-
-
Notifications
You must be signed in to change notification settings - Fork 35k
Expand file tree
/
Copy pathobject.c
More file actions
1981 lines (1714 loc) · 54.2 KB
/
Copy pathobject.c
File metadata and controls
1981 lines (1714 loc) · 54.2 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
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
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
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
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
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
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
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
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
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
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
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
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
732
733
734
735
736
737
738
739
740
741
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
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
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
/* Generic object operations; and implementation of None (NoObject) */
#include "Python.h"
#include "frameobject.h"
#ifdef __cplusplus
extern "C" {
#endif
#ifdef Py_REF_DEBUG
Py_ssize_t _Py_RefTotal;
Py_ssize_t
_Py_GetRefTotal(void)
{
PyObject *o;
Py_ssize_t total = _Py_RefTotal;
/* ignore the references to the dummy object of the dicts and sets
because they are not reliable and not useful (now that the
hash table code is well-tested) */
o = _PyDict_Dummy();
if (o != NULL)
total -= o->ob_refcnt;
o = _PySet_Dummy();
if (o != NULL)
total -= o->ob_refcnt;
return total;
}
#endif /* Py_REF_DEBUG */
int Py_DivisionWarningFlag;
/* Object allocation routines used by NEWOBJ and NEWVAROBJ macros.
These are used by the individual routines for object creation.
Do not call them otherwise, they do not initialize the object! */
#ifdef Py_TRACE_REFS
/* Head of circular doubly-linked list of all objects. These are linked
* together via the _ob_prev and _ob_next members of a PyObject, which
* exist only in a Py_TRACE_REFS build.
*/
static PyObject refchain = {&refchain, &refchain};
/* Insert op at the front of the list of all objects. If force is true,
* op is added even if _ob_prev and _ob_next are non-NULL already. If
* force is false amd _ob_prev or _ob_next are non-NULL, do nothing.
* force should be true if and only if op points to freshly allocated,
* uninitialized memory, or you've unlinked op from the list and are
* relinking it into the front.
* Note that objects are normally added to the list via _Py_NewReference,
* which is called by PyObject_Init. Not all objects are initialized that
* way, though; exceptions include statically allocated type objects, and
* statically allocated singletons (like Py_True and Py_None).
*/
void
_Py_AddToAllObjects(PyObject *op, int force)
{
#ifdef Py_DEBUG
if (!force) {
/* If it's initialized memory, op must be in or out of
* the list unambiguously.
*/
assert((op->_ob_prev == NULL) == (op->_ob_next == NULL));
}
#endif
if (force || op->_ob_prev == NULL) {
op->_ob_next = refchain._ob_next;
op->_ob_prev = &refchain;
refchain._ob_next->_ob_prev = op;
refchain._ob_next = op;
}
}
#endif /* Py_TRACE_REFS */
