsigned char *)p,
				      8,
				      1, /* little-endian */
				      1  /* signed */);
1097
#endif
1098 1099 1100 1101 1102
}

static PyObject *
lu_ulonglong(const char *p, const formatdef *f)
{
1103
#ifdef HAVE_LONG_LONG
1104
	unsigned PY_LONG_LONG x = 0;
1105
	Py_ssize_t i = f->size;
1106
	const unsigned char *bytes = (const unsigned char *)p;
1107
	do {
1108
		x = (x<<8) | bytes[--i];
1109
	} while (i > 0);
1110
	if (x <= LONG_MAX)
1111 1112 1113
		return PyInt_FromLong(Py_SAFE_DOWNCAST(x, unsigned PY_LONG_LONG, long));
	return PyLong_FromUnsignedLongLong(x);
#else
1114 1115 1116 1117
	return _PyLong_FromByteArray((const unsigned char *)p,
				      8,
				      1, /* little-endian */
				      0  /* signed */);
1118
#endif
1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136
}

static PyObject *
lu_float(const char *p, const formatdef *f)
{
	return unpack_float(p, 1);
}

static PyObject *
lu_double(const char *p, const formatdef *f)
{
	return unpack_double(p, 1);
}

static int
lp_int(char *p, PyObject *v, const formatdef *f)
{
	long x;
1137
	Py_ssize_t i;
1138
	if (get_wrapped_long(v, &x) < 0)
1139 1140
		return -1;
	i = f->size;
1141 1142
	if (i != SIZEOF_LONG) {
		if ((i == 2) && (x < -32768 || x > 32767))
1143
			RANGE_ERROR(x, f, 0, 0xffffL);
1144
#if (SIZEOF_LONG != 4)
1145
		else if ((i == 4) && (x < -2147483648L || x > 2147483647L))
1146 1147
			RANGE_ERROR(x, f, 0, 0xffffffffL);
#endif
1148
#ifdef PY_STRUCT_OVERFLOW_MASKING
1149 1150
		else if ((i == 1) && (x < -128 || x > 127))
			RANGE_ERROR(x, f, 0, 0xffL);
1151
#endif
1152
	}
1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163
	do {
		*p++ = (char)x;
		x >>= 8;
	} while (--i > 0);
	return 0;
}

static int
lp_uint(char *p, PyObject *v, const formatdef *f)
{
	unsigned long x;
1164
	Py_ssize_t i;
1165
	if (get_wrapped_ulong(v, &x) < 0)
1166 1167
		return -1;
	i = f->size;
1168 1169 1170 1171
	if (i != SIZEOF_LONG) {
		unsigned long maxint = 1;
		maxint <<= (unsigned long)(i * 8);
		if (x >= maxint)
1172
			RANGE_ERROR(x, f, 1, maxint - 1);
1173
	}
1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238
	do {
		*p++ = (char)x;
		x >>= 8;
	} while (--i > 0);
	return 0;
}

static int
lp_longlong(char *p, PyObject *v, const formatdef *f)
{
	int res;
	v = get_pylong(v);
	if (v == NULL)
		return -1;
	res = _PyLong_AsByteArray((PyLongObject*)v,
			   	  (unsigned char *)p,
				  8,
				  1, /* little_endian */
				  1  /* signed */);
	Py_DECREF(v);
	return res;
}

static int
lp_ulonglong(char *p, PyObject *v, const formatdef *f)
{
	int res;
	v = get_pylong(v);
	if (v == NULL)
		return -1;
	res = _PyLong_AsByteArray((PyLongObject*)v,
			   	  (unsigned char *)p,
				  8,
				  1, /* little_endian */
				  0  /* signed */);
	Py_DECREF(v);
	return res;
}

static int
lp_float(char *p, PyObject *v, const formatdef *f)
{
	double x = PyFloat_AsDouble(v);
	if (x == -1 && PyErr_Occurred()) {
		PyErr_SetString(StructError,
				"required argument is not a float");
		return -1;
	}
	return _PyFloat_Pack4(x, (unsigned char *)p, 1);
}

