forked from ruby/ruby
-
Notifications
You must be signed in to change notification settings - Fork 12
Expand file tree
/
Copy pathenum.c
More file actions
3114 lines (2747 loc) · 78.6 KB
/
Copy pathenum.c
File metadata and controls
3114 lines (2747 loc) · 78.6 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
/**********************************************************************
enum.c -
$Author$
created at: Fri Oct 1 15:15:19 JST 1993
Copyright (C) 1993-2007 Yukihiro Matsumoto
**********************************************************************/
#include "ruby/ruby.h"
#include "ruby/util.h"
#include "node.h"
#include "id.h"
#include "internal.h"
VALUE rb_f_send(int argc, VALUE *argv, VALUE recv);
VALUE rb_mEnumerable;
static ID id_next;
static ID id_div;
static ID id_call;
static ID id_size;
#define id_each idEach
#define id_eqq idEqq
#define id_cmp idCmp
#define id_lshift idLTLT
VALUE
rb_enum_values_pack(int argc, const VALUE *argv)
{
if (argc == 0) return Qnil;
if (argc == 1) return argv[0];
return rb_ary_new4(argc, argv);
}
#define ENUM_WANT_SVALUE() do { \
i = rb_enum_values_pack(argc, argv); \
} while (0)
#define enum_yield rb_yield_values2
static VALUE
grep_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, args))
{
NODE *memo = RNODE(args);
ENUM_WANT_SVALUE();
if (RTEST(rb_funcall(memo->u1.value, id_eqq, 1, i))) {
rb_ary_push(memo->u2.value, i);
}
return Qnil;
}
static VALUE
grep_iter_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, args))
{
NODE *memo = RNODE(args);
ENUM_WANT_SVALUE();
if (RTEST(rb_funcall(memo->u1.value, id_eqq, 1, i))) {
rb_ary_push(memo->u2.value, rb_yield(i));
}
return Qnil;
}
/*
* call-seq:
* enum.grep(pattern) -> array
* enum.grep(pattern) { |obj| block } -> array
*
* Returns an array of every element in <i>enum</i> for which
* <code>Pattern === element</code>. If the optional <em>block</em> is
* supplied, each matching element is passed to it, and the block's
* result is stored in the output array.
*
* (1..100).grep 38..44 #=> [38, 39, 40, 41, 42, 43, 44]
* c = IO.constants
* c.grep(/SEEK/) #=> [:SEEK_SET, :SEEK_CUR, :SEEK_END]
* res = c.grep(/SEEK/) { |v| IO.const_get(v) }
* res #=> [0, 1, 2]
*
*/
static VALUE
enum_grep(VALUE obj, VALUE pat)
{
VALUE ary = rb_ary_new();
NODE *memo = NEW_MEMO(pat, ary, 0);
rb_block_call(obj, id_each, 0, 0, rb_block_given_p() ? grep_iter_i : grep_i, (VALUE)memo);
return ary;
}
static VALUE
count_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, memop))
{
NODE *memo = RNODE(memop);
ENUM_WANT_SVALUE();
if (rb_equal(i, memo->u1.value)) {
memo->u3.cnt++;
}
return Qnil;
}
static VALUE
count_iter_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, memop))
{
NODE *memo = RNODE(memop);
if (RTEST(enum_yield(argc, argv))) {
memo->u3.cnt++;
}
return Qnil;
}
static VALUE
count_all_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, memop))
{
NODE *memo = RNODE(memop);
memo->u3.cnt++;
return Qnil;
}
/*
* call-seq:
* enum.count -> int
* enum.count(item) -> int
* enum.count { |obj| block } -> int
*
* Returns the number of items in +enum+ through enumeration.
* If an argument is given, the number of items in +enum+ that
* are equal to +item+ are counted. If a block is given, it
* counts the number of elements yielding a true value.