#ifdef COUNT_ALLOCS
static PyTypeObject *type_list;
/* All types are added to type_list, at least when
they get one object created. That makes them
immortal, which unfortunately contributes to
garbage itself. If unlist_types_without_objects
is set, they will be removed from the type_list
once the last object is deallocated. */
static int unlist_types_without_objects;
extern Py_ssize_t tuple_zero_allocs, fast_tuple_allocs;
extern Py_ssize_t quick_int_allocs, quick_neg_int_allocs;
extern Py_ssize_t null_strings, one_strings;
void
dump_counts(FILE* f)
{
PyTypeObject *tp;
for (tp = type_list; tp; tp = tp->tp_next)
fprintf(f, "%s alloc'd: %" PY_FORMAT_SIZE_T "d, "
"freed: %" PY_FORMAT_SIZE_T "d, "
"max in use: %" PY_FORMAT_SIZE_T "d\n",
tp->tp_name, tp->tp_allocs, tp->tp_frees,
tp->tp_maxalloc);
fprintf(f, "fast tuple allocs: %" PY_FORMAT_SIZE_T "d, "
"empty: %" PY_FORMAT_SIZE_T "d\n",
fast_tuple_allocs, tuple_zero_allocs);
fprintf(f, "fast int allocs: pos: %" PY_FORMAT_SIZE_T "d, "
"neg: %" PY_FORMAT_SIZE_T "d\n",
quick_int_allocs, quick_neg_int_allocs);
fprintf(f, "null strings: %" PY_FORMAT_SIZE_T "d, "
"1-strings: %" PY_FORMAT_SIZE_T "d\n",
null_strings, one_strings);
}
PyObject *
get_counts(void)
{
PyTypeObject *tp;
PyObject *result;
PyObject *v;
result = PyList_New(0);
if (result == NULL)
return NULL;
for (tp = type_list; tp; tp = tp->tp_next) {
v = Py_BuildValue("(snnn)", tp->tp_name, tp->tp_allocs,
tp->tp_frees, tp->tp_maxalloc);
if (v == NULL) {
Py_DECREF(result);
return NULL;
}
if (PyList_Append(result, v) < 0) {
Py_DECREF(v);
Py_DECREF(result);
return NULL;
}
Py_DECREF(v);
}
return result;
}
void
inc_count(PyTypeObject *tp)
{
if (tp->tp_next == NULL && tp->tp_prev == NULL) {
/* first time; insert in linked list */
if (tp->tp_next != NULL) /* sanity check */
Py_FatalError("XXX inc_count sanity check");
if (type_list)
type_list->tp_prev = tp;
tp->tp_next = type_list;
/* Note that as of Python 2.2, heap-allocated type objects
* can go away, but this code requires that they stay alive
* until program exit. That's why we're careful with
* refcounts here. type_list gets a new reference to tp,
* while ownership of the reference type_list used to hold
* (if any) was transferred to tp->tp_next in the line above.
* tp is thus effectively immortal after this.
*/
Py_INCREF(tp);
type_list = tp;
#ifdef Py_TRACE_REFS
/* Also insert in the doubly-linked list of all objects,
* if not already there.
*/
_Py_AddToAllObjects((PyObject *)tp, 0);
#endif
}
tp->tp_allocs++;
if (tp->tp_allocs - tp->tp_frees > tp->tp_maxalloc)
tp->tp_maxalloc = tp->tp_allocs - tp->tp_frees;
}
void dec_count(PyTypeObject *tp)
{
tp->tp_frees++;
if (unlist_types_without_objects &&
tp->tp_allocs == tp->tp_frees) {
/* unlink the type from type_list */
if (tp->tp_prev)
tp->tp_prev->tp_next = tp->tp_next;
else
type_list = tp->tp_next;
if (tp->tp_next)
tp->tp_next->tp_prev = tp->tp_prev;
tp->tp_next = tp->tp_prev = NULL;
Py_DECREF(tp);
}
}
#endif
#ifdef Py_REF_DEBUG
/* Log a fatal error; doesn't return. */
void
_Py_NegativeRefcount(const char *fname, int lineno, PyObject *op)
{
char buf[300];
PyOS_snprintf(buf, sizeof(buf),
"%s:%i object at %p has negative ref count "
"%" PY_FORMAT_SIZE_T "d",
fname, lineno, op, op->ob_refcnt);
Py_FatalError(buf);
}
#endif /* Py_REF_DEBUG */
void
Py_IncRef(PyObject *o)