static int
lp_double(char *p, PyObject *v, const formatdef *f)
{
	double x = PyFloat_AsDouble(v);
	if (x == -1 && PyErr_Occurred()) {
		PyErr_SetString(StructError,
				"required argument is not a float");
		return -1;
	}
	return _PyFloat_Pack8(x, (unsigned char *)p, 1);
}

static formatdef lilendian_table[] = {
	{'x',	1,		0,		NULL},
1239 1240
#ifdef PY_STRUCT_OVERFLOW_MASKING
	/* Native packers do range checking without overflow masking. */
1241 1242 1243
	{'b',	1,		0,		nu_byte,	lp_int},
	{'B',	1,		0,		nu_ubyte,	lp_uint},
#else
1244 1245
	{'b',	1,		0,		nu_byte,	np_byte},
	{'B',	1,		0,		nu_ubyte,	np_ubyte},
1246
#endif
1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257
	{'c',	1,		0,		nu_char,	np_char},
	{'s',	1,		0,		NULL},
	{'p',	1,		0,		NULL},
	{'h',	2,		0,		lu_int,		lp_int},
	{'H',	2,		0,		lu_uint,	lp_uint},
	{'i',	4,		0,		lu_int,		lp_int},
	{'I',	4,		0,		lu_uint,	lp_uint},
	{'l',	4,		0,		lu_int,		lp_int},
	{'L',	4,		0,		lu_uint,	lp_uint},
	{'q',	8,		0,		lu_longlong,	lp_longlong},
	{'Q',	8,		0,		lu_ulonglong,	lp_ulonglong},
1258 1259
	{'t',	1,		0,		bu_bool,	bp_bool}, /* Std rep not endian dep,
		but potentially different from native rep -- reuse bx_bool funcs. */
1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
	{'f',	4,		0,		lu_float,	lp_float},
	{'d',	8,		0,		lu_double,	lp_double},
	{0}
};


static const formatdef *
whichtable(char **pfmt)
{
	const char *fmt = (*pfmt)++; /* May be backed out of later */
	switch (*fmt) {
	case '<':
		return lilendian_table;
	case '>':
	case '!': /* Network byte order is big-endian */
		return bigendian_table;
	case '=': { /* Host byte order -- different from native in aligment! */
		int n = 1;
		char *p = (char *) &n;
		if (*p == 1)
			return lilendian_table;
		else
			return bigendian_table;
	}
	default:
		--*pfmt; /* Back out of pointer increment */
		/* Fall through */
	case '@':
		return native_table;
	}
}


/* Get the table entry for a format code */

static const formatdef *
getentry(int c, const formatdef *f)
{
	for (; f->format != '\0'; f++) {
		if (f->format == c) {
			return f;
		}
	}
	PyErr_SetString(StructError, "bad char in struct format");
	return NULL;
}


/* Align a size according to a format code */

static int
1311
align(Py_ssize_t size, char c, const formatdef *e)
1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331
{
	if (e->format == c) {
		if (e->alignment) {
			size = ((size + e->alignment - 1)
				/ e->alignment)
				* e->alignment;
		}
	}
	return size;
}


/* calculate the size of a format string */

static int
prepare_s(PyStructObject *self)
{
	const formatdef *f;
	const formatdef *e;
	formatcode *codes;
1332

1333 1334 1335
	const char *s;
	const char *fmt;
	char c;
1336
	Py_ssize_t size, len, num, itemsize, x;
1337 1338 1339 1340

	fmt = PyString_AS_STRING(self->s_format);

	f = whichtable((char **)&fmt);
1341

1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368
	s = fmt;
	size = 0;
	len = 0;
	while ((c = *s++) != '\0') {
		if (isspace(Py_CHARMASK(c)))
			continue;
		if ('0' <= c && c <= '9') {
			num = c - '0';
			while ('0' <= (c = *s++) && c <= '9') {
				x = num*10 + (c - '0');
				if (x/10 != num) {
					PyErr_SetString(
						StructError,
						"overflow in item count");
					return -1;
				}
				num = x;
			}
			if (c == '\0')
				break;
		}
		else
			num = 1;

		e = getentry(c, f);
		if (e == NULL)
			return -1;
1369

1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389
		switch (c) {
			case 's': /* fall through */
			case 'p': len++; break;
			case 'x': break;
			default: len += num; break;
		}

		itemsize = e->size;
		size = align(size, c, e);
		x = num * itemsize;
		size += x;
		if (x/itemsize != num || size < 0) {
			PyErr_SetString(StructError,
					"total struct size too long");
			return -1;
		}
	}

	self->s_size = size;
	self->s_len = len;
1390
	codes = PyMem_MALLOC((len + 1) * sizeof(formatcode));
1391 1392 1393 1394 1395
	if (codes == NULL) {
		PyErr_NoMemory();
		return -1;
	}
	self->s_codes = codes;
1396