*
* ary = [1, 2, 4, 2]
* ary.count #=> 4
* ary.count(2) #=> 2
* ary.count{ |x| x%2==0 } #=> 3
*
*/
static VALUE
enum_count(int argc, VALUE *argv, VALUE obj)
{
VALUE item = Qnil;
NODE *memo;
rb_block_call_func *func;
if (argc == 0) {
if (rb_block_given_p()) {
func = count_iter_i;
}
else {
func = count_all_i;
}
}
else {
rb_scan_args(argc, argv, "1", &item);
if (rb_block_given_p()) {
rb_warn("given block not used");
}
func = count_i;
}
memo = NEW_MEMO(item, 0, 0);
rb_block_call(obj, id_each, 0, 0, func, (VALUE)memo);
return INT2NUM(memo->u3.cnt);
}
static VALUE
find_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, memop))
{
ENUM_WANT_SVALUE();
if (RTEST(rb_yield(i))) {
NODE *memo = RNODE(memop);
memo->u1.value = i;
memo->u3.cnt = 1;
rb_iter_break();
}
return Qnil;
}
/*
* call-seq:
* enum.detect(ifnone = nil) { |obj| block } -> obj or nil
* enum.find(ifnone = nil) { |obj| block } -> obj or nil
* enum.detect(ifnone = nil) -> an_enumerator
* enum.find(ifnone = nil) -> an_enumerator
*
* Passes each entry in <i>enum</i> to <em>block</em>. Returns the
* first for which <em>block</em> is not false. If no
* object matches, calls <i>ifnone</i> and returns its result when it
* is specified, or returns <code>nil</code> otherwise.
*
* If no block is given, an enumerator is returned instead.
*
* (1..10).detect { |i| i % 5 == 0 and i % 7 == 0 } #=> nil
* (1..100).detect { |i| i % 5 == 0 and i % 7 == 0 } #=> 35
*
*/
static VALUE
enum_find(int argc, VALUE *argv, VALUE obj)
{
NODE *memo;
VALUE if_none;
rb_scan_args(argc, argv, "01", &if_none);
RETURN_ENUMERATOR(obj, argc, argv);
memo = NEW_MEMO(Qundef, 0, 0);
rb_block_call(obj, id_each, 0, 0, find_i, (VALUE)memo);
if (memo->u3.cnt) {
return memo->u1.value;
}
if (!NIL_P(if_none)) {
return rb_funcall(if_none, id_call, 0, 0);
}
return Qnil;
}
static VALUE
find_index_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, memop))
{
NODE *memo = RNODE(memop);
ENUM_WANT_SVALUE();
if (rb_equal(i, memo->u2.value)) {
memo->u1.value = UINT2NUM(memo->u3.cnt);
rb_iter_break();
}
memo->u3.cnt++;
return Qnil;
}
static VALUE
find_index_iter_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, memop))
{
NODE *memo = RNODE(memop);
if (RTEST(enum_yield(argc, argv))) {
memo->u1.value = UINT2NUM(memo->u3.cnt);
rb_iter_break();
}
memo->u3.cnt++;
return Qnil;
}
/*
* call-seq:
* enum.find_index(value) -> int or nil
* enum.find_index { |obj| block } -> int or nil
* enum.find_index -> an_enumerator
*
* Compares each entry in <i>enum</i> with <em>value</em> or passes
* to <em>block</em>. Returns the index for the first for which the
* evaluated value is non-false. If no object matches, returns
* <code>nil</code>
*
* If neither block nor argument is given, an enumerator is returned instead.
*
* (1..10).find_index { |i| i % 5 == 0 and i % 7 == 0 } #=> nil
* (1..100).find_index { |i| i % 5 == 0 and i % 7 == 0 } #=> 34
* (1..100).find_index(50) #=> 49
*
*/
static VALUE
enum_find_index(int argc, VALUE *argv, VALUE obj)
{
NODE *memo; /* [return value, current index, ] */
VALUE condition_value = Qnil;
rb_block_call_func *func;
if (argc == 0) {
RETURN_ENUMERATOR(obj, 0, 0);
func = find_index_iter_i;
}
else {
rb_scan_args(argc, argv, "1", &condition_value);
if (rb_block_given_p()) {
rb_warn("given block not used");
}
func = find_index_i;
}
memo = NEW_MEMO(Qnil, condition_value, 0);
rb_block_call(obj, id_each, 0, 0, func, (VALUE)memo);
return memo->u1.value;
}
static VALUE
find_all_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, ary))
{
ENUM_WANT_SVALUE();
if (RTEST(rb_yield(i))) {
rb_ary_push(ary, i);
}
return Qnil;
}
static VALUE
enum_size(VALUE self, VALUE args, VALUE eobj)
{
VALUE r;
r = rb_check_funcall(self, id_size, 0, 0);
return (r == Qundef) ? Qnil : r;
}
/*
* call-seq:
* enum.find_all { |obj| block } -> array
* enum.select { |obj| block } -> array
* enum.find_all -> an_enumerator
* enum.select -> an_enumerator
*
* Returns an array containing all elements of +enum+
* for which the given +block+ returns a true value.