{
Py_XINCREF(o);
}
void
Py_DecRef(PyObject *o)
{
Py_XDECREF(o);
}
PyObject *
PyObject_Init(PyObject *op, PyTypeObject *tp)
{
if (op == NULL)
return PyErr_NoMemory();
/* Any changes should be reflected in PyObject_INIT (objimpl.h) */
Py_TYPE(op) = tp;
_Py_NewReference(op);
return op;
}
PyVarObject *
PyObject_InitVar(PyVarObject *op, PyTypeObject *tp, Py_ssize_t size)
{
if (op == NULL)
return (PyVarObject *) PyErr_NoMemory();
/* Any changes should be reflected in PyObject_INIT_VAR */
op->ob_size = size;
Py_TYPE(op) = tp;
_Py_NewReference((PyObject *)op);
return op;
}
PyObject *
_PyObject_New(PyTypeObject *tp)
{
PyObject *op;
op = (PyObject *) PyObject_MALLOC(_PyObject_SIZE(tp));
if (op == NULL)
return PyErr_NoMemory();
return PyObject_INIT(op, tp);
}
PyVarObject *
_PyObject_NewVar(PyTypeObject *tp, Py_ssize_t nitems)
{
PyVarObject *op;
const size_t size = _PyObject_VAR_SIZE(tp, nitems);
op = (PyVarObject *) PyObject_MALLOC(size);
if (op == NULL)
return (PyVarObject *)PyErr_NoMemory();
return PyObject_INIT_VAR(op, tp, nitems);
}
int
PyObject_Print(PyObject *op, FILE *fp, int flags)
{
int ret = 0;
if (PyErr_CheckSignals())
return -1;
#ifdef USE_STACKCHECK
if (PyOS_CheckStack()) {
PyErr_SetString(PyExc_MemoryError, "stack overflow");
return -1;
}
#endif
clearerr(fp); /* Clear any previous error condition */
if (op == NULL) {
Py_BEGIN_ALLOW_THREADS
fprintf(fp, "<nil>");
Py_END_ALLOW_THREADS
}
else {
if (op->ob_refcnt <= 0)
/* XXX(twouters) cast refcount to long until %zd is
universally available */
Py_BEGIN_ALLOW_THREADS
fprintf(fp, "<refcnt %ld at %p>",
(long)op->ob_refcnt, op);
Py_END_ALLOW_THREADS
else {
PyObject *s;
if (flags & Py_PRINT_RAW)
s = PyObject_Str(op);
else
s = PyObject_Repr(op);
if (s == NULL)
ret = -1;
else if (PyBytes_Check(s)) {
fwrite(PyBytes_AS_STRING(s), 1,
PyBytes_GET_SIZE(s), fp);
}
else if (PyUnicode_Check(s)) {
PyObject *t;
t = PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(s),
PyUnicode_GET_SIZE(s),
"backslashreplace");
if (t == NULL)
ret = 0;
else {
fwrite(PyBytes_AS_STRING(t), 1,
PyBytes_GET_SIZE(t), fp);
Py_DECREF(t);
}
}
else {
PyErr_Format(PyExc_TypeError,
"str() or repr() returned '%.100s'",
s->ob_type->tp_name);
ret = -1;
}
Py_XDECREF(s);
}
}
if (ret == 0) {
if (ferror(fp)) {
PyErr_SetFromErrno(PyExc_IOError);
clearerr(fp);
ret = -1;
}
}
return ret;
}
/* For debugging convenience. Set a breakpoint here and call it from your DLL */
void
_Py_BreakPoint(void)
{
}
/* For debugging convenience. See Misc/gdbinit for some useful gdb hooks */
void
_PyObject_Dump(PyObject* op)
{
if (op == NULL)
fprintf(stderr, "NULL\n");
else {
#ifdef WITH_THREAD
PyGILState_STATE gil;
#endif
fprintf(stderr, "object : ");
#ifdef WITH_THREAD
gil = PyGILState_Ensure();
#endif
(void)PyObject_Print(op, stderr, 0);
#ifdef WITH_THREAD
PyGILState_Release(gil);
#endif
/* XXX(twouters) cast refcount to long until %zd is
universally available */
fprintf(stderr, "\n"
"type : %s\n"
"refcount: %ld\n"
"address : %p\n",
Py_TYPE(op)==NULL ? "NULL" : Py_TYPE(op)->tp_name,
(long)op->ob_refcnt,
op);
}
}
PyObject *
PyObject_Repr(PyObject *v)
{
PyObject *res;
if (PyErr_CheckSignals())
return NULL;
#ifdef USE_STACKCHECK
if (PyOS_CheckStack()) {
PyErr_SetString(PyExc_MemoryError, "stack overflow");
return NULL;
}
#endif
if (v == NULL)
return PyUnicode_FromString("<NULL>");