1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412
	s = fmt;
	size = 0;
	while ((c = *s++) != '\0') {
		if (isspace(Py_CHARMASK(c)))
			continue;
		if ('0' <= c && c <= '9') {
			num = c - '0';
			while ('0' <= (c = *s++) && c <= '9')
				num = num*10 + (c - '0');
			if (c == '\0')
				break;
		}
		else
			num = 1;

		e = getentry(c, f);
1413

1414
		size = align(size, c, e);
1415
		if (c == 's' || c == 'p') {
1416
			codes->offset = size;
1417
			codes->size = num;
1418 1419
			codes->fmtdef = e;
			codes++;
1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430
			size += num;
		} else if (c == 'x') {
			size += num;
		} else {
			while (--num >= 0) {
				codes->offset = size;
				codes->size = e->size;
				codes->fmtdef = e;
				codes++;
				size += e->size;
			}
1431 1432 1433
		}
	}
	codes->fmtdef = NULL;
1434 1435
	codes->offset = size;
	codes->size = 0;
1436

1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470
	return 0;
}

static PyObject *
s_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
{
	PyObject *self;

	assert(type != NULL && type->tp_alloc != NULL);

	self = type->tp_alloc(type, 0);
	if (self != NULL) {
		PyStructObject *s = (PyStructObject*)self;
		Py_INCREF(Py_None);
		s->s_format = Py_None;
		s->s_codes = NULL;
		s->s_size = -1;
		s->s_len = -1;
	}
	return self;
}

static int
s_init(PyObject *self, PyObject *args, PyObject *kwds)
{
	PyStructObject *soself = (PyStructObject *)self;
	PyObject *o_format = NULL;
	int ret = 0;
	static char *kwlist[] = {"format", 0};

	assert(PyStruct_Check(self));

	if (!PyArg_ParseTupleAndKeywords(args, kwds, "S:Struct", kwlist,
					 &o_format))
1471
		return -1;
1472 1473 1474 1475

	Py_INCREF(o_format);
	Py_XDECREF(soself->s_format);
	soself->s_format = o_format;
1476

1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489
	ret = prepare_s(soself);
	return ret;
}

static void
s_dealloc(PyStructObject *s)
{
	if (s->weakreflist != NULL)
		PyObject_ClearWeakRefs((PyObject *)s);
	if (s->s_codes != NULL) {
		PyMem_FREE(s->s_codes);
	}
	Py_XDECREF(s->s_format);
1490
	Py_Type(s)->tp_free((PyObject *)s);
1491 1492 1493
}

static PyObject *
1494
s_unpack_internal(PyStructObject *soself, char *startfrom) {
1495
	formatcode *code;
1496 1497
	Py_ssize_t i = 0;
	PyObject *result = PyTuple_New(soself->s_len);
1498 1499 1500 1501 1502 1503
	if (result == NULL)
		return NULL;

	for (code = soself->s_codes; code->fmtdef != NULL; code++) {
		PyObject *v;
		const formatdef *e = code->fmtdef;
1504
		const char *res = startfrom + code->offset;
1505
		if (e->format == 's') {
1506
			v = PyString_FromStringAndSize(res, code->size);
1507
		} else if (e->format == 'p') {
1508 1509 1510
			Py_ssize_t n = *(unsigned char*)res;
			if (n >= code->size)
				n = code->size - 1;
1511 1512
			v = PyString_FromStringAndSize(res + 1, n);
		} else {
1513
			v = e->unpack(res, e);
1514
		}
Neal Norwitz's avatar
Neal Norwitz committed
1515 1516 1517
		if (v == NULL)
			goto fail;
		PyTuple_SET_ITEM(result, i++, v);
1518 1519 1520 1521 1522 1523
	}