*
* If no block is given, an Enumerator is returned instead.
*
*
* (1..10).find_all { |i| i % 3 == 0 } #=> [3, 6, 9]
*
* [1,2,3,4,5].select { |num| num.even? } #=> [2, 4]
*
* See also Enumerable#reject.
*/
static VALUE
enum_find_all(VALUE obj)
{
VALUE ary;
RETURN_SIZED_ENUMERATOR(obj, 0, 0, enum_size);
ary = rb_ary_new();
rb_block_call(obj, id_each, 0, 0, find_all_i, ary);
return ary;
}
static VALUE
reject_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, ary))
{
ENUM_WANT_SVALUE();
if (!RTEST(rb_yield(i))) {
rb_ary_push(ary, i);
}
return Qnil;
}
/*
* call-seq:
* enum.reject { |obj| block } -> array
* enum.reject -> an_enumerator
*
* Returns an array for all elements of +enum+ for which the given
* +block+ returns false.
*
* If no block is given, an Enumerator is returned instead.
*
* (1..10).reject { |i| i % 3 == 0 } #=> [1, 2, 4, 5, 7, 8, 10]
*
* [1, 2, 3, 4, 5].reject { |num| num.even? } #=> [1, 3, 5]
*
* See also Enumerable#find_all.
*/
static VALUE
enum_reject(VALUE obj)
{
VALUE ary;
RETURN_SIZED_ENUMERATOR(obj, 0, 0, enum_size);
ary = rb_ary_new();
rb_block_call(obj, id_each, 0, 0, reject_i, ary);
return ary;
}
static VALUE
collect_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, ary))
{
rb_ary_push(ary, enum_yield(argc, argv));
return Qnil;
}
static VALUE
collect_all(RB_BLOCK_CALL_FUNC_ARGLIST(i, ary))
{
rb_thread_check_ints();
rb_ary_push(ary, rb_enum_values_pack(argc, argv));
return Qnil;
}
/*
* call-seq:
* enum.collect { |obj| block } -> array
* enum.map { |obj| block } -> array
* enum.collect -> an_enumerator
* enum.map -> an_enumerator
*
* Returns a new array with the results of running <em>block</em> once
* for every element in <i>enum</i>.
*
* If no block is given, an enumerator is returned instead.
*
* (1..4).map { |i| i*i } #=> [1, 4, 9, 16]
* (1..4).collect { "cat" } #=> ["cat", "cat", "cat", "cat"]
*
*/
static VALUE
enum_collect(VALUE obj)
{
VALUE ary;
RETURN_SIZED_ENUMERATOR(obj, 0, 0, enum_size);
ary = rb_ary_new();
rb_block_call(obj, id_each, 0, 0, collect_i, ary);
return ary;
}
static VALUE
flat_map_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, ary))
{
VALUE tmp;
i = enum_yield(argc, argv);
tmp = rb_check_array_type(i);
if (NIL_P(tmp)) {
rb_ary_push(ary, i);
}
else {
rb_ary_concat(ary, tmp);
}
return Qnil;
}
/*
* call-seq:
* enum.flat_map { |obj| block } -> array
* enum.collect_concat { |obj| block } -> array
* enum.flat_map -> an_enumerator
* enum.collect_concat -> an_enumerator
*
* Returns a new array with the concatenated results of running
* <em>block</em> once for every element in <i>enum</i>.
