-
Notifications
You must be signed in to change notification settings - Fork 1
/
hash.c
2093 lines (1586 loc) · 49 KB
/
hash.c
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
/*
Copyright (C) 2001-2009, Parrot Foundation.
$Id$
=head1 NAME
src/hash.c - Hash table
=head1 DESCRIPTION
A hashtable contains an array of bucket indexes. Buckets are nodes in a
linked list, each containing a C<void *> key and value. During hash
creation, the types of key and value as well as appropriate compare and
hashing functions can be set.
This hash implementation uses just one piece of malloced memory. The
C<< hash->bs >> bucket store points to this region.
This hash doesn't move during GC, therefore a lot of the old caveats
don't apply.
=head2 Functions
=over 4
=cut
*/
#include "parrot/parrot.h"
#include "pmc/pmc_key.h"
/* the number of entries above which it's faster to hash the hashval instead of
* looping over the used HashBuckets directly */
#define SMALL_HASH_SIZE 4
#define INITIAL_BUCKETS 4
/* HEADERIZER HFILE: include/parrot/hash.h */
/* HEADERIZER BEGIN: static */
/* Don't modify between HEADERIZER BEGIN / HEADERIZER END. Your changes will be lost. */
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
static int cstring_compare(SHIM_INTERP,
ARGIN(const char *a),
ARGIN(const char *b))
__attribute__nonnull__(2)
__attribute__nonnull__(3);
static void expand_hash(PARROT_INTERP, ARGMOD(Hash *hash))
__attribute__nonnull__(1)
__attribute__nonnull__(2)
FUNC_MODIFIES(*hash);
static void hash_freeze(PARROT_INTERP,
ARGIN(const Hash * const hash),
ARGMOD(PMC *info))
__attribute__nonnull__(1)
__attribute__nonnull__(2)
__attribute__nonnull__(3)
FUNC_MODIFIES(*info);
static void hash_thaw(PARROT_INTERP, ARGMOD(Hash *hash), ARGMOD(PMC *info))
__attribute__nonnull__(1)
__attribute__nonnull__(2)
__attribute__nonnull__(3)
FUNC_MODIFIES(*hash)
FUNC_MODIFIES(*info);
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
static size_t key_hash_cstring(SHIM_INTERP,
ARGIN(const void *value),
size_t seed)
__attribute__nonnull__(2);
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
static size_t key_hash_pointer(SHIM_INTERP,
ARGIN(const void *value),
size_t seed)
__attribute__nonnull__(2);
static void parrot_mark_hash_both(PARROT_INTERP, ARGIN(Hash *hash))
__attribute__nonnull__(1)
__attribute__nonnull__(2);
static void parrot_mark_hash_keys(PARROT_INTERP, ARGIN(Hash *hash))
__attribute__nonnull__(1)
__attribute__nonnull__(2);
static void parrot_mark_hash_values(PARROT_INTERP, ARGIN(Hash *hash))
__attribute__nonnull__(1)
__attribute__nonnull__(2);
#define ASSERT_ARGS_cstring_compare __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(a) \
, PARROT_ASSERT_ARG(b))
#define ASSERT_ARGS_expand_hash __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(interp) \
, PARROT_ASSERT_ARG(hash))
#define ASSERT_ARGS_hash_freeze __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(interp) \
, PARROT_ASSERT_ARG(hash) \
, PARROT_ASSERT_ARG(info))
#define ASSERT_ARGS_hash_thaw __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(interp) \
, PARROT_ASSERT_ARG(hash) \
, PARROT_ASSERT_ARG(info))
#define ASSERT_ARGS_key_hash_cstring __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(value))
#define ASSERT_ARGS_key_hash_pointer __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(value))
#define ASSERT_ARGS_parrot_mark_hash_both __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(interp) \
, PARROT_ASSERT_ARG(hash))
#define ASSERT_ARGS_parrot_mark_hash_keys __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(interp) \
, PARROT_ASSERT_ARG(hash))
#define ASSERT_ARGS_parrot_mark_hash_values __attribute__unused__ int _ASSERT_ARGS_CHECK = (\
PARROT_ASSERT_ARG(interp) \
, PARROT_ASSERT_ARG(hash))
/* Don't modify between HEADERIZER BEGIN / HEADERIZER END. Your changes will be lost. */
/* HEADERIZER END: static */
/*
=item C<size_t key_hash_STRING(PARROT_INTERP, STRING *s, size_t seed)>
Returns the hashed value of the key C<value>. See also string.c.