	return result;
fail:
	Py_DECREF(result);
	return NULL;
1524
}
1525 1526


1527
PyDoc_STRVAR(s_unpack__doc__,
1528
"S.unpack(str) -> (v1, v2, ...)\n\
1529 1530 1531 1532 1533 1534 1535 1536
\n\
Return tuple containing values unpacked according to this Struct's format.\n\
Requires len(str) == self.size. See struct.__doc__ for more on format\n\
strings.");

static PyObject *
s_unpack(PyObject *self, PyObject *inputstr)
{
1537 1538 1539
	char *start;
	Py_ssize_t len;
	PyObject *args=NULL, *result;
1540 1541
	PyStructObject *soself = (PyStructObject *)self;
	assert(PyStruct_Check(self));
1542
	assert(soself->s_codes != NULL);
1543 1544 1545 1546 1547
	if (inputstr == NULL)
		goto fail;
	if (PyString_Check(inputstr) &&
		PyString_GET_SIZE(inputstr) == soself->s_size) {
			return s_unpack_internal(soself, PyString_AS_STRING(inputstr));
1548
	}
1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565
	args = PyTuple_Pack(1, inputstr);
	if (args == NULL)
		return NULL;
	if (!PyArg_ParseTuple(args, "s#:unpack", &start, &len))
		goto fail;
	if (soself->s_size != len)
		goto fail;
	result = s_unpack_internal(soself, start);
	Py_DECREF(args);
	return result;

fail:
	Py_XDECREF(args);
	PyErr_Format(StructError,
		"unpack requires a string argument of length %zd",
		soself->s_size);
	return NULL;
1566 1567 1568
}

PyDoc_STRVAR(s_unpack_from__doc__,
1569
"S.unpack_from(buffer[, offset]) -> (v1, v2, ...)\n\
1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592
\n\
Return tuple containing values unpacked according to this Struct's format.\n\
Unlike unpack, unpack_from can unpack values from any object supporting\n\
the buffer API, not just str. Requires len(buffer[offset:]) >= self.size.\n\
See struct.__doc__ for more on format strings.");

static PyObject *
s_unpack_from(PyObject *self, PyObject *args, PyObject *kwds)
{
	static char *kwlist[] = {"buffer", "offset", 0};
#if (PY_VERSION_HEX < 0x02050000)
	static char *fmt = "z#|i:unpack_from";
#else
	static char *fmt = "z#|n:unpack_from";
#endif
	Py_ssize_t buffer_len = 0, offset = 0;
	char *buffer = NULL;
	PyStructObject *soself = (PyStructObject *)self;
	assert(PyStruct_Check(self));
	assert(soself->s_codes != NULL);

	if (!PyArg_ParseTupleAndKeywords(args, kwds, fmt, kwlist,
					 &buffer, &buffer_len, &offset))
1593
		return NULL;
1594 1595 1596 1597 1598 1599

	if (buffer == NULL) {
		PyErr_Format(StructError,
			"unpack_from requires a buffer argument");
		return NULL;
	}
1600

1601 1602 1603 1604 1605
	if (offset < 0)
		offset += buffer_len;

	if (offset < 0 || (buffer_len - offset) < soself->s_size) {
		PyErr_Format(StructError,
1606
			"unpack_from requires a buffer of at least %zd bytes",
1607 1608 1609 1610 1611 1612
			soself->s_size);
		return NULL;
	}
	return s_unpack_internal(soself, buffer + offset);
}