*
* If no block is given, an enumerator is returned instead.
*
* [1, 2, 3, 4].flat_map { |e| [e, -e] } #=> [1, -1, 2, -2, 3, -3, 4, -4]
* [[1, 2], [3, 4]].flat_map { |e| e + [100] } #=> [1, 2, 100, 3, 4, 100]
*
*/
static VALUE
enum_flat_map(VALUE obj)
{
VALUE ary;
RETURN_SIZED_ENUMERATOR(obj, 0, 0, enum_size);
ary = rb_ary_new();
rb_block_call(obj, id_each, 0, 0, flat_map_i, ary);
return ary;
}
/*
* call-seq:
* enum.to_a(*args) -> array
* enum.entries(*args) -> array
*
* Returns an array containing the items in <i>enum</i>.
*
* (1..7).to_a #=> [1, 2, 3, 4, 5, 6, 7]
* { 'a'=>1, 'b'=>2, 'c'=>3 }.to_a #=> [["a", 1], ["b", 2], ["c", 3]]
*
* require 'prime'
* Prime.entries 10 #=> [2, 3, 5, 7]
*/
static VALUE
enum_to_a(int argc, VALUE *argv, VALUE obj)
{
VALUE ary = rb_ary_new();
rb_block_call(obj, id_each, argc, argv, collect_all, ary);
OBJ_INFECT(ary, obj);
return ary;
}
static VALUE
enum_to_h_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, hash))
{
VALUE key_value_pair;
ENUM_WANT_SVALUE();
rb_thread_check_ints();
key_value_pair = rb_check_array_type(i);
if (NIL_P(key_value_pair)) {
rb_raise(rb_eTypeError, "wrong element type %s (expected array)",
rb_builtin_class_name(i));
}
if (RARRAY_LEN(key_value_pair) != 2) {
rb_raise(rb_eArgError, "element has wrong array length (expected 2, was %ld)",
RARRAY_LEN(key_value_pair));
}
rb_hash_aset(hash, RARRAY_AREF(key_value_pair, 0), RARRAY_AREF(key_value_pair, 1));
return Qnil;
}
/*
* call-seq:
* enum.to_h(*args) -> hash
*
* Returns the result of interpreting <i>enum</i> as a list of
* <tt>[key, value]</tt> pairs.
*
* %i[hello world].each_with_index.to_h
* # => {:hello => 0, :world => 1}
*/
static VALUE
enum_to_h(int argc, VALUE *argv, VALUE obj)
{
VALUE hash = rb_hash_new();
rb_block_call(obj, id_each, argc, argv, enum_to_h_i, hash);
OBJ_INFECT(hash, obj);
return hash;
}
static VALUE
inject_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, p))
{
NODE *memo = RNODE(p);
ENUM_WANT_SVALUE();
if (memo->u2.argc == 0) {
memo->u2.argc = 1;
memo->u1.value = i;
}
else {
memo->u1.value = rb_yield_values(2, memo->u1.value, i);
}
return Qnil;
}
static VALUE
inject_op_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, p))
{
NODE *memo = RNODE(p);
VALUE name;
ENUM_WANT_SVALUE();
if (memo->u2.argc == 0) {
memo->u2.argc = 1;
memo->u1.value = i;
}
else if (SYMBOL_P(name = memo->u3.value)) {
memo->u1.value = rb_funcall(memo->u1.value, SYM2ID(name), 1, i);
}
else {
VALUE args[2];
args[0] = name;
args[1] = i;
memo->u1.value = rb_f_send(numberof(args), args, memo->u1.value);
}
return Qnil;
}
/*
* call-seq:
* enum.inject(initial, sym) -> obj
* enum.inject(sym) -> obj
* enum.inject(initial) { |memo, obj| block } -> obj
* enum.inject { |memo, obj| block } -> obj
* enum.reduce(initial, sym) -> obj
* enum.reduce(sym) -> obj
* enum.reduce(initial) { |memo, obj| block } -> obj
* enum.reduce { |memo, obj| block } -> obj
*
* Combines all elements of <i>enum</i> by applying a binary
* operation, specified by a block or a symbol that names a
* method or operator.