=cut
*/
PARROT_WARN_UNUSED_RESULT
size_t
key_hash_STRING(PARROT_INTERP, ARGMOD(STRING *s), SHIM(size_t seed))
{
ASSERT_ARGS(key_hash_STRING)
if (s->hashval)
return s->hashval;
return Parrot_str_to_hashval(interp, s);
}
/*
=item C<int STRING_compare(PARROT_INTERP, const void *search_key, const void
*bucket_key)>
Compares the two strings, returning 0 if they are identical.
=cut
*/
PARROT_WARN_UNUSED_RESULT
int
STRING_compare(PARROT_INTERP, ARGIN(const void *search_key), ARGIN_NULLOK(const void *bucket_key))
{
ASSERT_ARGS(STRING_compare)
STRING const *s1 = (STRING const *)search_key;
STRING const *s2 = (STRING const *)bucket_key;
if (!s2)
return 1;
if (s1->hashval != s2->hashval)
return 1;
/* COWed strings */
if (Buffer_bufstart(s1) == Buffer_bufstart(s2) && s1->bufused == s2->bufused)
return 0;
return CHARSET_COMPARE(interp, s1, s2);
}
/*
=item C<int pointer_compare(PARROT_INTERP, const void *a, const void *b)>
Compares the two pointers, returning 0 if they are identical
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
int
pointer_compare(SHIM_INTERP, ARGIN_NULLOK(const void *a), ARGIN_NULLOK(const void *b))
{
ASSERT_ARGS(pointer_compare)
return a != b;
}
/*
=item C<static size_t key_hash_pointer(PARROT_INTERP, const void *value, size_t
seed)>
Returns a hashvalue for a pointer.
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
static size_t
key_hash_pointer(SHIM_INTERP, ARGIN(const void *value), size_t seed)
{
ASSERT_ARGS(key_hash_pointer)
return ((size_t) value) ^ seed;
}
/*
=item C<static size_t key_hash_cstring(PARROT_INTERP, const void *value, size_t
seed)>
Creates and returns a hash value from a string.
Takes an interpreter, a pointer to a string, and a seed value.
Returns the hash value.
Used by parrot_new_cstring_hash.
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
static size_t
key_hash_cstring(SHIM_INTERP, ARGIN(const void *value), size_t seed)
{
ASSERT_ARGS(key_hash_cstring)
const unsigned char * p = (const unsigned char *) value;
register size_t h = seed;
while (*p) {
h += h << 5;
h += *p++;
}
return h;
}
/*
=item C<static int cstring_compare(PARROT_INTERP, const char *a, const char *b)>
Compares two C strings for equality, returning -1, 0, and 1 if the first string
is less than, equal to, or greater than the second, respectively.
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
static int
cstring_compare(SHIM_INTERP, ARGIN(const char *a), ARGIN(const char *b))
{
ASSERT_ARGS(cstring_compare)
return strcmp(a, b);
}
/*
=item C<size_t key_hash_PMC(PARROT_INTERP, PMC *value, size_t seed)>
Returns a hashed value for an PMC key (passed as a void pointer, sadly).
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
size_t
key_hash_PMC(PARROT_INTERP, ARGIN(PMC *value), SHIM(size_t seed))
{
ASSERT_ARGS(key_hash_PMC)
return VTABLE_hashvalue(interp, value);
}
/*
=item C<int PMC_compare(PARROT_INTERP, PMC *a, PMC *b)>
Compares two PMC for equality, returning 0 if the first is equal to second.
Uses void pointers to store the PMC, sadly.
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
int
PMC_compare(PARROT_INTERP, ARGIN(PMC *a), ARGIN_NULLOK(PMC *b))
{
ASSERT_ARGS(PMC_compare)
/* If pointers are same - PMCs are same */
if (a == b)
return 0;
/* PMCs of different types are differ */
if (a->vtable->base_type != b->vtable->base_type)
return 1;
return !VTABLE_is_equal(interp, a, b);
}
/*
=item C<size_t key_hash_int(PARROT_INTERP, const void *value, size_t seed)>
Returns a hashed value for an integer key (passed as a void pointer, sadly).