if (Py_TYPE(v)->tp_repr == NULL)
return PyUnicode_FromFormat("<%s object at %p>",
v->ob_type->tp_name, v);
res = (*v->ob_type->tp_repr)(v);
if (res != NULL && !PyUnicode_Check(res)) {
PyErr_Format(PyExc_TypeError,
"__repr__ returned non-string (type %.200s)",
res->ob_type->tp_name);
Py_DECREF(res);
return NULL;
}
return res;
}
PyObject *
PyObject_Str(PyObject *v)
{
PyObject *res;
if (PyErr_CheckSignals())
return NULL;
#ifdef USE_STACKCHECK
if (PyOS_CheckStack()) {
PyErr_SetString(PyExc_MemoryError, "stack overflow");
return NULL;
}
#endif
if (v == NULL)
return PyUnicode_FromString("<NULL>");
if (PyUnicode_CheckExact(v)) {
Py_INCREF(v);
return v;
}
if (Py_TYPE(v)->tp_str == NULL)
return PyObject_Repr(v);
/* It is possible for a type to have a tp_str representation that loops
infinitely. */
if (Py_EnterRecursiveCall(" while getting the str of an object"))
return NULL;
res = (*Py_TYPE(v)->tp_str)(v);
Py_LeaveRecursiveCall();
if (res == NULL)
return NULL;
if (!PyUnicode_Check(res)) {
PyErr_Format(PyExc_TypeError,
"__str__ returned non-string (type %.200s)",
Py_TYPE(res)->tp_name);
Py_DECREF(res);
return NULL;
}
return res;
}
PyObject *
PyObject_ASCII(PyObject *v)
{
PyObject *repr, *ascii, *res;
repr = PyObject_Repr(v);
if (repr == NULL)
return NULL;
/* repr is guaranteed to be a PyUnicode object by PyObject_Repr */
ascii = PyUnicode_EncodeASCII(
PyUnicode_AS_UNICODE(repr),
PyUnicode_GET_SIZE(repr),
"backslashreplace");
Py_DECREF(repr);
if (ascii == NULL)
return NULL;
res = PyUnicode_DecodeASCII(
PyBytes_AS_STRING(ascii),
PyBytes_GET_SIZE(ascii),
NULL);
Py_DECREF(ascii);
return res;
}
PyObject *
PyObject_Bytes(PyObject *v)
{
PyObject *result, *func;
static PyObject *bytesstring = NULL;
if (v == NULL)
return PyBytes_FromString("<NULL>");
if (PyBytes_CheckExact(v)) {
Py_INCREF(v);
return v;
}
func = _PyObject_LookupSpecial(v, "__bytes__", &bytesstring);
if (func != NULL) {
result = PyObject_CallFunctionObjArgs(func, NULL);
Py_DECREF(func);
if (result == NULL)
return NULL;
if (!PyBytes_Check(result)) {
PyErr_Format(PyExc_TypeError,
"__bytes__ returned non-bytes (type %.200s)",
Py_TYPE(result)->tp_name);
Py_DECREF(result);
return NULL;
}
return result;
}
else if (PyErr_Occurred())
return NULL;
return PyBytes_FromObject(v);
}
/* For Python 3.0.1 and later, the old three-way comparison has been
completely removed in favour of rich comparisons. PyObject_Compare() and
PyObject_Cmp() are gone, and the builtin cmp function no longer exists.
The old tp_compare slot has been renamed to tp_reserved, and should no
longer be used. Use tp_richcompare instead.
See (*) below for practical amendments.
tp_richcompare gets called with a first argument of the appropriate type
and a second object of an arbitrary type. We never do any kind of
coercion.
The tp_richcompare slot should return an object, as follows:
NULL if an exception occurred
NotImplemented if the requested comparison is not implemented
any other false value if the requested comparison is false
any other true value if the requested comparison is true
The PyObject_RichCompare[Bool]() wrappers raise TypeError when they get
NotImplemented.
(*) Practical amendments:
- If rich comparison returns NotImplemented, == and != are decided by
comparing the object pointer (i.e. falling back to the base object
implementation).