1613

1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625
/*
 * Guts of the pack function.
 *
 * Takes a struct object, a tuple of arguments, and offset in that tuple of
 * argument for where to start processing the arguments for packing, and a
 * character buffer for writing the packed string.  The caller must insure
 * that the buffer may contain the required length for packing the arguments.
 * 0 is returned on success, 1 is returned if there is an error.
 *
 */
static int
s_pack_internal(PyStructObject *soself, PyObject *args, int offset, char* buf)
1626 1627
{
	formatcode *code;
Neal Norwitz's avatar
Neal Norwitz committed
1628 1629
	/* XXX(nnorwitz): why does i need to be a local?  can we use
	   the offset parameter or do we need the wider width? */
1630
	Py_ssize_t i;
1631 1632 1633

	memset(buf, '\0', soself->s_size);
	i = offset;
1634 1635
	for (code = soself->s_codes; code->fmtdef != NULL; code++) {
		Py_ssize_t n;
Neal Norwitz's avatar
Neal Norwitz committed
1636
		PyObject *v = PyTuple_GET_ITEM(args, i++);
1637
		const formatdef *e = code->fmtdef;
1638
		char *res = buf + code->offset;
1639 1640 1641 1642
		if (e->format == 's') {
			if (!PyString_Check(v)) {
				PyErr_SetString(StructError,
						"argument for 's' must be a string");
1643
				return -1;
1644 1645
			}
			n = PyString_GET_SIZE(v);
1646 1647
			if (n > code->size)
				n = code->size;
1648 1649 1650 1651 1652 1653
			if (n > 0)
				memcpy(res, PyString_AS_STRING(v), n);
		} else if (e->format == 'p') {
			if (!PyString_Check(v)) {
				PyErr_SetString(StructError,
						"argument for 'p' must be a string");
1654
				return -1;
1655 1656
			}
			n = PyString_GET_SIZE(v);
1657 1658
			if (n > (code->size - 1))
				n = code->size - 1;
1659 1660 1661 1662 1663 1664
			if (n > 0)
				memcpy(res + 1, PyString_AS_STRING(v), n);
			if (n > 255)
				n = 255;
			*res = Py_SAFE_DOWNCAST(n, Py_ssize_t, unsigned char);
		} else {
1665 1666 1667 1668
			if (e->pack(res, v, e) < 0) {
				if (PyLong_Check(v) && PyErr_ExceptionMatches(PyExc_OverflowError))
					PyErr_SetString(StructError,
							"long too large to convert to int");
1669
				return -1;
1670
			}
1671 1672
		}
	}
1673

1674 1675 1676 1677 1678 1679
	/* Success */
	return 0;
}


PyDoc_STRVAR(s_pack__doc__,
1680
"S.pack(v1, v2, ...) -> string\n\
1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694
\n\
Return a string containing values v1, v2, ... packed according to this\n\
Struct's format. See struct.__doc__ for more on format strings.");

static PyObject *
s_pack(PyObject *self, PyObject *args)
{
	PyStructObject *soself;
	PyObject *result;

	/* Validate arguments. */
	soself = (PyStructObject *)self;
	assert(PyStruct_Check(self));
	assert(soself->s_codes != NULL);
1695
	if (PyTuple_GET_SIZE(args) != soself->s_len)
1696 1697
	{
		PyErr_Format(StructError,
1698
			"pack requires exactly %zd arguments", soself->s_len);
1699 1700
		return NULL;
	}
1701

1702 1703 1704 1705
	/* Allocate a new string */
	result = PyString_FromStringAndSize((char *)NULL, soself->s_size);
	if (result == NULL)
		return NULL;
1706

1707 1708 1709 1710 1711 1712
	/* Call the guts */
	if ( s_pack_internal(soself, args, 0, PyString_AS_STRING(result)) != 0 ) {
		Py_DECREF(result);
		return NULL;
	}

1713
	return result;
1714
}
1715

1716 1717
PyDoc_STRVAR(s_pack_into__doc__,
"S.pack_into(buffer, offset, v1, v2, ...)\n\
1718
\n\
1719
Pack the values v1, v2, ... according to this Struct's format, write \n\
1720 1721
the packed bytes into the writable buffer buf starting at offset.  Note\n\
that the offset is not an optional argument.  See struct.__doc__ for \n\
1722 1723 1724
more on format strings.");

static PyObject *
1725
s_pack_into(PyObject *self, PyObject *args)
1726 1727 1728 1729 1730 1731 1732 1733 1734
{
	PyStructObject *soself;
	char *buffer;
	Py_ssize_t buffer_len, offset;