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
size_t
key_hash_int(SHIM_INTERP, ARGIN_NULLOK(const void *value), size_t seed)
{
ASSERT_ARGS(key_hash_int)
return (size_t)value ^ seed;
}
/*
=item C<int int_compare(PARROT_INTERP, const void *a, const void *b)>
Compares two integers for equality, returning -1, 0, and 1 if the first is less
than, equal to, or greater than the second, respectively. Uses void pointers
to store the integers, sadly.
=cut
*/
PARROT_WARN_UNUSED_RESULT
PARROT_PURE_FUNCTION
int
int_compare(SHIM_INTERP, ARGIN_NULLOK(const void *a), ARGIN_NULLOK(const void *b))
{
ASSERT_ARGS(int_compare)
return a != b;
}
/*
=item C<void parrot_dump_hash(PARROT_INTERP, const Hash *hash)>
Prints out the hash in human-readable form, at least once someone implements
this.
=cut
*/
PARROT_EXPORT
void
parrot_dump_hash(SHIM_INTERP, SHIM(const Hash *hash))
{
ASSERT_ARGS(parrot_dump_hash)
}
/*
=item C<void parrot_mark_hash(PARROT_INTERP, Hash *hash)>
Marks the hash and its contents as live. Assumes that key and value are non
null in all buckets.
=cut
*/
PARROT_EXPORT
void
parrot_mark_hash(PARROT_INTERP, ARGIN(Hash *hash))
{
ASSERT_ARGS(parrot_mark_hash)
int mark_key = 0;
int mark_value = 0;
if (hash->entry_type == (PARROT_DATA_TYPE) enum_hash_string
|| hash->entry_type == (PARROT_DATA_TYPE) enum_hash_pmc)
mark_value = 1;
if (hash->key_type == Hash_key_type_STRING
|| hash->key_type == Hash_key_type_PMC)
mark_key = 1;
if (mark_key) {
if (mark_value)
parrot_mark_hash_both(interp, hash);
else
parrot_mark_hash_keys(interp, hash);
}
else {
if (mark_value)
parrot_mark_hash_values(interp, hash);
}
}
/*
=item C<static void parrot_mark_hash_keys(PARROT_INTERP, Hash *hash)>
Marks the hash and only its keys as live.
=cut
*/
static void
parrot_mark_hash_keys(PARROT_INTERP, ARGIN(Hash *hash))
{
ASSERT_ARGS(parrot_mark_hash_keys)
UINTVAL entries = hash->entries;
UINTVAL found = 0;
INTVAL i;
for (i = hash->mask; i >= 0; --i) {
HashBucket *bucket = hash->bi[i];
while (bucket) {
if (++found > entries)
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"Detected hash corruption at hash %p entries %d",
hash, (int)entries);
PARROT_ASSERT(bucket->key);
Parrot_gc_mark_PObj_alive(interp, (PObj *)bucket->key);
bucket = bucket->next;
}
}
}
/*
=item C<static void parrot_mark_hash_values(PARROT_INTERP, Hash *hash)>
Marks the hash and only its values as live.
=cut
*/
static void
parrot_mark_hash_values(PARROT_INTERP, ARGIN(Hash *hash))
{
ASSERT_ARGS(parrot_mark_hash_values)
const UINTVAL entries = hash->entries;
UINTVAL found = 0;
INTVAL i;
for (i = hash->mask; i >= 0; --i) {
HashBucket *bucket = hash->bi[i];
while (bucket) {
if (++found > entries)
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"Detected hash corruption at hash %p entries %d",
hash, (int)entries);
PARROT_ASSERT(bucket->value);
Parrot_gc_mark_PObj_alive(interp, (PObj *)bucket->value);
bucket = bucket->next;
}
}
}
/*
=item C<static void parrot_mark_hash_both(PARROT_INTERP, Hash *hash)>
Marks the hash and both its keys and values as live.
=cut
*/
static void
parrot_mark_hash_both(PARROT_INTERP, ARGIN(Hash *hash))
{
ASSERT_ARGS(parrot_mark_hash_both)
const UINTVAL entries = hash->entries;
UINTVAL found = 0;
INTVAL i;
for (i = hash->mask; i >= 0; --i) {
HashBucket *bucket = hash->bi[i];
while (bucket) {
if (++found > entries)
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"Detected hash corruption at hash %p entries %d",
hash, (int)entries);
PARROT_ASSERT(bucket->key);
Parrot_gc_mark_PObj_alive(interp, (PObj *)bucket->key);
PARROT_ASSERT(bucket->value);
Parrot_gc_mark_PObj_alive(interp, (PObj *)bucket->value);
bucket = bucket->next;
}
}
}
/*
=item C<static void hash_thaw(PARROT_INTERP, Hash *hash, PMC *info)>
Visits the contents of a hash during freeze/thaw.