*/
/* Map rich comparison operators to their swapped version, e.g. LT <--> GT */
int _Py_SwappedOp[] = {Py_GT, Py_GE, Py_EQ, Py_NE, Py_LT, Py_LE};
static char *opstrings[] = {"<", "<=", "==", "!=", ">", ">="};
/* Perform a rich comparison, raising TypeError when the requested comparison
operator is not supported. */
static PyObject *
do_richcompare(PyObject *v, PyObject *w, int op)
{
richcmpfunc f;
PyObject *res;
int checked_reverse_op = 0;
if (v->ob_type != w->ob_type &&
PyType_IsSubtype(w->ob_type, v->ob_type) &&
(f = w->ob_type->tp_richcompare) != NULL) {
checked_reverse_op = 1;
res = (*f)(w, v, _Py_SwappedOp[op]);
if (res != Py_NotImplemented)
return res;
Py_DECREF(res);
}
if ((f = v->ob_type->tp_richcompare) != NULL) {
res = (*f)(v, w, op);
if (res != Py_NotImplemented)
return res;
Py_DECREF(res);
}
if (!checked_reverse_op && (f = w->ob_type->tp_richcompare) != NULL) {
res = (*f)(w, v, _Py_SwappedOp[op]);
if (res != Py_NotImplemented)
return res;
Py_DECREF(res);
}
/* If neither object implements it, provide a sensible default
for == and !=, but raise an exception for ordering. */
switch (op) {
case Py_EQ:
res = (v == w) ? Py_True : Py_False;
break;
case Py_NE:
res = (v != w) ? Py_True : Py_False;
break;
default:
/* XXX Special-case None so it doesn't show as NoneType() */
PyErr_Format(PyExc_TypeError,
"unorderable types: %.100s() %s %.100s()",
v->ob_type->tp_name,
opstrings[op],
w->ob_type->tp_name);
return NULL;
}
Py_INCREF(res);
return res;
}
/* Perform a rich comparison with object result. This wraps do_richcompare()
with a check for NULL arguments and a recursion check. */
PyObject *
PyObject_RichCompare(PyObject *v, PyObject *w, int op)
{
PyObject *res;
assert(Py_LT <= op && op <= Py_GE);
if (v == NULL || w == NULL) {
if (!PyErr_Occurred())
PyErr_BadInternalCall();
return NULL;
}
if (Py_EnterRecursiveCall(" in comparison"))
return NULL;
res = do_richcompare(v, w, op);
Py_LeaveRecursiveCall();
return res;
}
/* Perform a rich comparison with integer result. This wraps
PyObject_RichCompare(), returning -1 for error, 0 for false, 1 for true. */
int
PyObject_RichCompareBool(PyObject *v, PyObject *w, int op)
{
PyObject *res;
int ok;
/* Quick result when objects are the same.
Guarantees that identity implies equality. */
if (v == w) {
if (op == Py_EQ)
return 1;
else if (op == Py_NE)
return 0;
}
res = PyObject_RichCompare(v, w, op);
if (res == NULL)
return -1;
if (PyBool_Check(res))
ok = (res == Py_True);
else
ok = PyObject_IsTrue(res);
Py_DECREF(res);
return ok;
}
/* Set of hash utility functions to help maintaining the invariant that
if a==b then hash(a)==hash(b)
All the utility functions (_Py_Hash*()) return "-1" to signify an error.
*/
/* For numeric types, the hash of a number x is based on the reduction
of x modulo the prime P = 2**_PyHASH_BITS - 1. It's designed so that
hash(x) == hash(y) whenever x and y are numerically equal, even if
x and y have different types.
A quick summary of the hashing strategy:
(1) First define the 'reduction of x modulo P' for any rational
number x; this is a standard extension of the usual notion of
reduction modulo P for integers. If x == p/q (written in lowest
terms), the reduction is interpreted as the reduction of p times
the inverse of the reduction of q, all modulo P; if q is exactly
divisible by P then define the reduction to be infinity. So we've
got a well-defined map
reduce : { rational numbers } -> { 0, 1, 2, ..., P-1, infinity }.
(2) Now for a rational number x, define hash(x) by:
reduce(x) if x >= 0
-reduce(-x) if x < 0
If the result of the reduction is infinity (this is impossible for
integers, floats and Decimals) then use the predefined hash value
_PyHASH_INF for x >= 0, or -_PyHASH_INF for x < 0, instead.
_PyHASH_INF, -_PyHASH_INF and _PyHASH_NAN are also used for the
hashes of float and Decimal infinities and nans.
A selling point for the above strategy is that it makes it possible
to compute hashes of decimal and binary floating-point numbers
efficiently, even if the exponent of the binary or decimal number
is large. The key point is that
reduce(x * y) == reduce(x) * reduce(y) (modulo _PyHASH_MODULUS)
provided that {reduce(x), reduce(y)} != {0, infinity}. The reduction of a
binary or decimal float is never infinity, since the denominator is a power
of 2 (for binary) or a divisor of a power of 10 (for decimal). So we have,
for nonnegative x,
reduce(x * 2**e) == reduce(x) * reduce(2**e) % _PyHASH_MODULUS
reduce(x * 10**e) == reduce(x) * reduce(10**e) % _PyHASH_MODULUS
and reduce(10**e) can be computed efficiently by the usual modular
exponentiation algorithm. For reduce(2**e) it's even better: since
P is of the form 2**n-1, reduce(2**e) is 2**(e mod n), and multiplication
by 2**(e mod n) modulo 2**n-1 just amounts to a rotation of bits.