	/* Validate arguments.  +1 is for the first arg as buffer. */
	soself = (PyStructObject *)self;
	assert(PyStruct_Check(self));
	assert(soself->s_codes != NULL);
1735
	if (PyTuple_GET_SIZE(args) != (soself->s_len + 2))
1736 1737
	{
		PyErr_Format(StructError,
1738
			     "pack_into requires exactly %zd arguments",
1739 1740 1741 1742 1743
			     (soself->s_len + 2));
		return NULL;
	}

	/* Extract a writable memory buffer from the first argument */
1744 1745
	if ( PyObject_AsWriteBuffer(PyTuple_GET_ITEM(args, 0),
								(void**)&buffer, &buffer_len) == -1 ) {
1746
		return NULL;
1747 1748
	}
	assert( buffer_len >= 0 );
1749 1750

	/* Extract the offset from the first argument */
1751
	offset = PyInt_AsSsize_t(PyTuple_GET_ITEM(args, 1));
1752

1753
	/* Support negative offsets. */
1754 1755 1756 1757 1758 1759
	if (offset < 0)
		offset += buffer_len;

	/* Check boundaries */
	if (offset < 0 || (buffer_len - offset) < soself->s_size) {
		PyErr_Format(StructError,
1760
			     "pack_into requires a buffer of at least %zd bytes",
1761 1762 1763
			     soself->s_size);
		return NULL;
	}
1764

1765 1766 1767 1768 1769
	/* Call the guts */
	if ( s_pack_internal(soself, args, 2, buffer + offset) != 0 ) {
		return NULL;
	}

1770
	Py_RETURN_NONE;
1771 1772
}

1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784
static PyObject *
s_get_format(PyStructObject *self, void *unused)
{
	Py_INCREF(self->s_format);
	return self->s_format;
}

static PyObject *
s_get_size(PyStructObject *self, void *unused)
{
    return PyInt_FromSsize_t(self->s_size);
}
1785 1786 1787 1788

/* List of functions */

static struct PyMethodDef s_methods[] = {
1789 1790 1791
	{"pack",	s_pack,		METH_VARARGS, s_pack__doc__},
	{"pack_into",	s_pack_into,	METH_VARARGS, s_pack_into__doc__},
	{"unpack",	s_unpack,       METH_O, s_unpack__doc__},
1792
	{"unpack_from",	(PyCFunction)s_unpack_from, METH_VARARGS|METH_KEYWORDS,
1793
			s_unpack_from__doc__},
1794 1795 1796 1797 1798 1799 1800
	{NULL,	 NULL}		/* sentinel */
};

PyDoc_STRVAR(s__doc__, "Compiled struct object");

#define OFF(x) offsetof(PyStructObject, x)

1801
static PyGetSetDef s_getsetlist[] = {
1802 1803
	{"format", (getter)s_get_format, (setter)NULL, "struct format string", NULL},
	{"size", (getter)s_get_size, (setter)NULL, "struct size in bytes", NULL},
1804
	{NULL} /* sentinel */
1805 1806 1807 1808
};

static
PyTypeObject PyStructType = {
1809
	PyVarObject_HEAD_INIT(NULL, 0)
1810 1811 1812
	"Struct",
	sizeof(PyStructObject),
	0,
1813
	(destructor)s_dealloc,	/* tp_dealloc */
1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824
	0,					/* tp_print */
	0,					/* tp_getattr */
	0,					/* tp_setattr */
	0,					/* tp_compare */
	0,					/* tp_repr */
	0,					/* tp_as_number */
	0,					/* tp_as_sequence */
	0,					/* tp_as_mapping */
	0,					/* tp_hash */
	0,					/* tp_call */
	0,					/* tp_str */
1825 1826
	PyObject_GenericGetAttr,	/* tp_getattro */
	PyObject_GenericSetAttr,	/* tp_setattro */
1827
	0,					/* tp_as_buffer */
1828 1829
	Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE | Py_TPFLAGS_HAVE_WEAKREFS,/* tp_flags */
	s__doc__,			/* tp_doc */
1830 1831 1832 1833 1834 1835
	0,					/* tp_traverse */
	0,					/* tp_clear */
	0,					/* tp_richcompare */
	offsetof(PyStructObject, weakreflist),	/* tp_weaklistoffset */
	0,					/* tp_iter */
	0,					/* tp_iternext */
1836 1837 1838
	s_methods,			/* tp_methods */
	NULL,				/* tp_members */
	s_getsetlist,		/* tp_getset */
1839 1840 1841 1842 1843
	0,					/* tp_base */
	0,					/* tp_dict */
	0,					/* tp_descr_get */
	0,					/* tp_descr_set */
	0,					/* tp_dictoffset */
1844 1845 1846 1847
	s_init,				/* tp_init */
	PyType_GenericAlloc,/* tp_alloc */
	s_new,				/* tp_new */
	PyObject_Del,		/* tp_free */
1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858
};