C<pinfo> is the visit info, (see include/parrot/pmc_freeze.h>).
=cut
*/
static void
hash_thaw(PARROT_INTERP, ARGMOD(Hash *hash), ARGMOD(PMC *info))
{
ASSERT_ARGS(hash_thaw)
/* during thaw, info->extra is the key/value count */
const size_t num_entries = (size_t) hash->entries;
size_t entry_index;
hash->entries = 0;
for (entry_index = 0; entry_index < num_entries; ++entry_index) {
HashBucket *b;
switch (hash->key_type) {
case Hash_key_type_STRING:
{
STRING * const s_key = VTABLE_shift_string(interp, info);
b = parrot_hash_put(interp, hash, s_key, NULL);
}
break;
case Hash_key_type_int:
{
const INTVAL i_key = VTABLE_shift_integer(interp, info);
b = parrot_hash_put(interp, hash, (void*)i_key, NULL);
}
break;
default:
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"unimplemented key type");
break;
}
switch (hash->entry_type) {
case enum_hash_pmc:
{
PMC *p = VTABLE_shift_pmc(interp, info);
b->value = (void *)p;
break;
}
case enum_hash_int:
{
const INTVAL i = VTABLE_shift_integer(interp, info);
b->value = (void *)i;
break;
}
default:
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"unimplemented value type");
break;
}
}
}
/*
=item C<static void hash_freeze(PARROT_INTERP, const Hash * const hash, PMC
*info)>
Freezes hash into a string.
Takes an interpreter, a pointer to the hash, and a pointer to the structure
containing the string start location.
Use by parrot_hash_visit.
=cut
*/
static void
hash_freeze(PARROT_INTERP, ARGIN(const Hash * const hash), ARGMOD(PMC *info))
{
ASSERT_ARGS(hash_freeze)
size_t i;
for (i = 0; i < hash->entries; i++) {
HashBucket * const b = hash->bs+i;
switch (hash->key_type) {
case Hash_key_type_STRING:
VTABLE_push_string(interp, info, (STRING *)b->key);
break;
case Hash_key_type_int:
VTABLE_push_integer(interp, info, (INTVAL)b->key);
break;
default:
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"unimplemented key type");
break;
}
switch (hash->entry_type) {
case enum_hash_pmc:
VTABLE_push_pmc(interp, info, (PMC *)b->value);
break;
case enum_hash_int:
VTABLE_push_integer(interp, info, (INTVAL)b->value);
break;
default:
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"unimplemented value type");
break;
}
}
}
/*
=item C<void parrot_hash_visit(PARROT_INTERP, Hash *hash, void *pinfo)>
Freezes or thaws a hash as specified. Takes an interpreter, a pointer to the
hash, and a pointer to the structure identifying what to do and the location of
the string.
=cut
*/
PARROT_EXPORT
void
parrot_hash_visit(PARROT_INTERP, ARGMOD(Hash *hash), ARGMOD(void *pinfo))
{
ASSERT_ARGS(parrot_hash_visit)
PMC* const info = (PMC*) pinfo;
switch (VTABLE_get_integer(interp, info)) {
case VISIT_THAW_NORMAL:
hash_thaw(interp, hash, info);
break;
case VISIT_FREEZE_NORMAL:
hash_freeze(interp, hash, info);
break;
default:
Parrot_ex_throw_from_c_args(interp, NULL, 1,
"unimplemented visit mode");
}
}
/*
=item C<static void expand_hash(PARROT_INTERP, Hash *hash)>
Expands a hash when necessary.
For a hashtable of size N, we use C<MAXFULL_PERCENT> % of N as the
number of buckets. This way, as soon as we run out of buckets on the
free list, we know that it's time to resize the hashtable.
Algorithm for expansion: We exactly double the size of the hashtable.