*
* If you specify a block, then for each element in <i>enum</i>
* the block is passed an accumulator value (<i>memo</i>) and the element.
* If you specify a symbol instead, then each element in the collection
* will be passed to the named method of <i>memo</i>.
* In either case, the result becomes the new value for <i>memo</i>.
* At the end of the iteration, the final value of <i>memo</i> is the
* return value for the method.
*
* If you do not explicitly specify an <i>initial</i> value for <i>memo</i>,
* then the first element of collection is used as the initial value
* of <i>memo</i>.
*
*
* # Sum some numbers
* (5..10).reduce(:+) #=> 45
* # Same using a block and inject
* (5..10).inject { |sum, n| sum + n } #=> 45
* # Multiply some numbers
* (5..10).reduce(1, :*) #=> 151200
* # Same using a block
* (5..10).inject(1) { |product, n| product * n } #=> 151200
* # find the longest word
* longest = %w{ cat sheep bear }.inject do |memo, word|
* memo.length > word.length ? memo : word
* end
* longest #=> "sheep"
*
*/
static VALUE
enum_inject(int argc, VALUE *argv, VALUE obj)
{
NODE *memo;
VALUE init, op;
rb_block_call_func *iter = inject_i;
ID id;
switch (rb_scan_args(argc, argv, "02", &init, &op)) {
case 0:
break;
case 1:
if (rb_block_given_p()) {
break;
}
id = rb_check_id(&init);
op = id ? ID2SYM(id) : init;
argc = 0;
init = Qnil;
iter = inject_op_i;
break;
case 2:
if (rb_block_given_p()) {
rb_warning("given block not used");
}
id = rb_check_id(&op);
if (id) op = ID2SYM(id);
iter = inject_op_i;
break;
}
memo = NEW_MEMO(init, argc, op);
rb_block_call(obj, id_each, 0, 0, iter, (VALUE)memo);
return memo->u1.value;
}
static VALUE
partition_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, arys))
{
NODE *memo = RNODE(arys);
VALUE ary;
ENUM_WANT_SVALUE();
if (RTEST(rb_yield(i))) {
ary = memo->u1.value;
}
else {
ary = memo->u2.value;
}
rb_ary_push(ary, i);
return Qnil;
}
/*
* call-seq:
* enum.partition { |obj| block } -> [ true_array, false_array ]
* enum.partition -> an_enumerator
*
* Returns two arrays, the first containing the elements of
* <i>enum</i> for which the block evaluates to true, the second
* containing the rest.
*
* If no block is given, an enumerator is returned instead.
*
* (1..6).partition { |v| v.even? } #=> [[2, 4, 6], [1, 3, 5]]
*
*/
static VALUE
enum_partition(VALUE obj)
{
NODE *memo;
RETURN_SIZED_ENUMERATOR(obj, 0, 0, enum_size);
memo = NEW_MEMO(rb_ary_new(), rb_ary_new(), 0);
rb_block_call(obj, id_each, 0, 0, partition_i, (VALUE)memo);
return rb_assoc_new(memo->u1.value, memo->u2.value);
}
static VALUE
group_by_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, hash))
{
VALUE group;
VALUE values;
ENUM_WANT_SVALUE();
group = rb_yield(i);
values = rb_hash_aref(hash, group);
if (!RB_TYPE_P(values, T_ARRAY)) {
values = rb_ary_new3(1, i);
rb_hash_aset(hash, group, values);
}
else {
rb_ary_push(values, i);
}
return Qnil;
}
/*
* call-seq:
* enum.group_by { |obj| block } -> a_hash
* enum.group_by -> an_enumerator
*
* Groups the collection by result of the block. Returns a hash where the
* keys are the evaluated result from the block and the values are
* arrays of elements in the collection that correspond to the key.
*
* If no block is given an enumerator is returned.