*/
Py_hash_t
_Py_HashDouble(double v)
{
int e, sign;
double m;
Py_uhash_t x, y;
if (!Py_IS_FINITE(v)) {
if (Py_IS_INFINITY(v))
return v > 0 ? _PyHASH_INF : -_PyHASH_INF;
else
return _PyHASH_NAN;
}
m = frexp(v, &e);
sign = 1;
if (m < 0) {
sign = -1;
m = -m;
}
/* process 28 bits at a time; this should work well both for binary
and hexadecimal floating point. */
x = 0;
while (m) {
x = ((x << 28) & _PyHASH_MODULUS) | x >> (_PyHASH_BITS - 28);
m *= 268435456.0; /* 2**28 */
e -= 28;
y = (Py_uhash_t)m; /* pull out integer part */
m -= y;
x += y;
if (x >= _PyHASH_MODULUS)
x -= _PyHASH_MODULUS;
}
/* adjust for the exponent; first reduce it modulo _PyHASH_BITS */
e = e >= 0 ? e % _PyHASH_BITS : _PyHASH_BITS-1-((-1-e) % _PyHASH_BITS);
x = ((x << e) & _PyHASH_MODULUS) | x >> (_PyHASH_BITS - e);
x = x * sign;
if (x == (Py_uhash_t)-1)
x = (Py_uhash_t)-2;
return (Py_hash_t)x;
}
Py_hash_t
_Py_HashPointer(void *p)
{
Py_hash_t x;
size_t y = (size_t)p;
/* bottom 3 or 4 bits are likely to be 0; rotate y by 4 to avoid
excessive hash collisions for dicts and sets */
y = (y >> 4) | (y << (8 * SIZEOF_VOID_P - 4));
x = (Py_hash_t)y;
if (x == -1)
x = -2;
return x;
}
Py_hash_t
PyObject_HashNotImplemented(PyObject *v)
{
PyErr_Format(PyExc_TypeError, "unhashable type: '%.200s'",
Py_TYPE(v)->tp_name);
return -1;
}
_Py_HashSecret_t _Py_HashSecret;
Py_hash_t
PyObject_Hash(PyObject *v)
{
PyTypeObject *tp = Py_TYPE(v);
if (tp->tp_hash != NULL)
return (*tp->tp_hash)(v);
/* To keep to the general practice that inheriting
* solely from object in C code should work without
* an explicit call to PyType_Ready, we implicitly call
* PyType_Ready here and then check the tp_hash slot again
*/
if (tp->tp_dict == NULL) {
if (PyType_Ready(tp) < 0)
return -1;
if (tp->tp_hash != NULL)
return (*tp->tp_hash)(v);
}
/* Otherwise, the object can't be hashed */
return PyObject_HashNotImplemented(v);
}
PyObject *
PyObject_GetAttrString(PyObject *v, const char *name)
{
PyObject *w, *res;
if (Py_TYPE(v)->tp_getattr != NULL)
return (*Py_TYPE(v)->tp_getattr)(v, (char*)name);
w = PyUnicode_InternFromString(name);
if (w == NULL)
return NULL;
res = PyObject_GetAttr(v, w);
Py_XDECREF(w);
return res;
}
int
PyObject_HasAttrString(PyObject *v, const char *name)
{
PyObject *res = PyObject_GetAttrString(v, name);
if (res != NULL) {
Py_DECREF(res);
return 1;
}
PyErr_Clear();
return 0;
}
int
PyObject_SetAttrString(PyObject *v, const char *name, PyObject *w)
{
PyObject *s;
int res;
if (Py_TYPE(v)->tp_setattr != NULL)
return (*Py_TYPE(v)->tp_setattr)(v, (char*)name, w);
s = PyUnicode_InternFromString(name);
if (s == NULL)
return -1;
res = PyObject_SetAttr(v, s, w);
Py_XDECREF(s);
return res;
}
PyObject *
PyObject_GetAttr(PyObject *v, PyObject *name)
{
PyTypeObject *tp = Py_TYPE(v);
if (!PyUnicode_Check(name)) {
PyErr_Format(PyExc_TypeError,
"attribute name must be string, not '%.200s'",
name->ob_type->tp_name);
return NULL;
}
if (tp->tp_getattro != NULL)
return (*tp->tp_getattro)(v, name);
if (tp->tp_getattr != NULL) {
char *name_str = _PyUnicode_AsString(name);
if (name_str == NULL)
return NULL;
return (*tp->tp_getattr)(v, name_str);
}