Keys are assigned to buckets with the formula
bucket_index = hash(key) % parrot_hash_size
When doubling the size of the hashtable, we know that every key is either
already in the correct bucket, or belongs in the current bucket plus
C<parrot_hash_size> (the old C<parrot_hash_size>). In fact, because the
hashtable is always a power of two in size, it depends only on the next bit
in the hash value, after the ones previously used.
We scan through all the buckets in order, moving the buckets that need to be
moved. No bucket will be scanned twice, and the cache should be reasonably
happy because the hashtable accesses will be two parallel sequential scans.
(Of course, this also mucks with the C<< ->next >> pointers, and they'll be
all over memory.)
=cut
*/
static void
expand_hash(PARROT_INTERP, ARGMOD(Hash *hash))
{
ASSERT_ARGS(expand_hash)
HashBucket **old_bi, **new_bi;
HashBucket *bs, *b, *new_mem;
HashBucket *old_offset = (HashBucket *)((char *)hash + sizeof (Hash));
void * const old_mem = hash->bs;
const UINTVAL old_size = hash->mask + 1;
const UINTVAL new_size = old_size << 1;
const UINTVAL old_nb = N_BUCKETS(old_size);
size_t offset, i, new_loc;
/*
allocate some less buckets
e.g. 3 buckets, 4 pointers:
+---+---+---+-+-+-+-+
| --> bs | -> bi |
+---+---+---+-+-+-+-+
^ ^
| old_mem | hash->bi
*/
/* resize mem */
if (old_offset != old_mem) {
/* This buffer has been reallocated at least once before. */
new_mem = (HashBucket *)Parrot_gc_reallocate_memory_chunk_with_interior_pointers(
interp, old_mem, HASH_ALLOC_SIZE(new_size), HASH_ALLOC_SIZE(old_size));
}
else {
/* Allocate a new buffer. */
new_mem = (HashBucket *)Parrot_gc_allocate_memory_chunk_with_interior_pointers(
interp, HASH_ALLOC_SIZE(new_size));
memcpy(new_mem, old_mem, HASH_ALLOC_SIZE(old_size));
}
/*
+---+---+---+---+---+---+-+-+-+-+-+-+-+-+
| bs | old_bi | new_bi |
+---+---+---+---+---+---+-+-+-+-+-+-+-+-+
^ ^
| new_mem | hash->bi
*/
bs = new_mem;
old_bi = (HashBucket **)(bs + old_nb);
new_bi = (HashBucket **)(bs + N_BUCKETS(new_size));
/* things can have moved by this offset */
offset = (char *)new_mem - (char *)old_mem;
/* relocate the bucket index */
mem_sys_memmove(new_bi, old_bi, old_size * sizeof (HashBucket *));
/* update hash data */
hash->bi = new_bi;
hash->bs = bs;
hash->mask = new_size - 1;
/* clear freshly allocated bucket index */
memset(new_bi + old_size, 0, sizeof (HashBucket *) * old_size);
/*
* reloc pointers - this part would be also needed, if we
* allocate hash memory from GC movable memory, and then
* also the free_list needs updating (this is empty now,
* as expand_hash is only called for that case).
*/
if (offset) {
for (i = 0; i < old_size; ++i) {
HashBucket **next_p = new_bi + i;
while (*next_p) {
*next_p = (HashBucket *)((char *)*next_p + offset);
b = *next_p;
next_p = &b->next;
}
}
}
/* recalc bucket index */
for (i = 0; i < old_size; ++i) {
HashBucket **next_p = new_bi + i;
while (*next_p) {
b = *next_p;
/* rehash the bucket */
new_loc = (hash->hash_val)(interp, b->key, hash->seed) &
(new_size - 1);
if (i != new_loc) {
*next_p = b->next;
b->next = new_bi[new_loc];
new_bi[new_loc] = b;
}
else
next_p = &b->next;
}
}
/* add new buckets to free_list in reverse order
* lowest bucket is top on free list and will be used first */
for (i = 0, b = (HashBucket *)new_bi - 1; i < old_nb; ++i, --b) {
b->next = hash->free_list;
b->key = b->value = NULL;
hash->free_list = b;
}
}
/*
=item C<Hash* parrot_new_hash(PARROT_INTERP)>
Creates a new Parrot STRING hash.