*
* (1..6).group_by { |i| i%3 } #=> {0=>[3, 6], 1=>[1, 4], 2=>[2, 5]}
*
*/
static VALUE
enum_group_by(VALUE obj)
{
VALUE hash;
RETURN_SIZED_ENUMERATOR(obj, 0, 0, enum_size);
hash = rb_hash_new();
rb_block_call(obj, id_each, 0, 0, group_by_i, hash);
OBJ_INFECT(hash, obj);
return hash;
}
static VALUE
first_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, params))
{
NODE *memo = RNODE(params);
ENUM_WANT_SVALUE();
memo->u1.value = i;
rb_iter_break();
UNREACHABLE;
}
static VALUE enum_take(VALUE obj, VALUE n);
/*
* call-seq:
* enum.first -> obj or nil
* enum.first(n) -> an_array
*
* Returns the first element, or the first +n+ elements, of the enumerable.
* If the enumerable is empty, the first form returns <code>nil</code>, and the
* second form returns an empty array.
*
* %w[foo bar baz].first #=> "foo"
* %w[foo bar baz].first(2) #=> ["foo", "bar"]
* %w[foo bar baz].first(10) #=> ["foo", "bar", "baz"]
* [].first #=> nil
*
*/
static VALUE
enum_first(int argc, VALUE *argv, VALUE obj)
{
NODE *memo;
rb_check_arity(argc, 0, 1);
if (argc > 0) {
return enum_take(obj, argv[0]);
}
else {
memo = NEW_MEMO(Qnil, 0, 0);
rb_block_call(obj, id_each, 0, 0, first_i, (VALUE)memo);
return memo->u1.value;
}
}
/*
* call-seq:
* enum.sort -> array
* enum.sort { |a, b| block } -> array
*
* Returns an array containing the items in <i>enum</i> sorted,
* either according to their own <code><=></code> method, or by using
* the results of the supplied block. The block should return -1, 0, or
* +1 depending on the comparison between <i>a</i> and <i>b</i>. As of
* Ruby 1.8, the method <code>Enumerable#sort_by</code> implements a
* built-in Schwartzian Transform, useful when key computation or
* comparison is expensive.
*
* %w(rhea kea flea).sort #=> ["flea", "kea", "rhea"]
* (1..10).sort { |a, b| b <=> a } #=> [10, 9, 8, 7, 6, 5, 4, 3, 2, 1]
*/
static VALUE
enum_sort(VALUE obj)
{
return rb_ary_sort(enum_to_a(0, 0, obj));
}
#define SORT_BY_BUFSIZE 16
struct sort_by_data {
VALUE ary;
VALUE buf;
long n;
};
static VALUE
sort_by_i(RB_BLOCK_CALL_FUNC_ARGLIST(i, _data))
{
struct sort_by_data *data = (struct sort_by_data *)&RNODE(_data)->u1;
VALUE ary = data->ary;
VALUE v;
ENUM_WANT_SVALUE();
v = rb_yield(i);
if (RBASIC(ary)->klass) {
rb_raise(rb_eRuntimeError, "sort_by reentered");
}
if (RARRAY_LEN(data->buf) != SORT_BY_BUFSIZE*2) {
rb_raise(rb_eRuntimeError, "sort_by reentered");
}
RARRAY_ASET(data->buf, data->n*2, v);
RARRAY_ASET(data->buf, data->n*2+1, i);
data->n++;
if (data->n == SORT_BY_BUFSIZE) {
rb_ary_concat(ary, data->buf);
data->n = 0;
}
return Qnil;
}
static int
sort_by_cmp(const void *ap, const void *bp, void *data)
{
VALUE a;
VALUE b;
VALUE ary = (VALUE)data;
if (RBASIC(ary)->klass) {
rb_raise(rb_eRuntimeError, "sort_by reentered");
}
a = *(VALUE *)ap;
b = *(VALUE *)bp;
return rb_cmpint(rb_funcall(a, id_cmp, 1, b), a, b);
}
/*
* call-seq:
* enum.sort_by { |obj| block } -> array
* enum.sort_by -> an_enumerator
*
* Sorts <i>enum</i> using a set of keys generated by mapping the
* values in <i>enum</i> through the given block.
*
* If no block is given, an enumerator is returned instead.