/* Module initialization */

PyMODINIT_FUNC
init_struct(void)
{
	PyObject *m = Py_InitModule("_struct", NULL);
	if (m == NULL)
		return;

1859
	Py_Type(&PyStructType) = &PyType_Type;
Bob Ippolito's avatar
Bob Ippolito committed
1860 1861 1862
	if (PyType_Ready(&PyStructType) < 0)
		return;

1863
#ifdef PY_STRUCT_OVERFLOW_MASKING
1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878
	if (pyint_zero == NULL) {
		pyint_zero = PyInt_FromLong(0);
		if (pyint_zero == NULL)
			return;
	}
	if (pylong_ulong_mask == NULL) {
#if (SIZEOF_LONG == 4)
		pylong_ulong_mask = PyLong_FromString("FFFFFFFF", NULL, 16);
#else
		pylong_ulong_mask = PyLong_FromString("FFFFFFFFFFFFFFFF", NULL, 16);
#endif
		if (pylong_ulong_mask == NULL)
			return;
	}

1879
#else
1880 1881
	/* This speed trick can't be used until overflow masking goes away, because
	   native endian always raises exceptions instead of overflow masking. */
1882

1883 1884 1885 1886 1887 1888 1889 1890 1891
	/* Check endian and swap in faster functions */
	{
		int one = 1;
		formatdef *native = native_table;
		formatdef *other, *ptr;
		if ((int)*(unsigned char*)&one)
			other = lilendian_table;
		else
			other = bigendian_table;
1892 1893 1894 1895
		/* Scan through the native table, find a matching
		   entry in the endian table and swap in the
		   native implementations whenever possible
		   (64-bit platforms may not have "standard" sizes) */
1896 1897 1898 1899
		while (native->format != '\0' && other->format != '\0') {
			ptr = other;
			while (ptr->format != '\0') {
				if (ptr->format == native->format) {
1900 1901
					/* Match faster when formats are
					   listed in the same order */
1902 1903
					if (ptr == other)
						other++;
1904
					/* Only use the trick if the
1905 1906 1907 1908 1909 1910 1911 1912 1913
					   size matches */
					if (ptr->size != native->size)
						break;
					/* Skip float and double, could be
					   "unknown" float format */
					if (ptr->format == 'd' || ptr->format == 'f')
						break;
					ptr->pack = native->pack;
					ptr->unpack = native->unpack;
1914 1915 1916 1917 1918 1919 1920
					break;
				}
				ptr++;
			}
			native++;
		}
	}
1921
#endif
1922

1923 1924 1925 1926 1927 1928
	/* Add some symbolic constants to the module */
	if (StructError == NULL) {
		StructError = PyErr_NewException("struct.error", NULL, NULL);
		if (StructError == NULL)
			return;
	}
1929

1930 1931
	Py_INCREF(StructError);
	PyModule_AddObject(m, "error", StructError);
1932

1933 1934
	Py_INCREF((PyObject*)&PyStructType);
	PyModule_AddObject(m, "Struct", (PyObject*)&PyStructType);
1935

1936
	PyModule_AddIntConstant(m, "_PY_STRUCT_RANGE_CHECKING", 1);
1937 1938
#ifdef PY_STRUCT_OVERFLOW_MASKING
	PyModule_AddIntConstant(m, "_PY_STRUCT_OVERFLOW_MASKING", 1);
1939
#endif
1940 1941 1942 1943
#ifdef PY_STRUCT_FLOAT_COERCE
	PyModule_AddIntConstant(m, "_PY_STRUCT_FLOAT_COERCE", 1);
#endif

1944
}