=cut
*/
PARROT_EXPORT
PARROT_CANNOT_RETURN_NULL
Hash*
parrot_new_hash(PARROT_INTERP)
{
ASSERT_ARGS(parrot_new_hash)
return parrot_create_hash(interp,
enum_type_PMC,
Hash_key_type_STRING,
STRING_compare,
(hash_hash_key_fn)key_hash_STRING);
}
/*
=item C<Hash* parrot_new_cstring_hash(PARROT_INTERP)>
Creates a new C string hash in C<hptr>.
=cut
*/
PARROT_EXPORT
PARROT_CANNOT_RETURN_NULL
Hash*
parrot_new_cstring_hash(PARROT_INTERP)
{
ASSERT_ARGS(parrot_new_cstring_hash)
return parrot_create_hash(interp,
enum_type_PMC,
Hash_key_type_cstring,
(hash_comp_fn)cstring_compare,
(hash_hash_key_fn)key_hash_cstring);
}
/*
=item C<Hash * parrot_new_pointer_hash(PARROT_INTERP)>
Create and return a new hash with void * keys and values.
=cut
*/
PARROT_EXPORT
PARROT_CANNOT_RETURN_NULL
Hash *
parrot_new_pointer_hash(PARROT_INTERP)
{
ASSERT_ARGS(parrot_new_pointer_hash)
return parrot_create_hash(interp,
enum_type_ptr,
Hash_key_type_ptr,
pointer_compare,
key_hash_pointer);
}
/*
=item C<Hash* parrot_new_intval_hash(PARROT_INTERP)>
Creates and returns new Hash PMC with INTVAL keys and values. C<flags> can be
C<PObj_constant_FLAG> or 0.
=cut
*/
PARROT_EXPORT
PARROT_WARN_UNUSED_RESULT
PARROT_CANNOT_RETURN_NULL
Hash*
parrot_new_intval_hash(PARROT_INTERP)
{
ASSERT_ARGS(parrot_new_intval_hash)
return parrot_create_hash(interp,
enum_type_INTVAL,
Hash_key_type_int,
int_compare,
key_hash_int);
}
/*
=item C<Hash * parrot_create_hash(PARROT_INTERP, PARROT_DATA_TYPE val_type,
Hash_key_type hkey_type, hash_comp_fn compare, hash_hash_key_fn keyhash)>
Creates and initializes a hash. Function pointers determine its behaviors.
The container passed in is the address of the hash PMC that is using it. The
hash and the PMC point to each other.
Memory from this function must be freed.
=cut
*/
PARROT_CANNOT_RETURN_NULL
PARROT_WARN_UNUSED_RESULT
PARROT_MALLOC
Hash *
parrot_create_hash(PARROT_INTERP, PARROT_DATA_TYPE val_type, Hash_key_type hkey_type,
ARGIN(hash_comp_fn compare), ARGIN(hash_hash_key_fn keyhash))
{
ASSERT_ARGS(parrot_create_hash)
HashBucket *bp;
void *alloc = Parrot_gc_allocate_memory_chunk_with_interior_pointers(
interp, sizeof (Hash) + HASH_ALLOC_SIZE(INITIAL_BUCKETS));
Hash * const hash = (Hash*)alloc;
size_t i;
PARROT_ASSERT(INITIAL_BUCKETS % 4 == 0);
hash->compare = compare;
hash->hash_val = keyhash;
hash->entry_type = val_type;
hash->key_type = hkey_type;
hash->seed = interp->hash_seed;
hash->mask = INITIAL_BUCKETS - 1;
hash->entries = 0;
hash->container = PMCNULL;
/*
* TODO if we have a significant amount of small hashes:
* - allocate a bigger hash structure e.g. 128 byte
* - use the bucket store and bi inside this structure
* - when reallocate copy this part
*/
bp = (HashBucket *)((char *)alloc + sizeof (Hash));
hash->free_list = NULL;
/* fill free_list from hi addresses so that we can use
* buckets[i] directly in an OrderedHash, *if* nothing
* was deleted */
hash->bs = bp;
bp += N_BUCKETS(INITIAL_BUCKETS);
hash->bi = (HashBucket **)bp;
for (i = 0, --bp; i < N_BUCKETS(INITIAL_BUCKETS); ++i, --bp) {
bp->next = hash->free_list;
bp->key = NULL;
bp->value = NULL;
hash->free_list = bp;
}
for (i = 0; i < INITIAL_BUCKETS; ++i)
hash->bi[i] = NULL;
return hash;
}