*
* %w{apple pear fig}.sort_by { |word| word.length}
* #=> ["fig", "pear", "apple"]
*
* The current implementation of <code>sort_by</code> generates an
* array of tuples containing the original collection element and the
* mapped value. This makes <code>sort_by</code> fairly expensive when
* the keysets are simple.
*
* require 'benchmark'
*
* a = (1..100000).map { rand(100000) }
*
* Benchmark.bm(10) do |b|
* b.report("Sort") { a.sort }
* b.report("Sort by") { a.sort_by { |a| a } }
* end
*
* <em>produces:</em>
*
* user system total real
* Sort 0.180000 0.000000 0.180000 ( 0.175469)
* Sort by 1.980000 0.040000 2.020000 ( 2.013586)
*
* However, consider the case where comparing the keys is a non-trivial
* operation. The following code sorts some files on modification time
* using the basic <code>sort</code> method.
*
* files = Dir["*"]
* sorted = files.sort { |a, b| File.new(a).mtime <=> File.new(b).mtime }
* sorted #=> ["mon", "tues", "wed", "thurs"]
*
* This sort is inefficient: it generates two new <code>File</code>
* objects during every comparison. A slightly better technique is to
* use the <code>Kernel#test</code> method to generate the modification
* times directly.
*
* files = Dir["*"]
* sorted = files.sort { |a, b|
* test(?M, a) <=> test(?M, b)
* }
* sorted #=> ["mon", "tues", "wed", "thurs"]
*
* This still generates many unnecessary <code>Time</code> objects. A
* more efficient technique is to cache the sort keys (modification
* times in this case) before the sort. Perl users often call this
* approach a Schwartzian Transform, after Randal Schwartz. We
* construct a temporary array, where each element is an array
* containing our sort key along with the filename. We sort this array,
* and then extract the filename from the result.
*
* sorted = Dir["*"].collect { |f|
* [test(?M, f), f]
* }.sort.collect { |f| f[1] }
* sorted #=> ["mon", "tues", "wed", "thurs"]
*
* This is exactly what <code>sort_by</code> does internally.
*
* sorted = Dir["*"].sort_by { |f| test(?M, f) }
* sorted #=> ["mon", "tues", "wed", "thurs"]
*/
static VALUE
enum_sort_by(VALUE obj)
{
VALUE ary, buf;
NODE *memo;
long i;
struct sort_by_data *data;
RETURN_SIZED_ENUMERATOR(obj, 0, 0, enum_size);
if (RB_TYPE_P(obj, T_ARRAY) && RARRAY_LEN(obj) <= LONG_MAX/2) {
ary = rb_ary_new2(RARRAY_LEN(obj)*2);
}
else {
ary = rb_ary_new();
}
RBASIC_CLEAR_CLASS(ary);
buf = rb_ary_tmp_new(SORT_BY_BUFSIZE*2);
rb_ary_store(buf, SORT_BY_BUFSIZE*2-1, Qnil);
memo = NEW_MEMO(0, 0, 0);
OBJ_INFECT(memo, obj);
data = (struct sort_by_data *)&memo->u1;
data->ary = ary;
data->buf = buf;
data->n = 0;
rb_block_call(obj, id_each, 0, 0, sort_by_i, (VALUE)memo);
ary = data->ary;
buf = data->buf;
if (data->n) {
rb_ary_resize(buf, data->n*2);
rb_ary_concat(ary, buf);
}
if (RARRAY_LEN(ary) > 2) {
RARRAY_PTR_USE(ary, ptr,
ruby_qsort(ptr, RARRAY_LEN(ary)/2, 2*sizeof(VALUE),
sort_by_cmp, (void *)ary));
}
if (RBASIC(ary)->klass) {
rb_raise(rb_eRuntimeError, "sort_by reentered");
}
for (i=1; i<RARRAY_LEN(ary); i+=2) {
RARRAY_ASET(ary, i/2, RARRAY_AREF(ary, i));
}
rb_ary_resize(ary, RARRAY_LEN(ary)/2);
RBASIC_SET_CLASS_RAW(ary, rb_cArray);