PyErr_Format(PyExc_AttributeError,
"'%.50s' object has no attribute '%U'",
tp->tp_name, name);
return NULL;
}
int
PyObject_HasAttr(PyObject *v, PyObject *name)
{
PyObject *res = PyObject_GetAttr(v, name);
if (res != NULL) {
Py_DECREF(res);
return 1;
}
PyErr_Clear();
return 0;
}
int
PyObject_SetAttr(PyObject *v, PyObject *name, PyObject *value)
{
PyTypeObject *tp = Py_TYPE(v);
int err;
if (!PyUnicode_Check(name)) {
PyErr_Format(PyExc_TypeError,
"attribute name must be string, not '%.200s'",
name->ob_type->tp_name);
return -1;
}
Py_INCREF(name);
PyUnicode_InternInPlace(&name);
if (tp->tp_setattro != NULL) {
err = (*tp->tp_setattro)(v, name, value);
Py_DECREF(name);
return err;
}
if (tp->tp_setattr != NULL) {
char *name_str = _PyUnicode_AsString(name);
if (name_str == NULL)
return -1;
err = (*tp->tp_setattr)(v, name_str, value);
Py_DECREF(name);
return err;
}
Py_DECREF(name);
assert(name->ob_refcnt >= 1);
if (tp->tp_getattr == NULL && tp->tp_getattro == NULL)
PyErr_Format(PyExc_TypeError,
"'%.100s' object has no attributes "
"(%s .%U)",
tp->tp_name,
value==NULL ? "del" : "assign to",
name);
else
PyErr_Format(PyExc_TypeError,
"'%.100s' object has only read-only attributes "
"(%s .%U)",
tp->tp_name,
value==NULL ? "del" : "assign to",
name);
return -1;
}
/* Helper to get a pointer to an object's __dict__ slot, if any */
PyObject **
_PyObject_GetDictPtr(PyObject *obj)
{
Py_ssize_t dictoffset;
PyTypeObject *tp = Py_TYPE(obj);
dictoffset = tp->tp_dictoffset;
if (dictoffset == 0)
return NULL;
if (dictoffset < 0) {
Py_ssize_t tsize;
size_t size;
tsize = ((PyVarObject *)obj)->ob_size;
if (tsize < 0)
tsize = -tsize;
size = _PyObject_VAR_SIZE(tp, tsize);
dictoffset += (long)size;
assert(dictoffset > 0);
assert(dictoffset % SIZEOF_VOID_P == 0);
}
return (PyObject **) ((char *)obj + dictoffset);
}
PyObject *
PyObject_SelfIter(PyObject *obj)
{
Py_INCREF(obj);
return obj;
}
/* Helper used when the __next__ method is removed from a type:
tp_iternext is never NULL and can be safely called without checking
on every iteration.
*/
PyObject *
_PyObject_NextNotImplemented(PyObject *self)
{
PyErr_Format(PyExc_TypeError,
"'%.200s' object is not iterable",
Py_TYPE(self)->tp_name);
return NULL;
}
/* Generic GetAttr functions - put these in your tp_[gs]etattro slot */
PyObject *
_PyObject_GenericGetAttrWithDict(PyObject *obj, PyObject *name, PyObject *dict)
{
PyTypeObject *tp = Py_TYPE(obj);
PyObject *descr = NULL;
PyObject *res = NULL;
descrgetfunc f;
Py_ssize_t dictoffset;
PyObject **dictptr;
if (!PyUnicode_Check(name)){
PyErr_Format(PyExc_TypeError,
"attribute name must be string, not '%.200s'",
name->ob_type->tp_name);
return NULL;
}
else
Py_INCREF(name);
if (tp->tp_dict == NULL) {
if (PyType_Ready(tp) < 0)
goto done;
}
descr = _PyType_Lookup(tp, name);
Py_XINCREF(descr);
f = NULL;
if (descr != NULL) {
f = descr->ob_type->tp_descr_get;
if (f != NULL && PyDescr_IsData(descr)) {
res = f(descr, obj, (PyObject *)obj->ob_type);
Py_DECREF(descr);
goto done;
}
}
if (dict == NULL) {
/* Inline _PyObject_GetDictPtr */
dictoffset = tp->tp_dictoffset;
if (dictoffset != 0) {
if (dictoffset < 0) {
Py_ssize_t tsize;
size_t size;