/
DataFrame.php
898 lines (755 loc) · 23.4 KB
/
DataFrame.php
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
<?php
declare(strict_types=1);
namespace Flow\ETL;
use function Flow\ETL\DSL\to_output;
use Flow\ETL\DataFrame\GroupedDataFrame;
use Flow\ETL\Dataset\{Report, Statistics};
use Flow\ETL\Exception\{InvalidArgumentException, InvalidFileFormatException, RuntimeException};
use Flow\ETL\Extractor\PartitionsExtractor;
use Flow\ETL\Filesystem\SaveMode;
use Flow\ETL\Formatter\AsciiTableFormatter;
use Flow\ETL\Function\{AggregatingFunction, ScalarFunction, WindowFunction};
use Flow\ETL\Join\{Expression, Join};
use Flow\ETL\Loader\SchemaValidationLoader;
use Flow\ETL\Loader\StreamLoader\Output;
use Flow\ETL\Partition\ScalarFunctionFilter;
use Flow\ETL\PHP\Type\{AutoCaster, Caster};
use Flow\ETL\Pipeline\{BatchingPipeline,
CachingPipeline,
CollectingPipeline,
GroupByPipeline,
HashJoinPipeline,
LinkedPipeline,
PartitioningPipeline,
SynchronousPipeline,
VoidPipeline};
use Flow\ETL\Row\{Reference, References, Schema};
use Flow\ETL\Transformer\StyleConverter\StringStyles;
use Flow\ETL\Transformer\{
AutoCastTransformer,
CallbackRowTransformer,
CrossJoinRowsTransformer,
DropDuplicatesTransformer,
DropEntriesTransformer,
DropPartitionsTransformer,
EntryNameStyleConverterTransformer,
JoinEachRowsTransformer,
LimitTransformer,
OrderEntriesTransformer,
OrderEntries\Comparator,
OrderEntries\TypeComparator,
RenameAllCaseTransformer,
RenameEntryTransformer,
RenameStrReplaceAllEntriesTransformer,
ScalarFunctionFilterTransformer,
ScalarFunctionTransformer,
SelectEntriesTransformer,
UntilTransformer,
WindowFunctionTransformer
};
use Flow\RDSL\AccessControl\{AllowAll, AllowList, DenyAll};
use Flow\RDSL\Attribute\DSLMethod;
use Flow\RDSL\{Builder, DSLNamespace, Executor, Finder};
final class DataFrame
{
private FlowContext $context;
public function __construct(private Pipeline $pipeline, Config|FlowContext $context)
{
$this->context = $context instanceof FlowContext ? $context : new FlowContext($context);
}
/**
* @throws InvalidArgumentException
*/
public static function fromArray(array $definition) : self
{
$namespaces = [
DSLNamespace::global(new DenyAll()),
new DSLNamespace('\Flow\ETL\DSL\Adapter\Avro', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\ChartJS', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\CSV', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\Doctrine', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\Elasticsearch', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\GoogleSheet', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\JSON', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\Meilisearch', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\Parquet', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\Text', new AllowAll()),
new DSLNamespace('\Flow\ETL\Adapter\XML', new AllowAll()),
new DSLNamespace('\Flow\ETL\DSL', new AllowAll()),
];
try {
$builder = new Builder(
new Finder(
$namespaces,
entryPointACL: new AllowList(['data_frame', 'df']),
methodACL: new AllowAll()
)
);
$results = (new Executor())->execute($builder->parse($definition));
if (\count($results) !== 1) {
throw new InvalidArgumentException('Invalid JSON, please make sure that there is only one data_frame function');
}
if (!$results[0] instanceof self) {
throw new InvalidArgumentException('Invalid JSON, expected DataFrame instance but got ' . \get_class($results[0]));
}
return $results[0];
} catch (\Flow\RDSL\Exception\InvalidArgumentException $e) {
throw new InvalidArgumentException($e->getMessage(), $e->getCode(), $e);
}
}
/**
* @throws \JsonException
* @throws InvalidArgumentException
*/
public static function fromJson(string $json) : self
{
try {
return self::fromArray(\json_decode($json, true, 512, JSON_THROW_ON_ERROR));
} catch (\JsonException $exception) {
throw new InvalidFileFormatException('json', 'unknown');
}
}
/**
* @lazy
*/
public function aggregate(AggregatingFunction ...$aggregations) : self
{
$groupBy = new GroupBy();
$groupBy->aggregate(...$aggregations);
$this->pipeline = new LinkedPipeline(new GroupByPipeline($groupBy, $this->pipeline));
return $this;
}
public function autoCast() : self
{
$this->pipeline->add(new AutoCastTransformer(new AutoCaster(Caster::default())));
return $this;
}
/**
* Merge/Split Rows yielded by Extractor into batches of given size.
* For example, when Extractor is yielding one row at time, this method will merge them into batches of given size
* before passing them to the next pipeline element.
* Similarly when Extractor is yielding batches of rows, this method will split them into smaller batches of given size.
*
* In order to merge all Rows into a single batch use DataFrame::collect() method.
*
* @param int<1, max> $size
*
* @lazy
*/
public function batchSize(int $size) : self
{
$this->pipeline = new LinkedPipeline(new BatchingPipeline($this->pipeline, $size));
return $this;
}
/**
* Start processing rows up to this moment and put each instance of Rows
* into previously defined cache.
* Cache type can be set through ConfigBuilder.
* By default everything is cached in system tmp dir.
*
* @lazy
*
* @param null|string $id
*
* @throws InvalidArgumentException
*/
public function cache(?string $id = null, ?int $cacheBatchSize = null) : self
{
if ($cacheBatchSize !== null && $cacheBatchSize < 1) {
throw new InvalidArgumentException('Cache batch size must be greater than 0');
}
$this->batchSize($cacheBatchSize ?? $this->context->config->cacheBatchSize());
$this->pipeline = new LinkedPipeline(new CachingPipeline($this->pipeline, $id));
return $this;
}
/**
* Before transforming rows, collect them and merge into single Rows instance.
* This might lead to memory issues when processing large amount of rows, use with caution.
*
* @lazy
*/
public function collect() : self
{
$this->pipeline = new LinkedPipeline(new CollectingPipeline($this->pipeline));
return $this;
}
/**
* This method allows to collect references to all entries used in this pipeline.
*
* ```php
* (new Flow())
* ->read(From::chain())
* ->collectRefs($refs = refs())
* ->run();
* ```
*
* @lazy
*/
#[DSLMethod(exclude: true)]
public function collectRefs(References $references) : self
{
$this->transform(new CallbackRowTransformer(function (Row $row) use ($references) : Row {
foreach ($row->entries()->all() as $entry) {
$references->add($entry->ref());
}
return $row;
}));
return $this;
}
/**
* @trigger
* Return total count of rows processed by this pipeline.
*/
#[DSLMethod(exclude: true)]
public function count() : int
{
$clone = clone $this;
$total = 0;
foreach ($clone->pipeline->process($clone->context) as $rows) {
$total += $rows->count();
}
return $total;
}
/**
* @lazy
*/
public function crossJoin(self $dataFrame, string $prefix = '') : self
{
$this->pipeline->add(new CrossJoinRowsTransformer($dataFrame, $prefix));
return $this;
}
/**
* @param int $limit maximum numbers of rows to display
* @param bool|int $truncate false or if set to 0 columns are not truncated, otherwise default truncate to 20 characters
* @param Formatter $formatter
*
* @trigger
*
* @throws InvalidArgumentException
*/
#[DSLMethod(exclude: true)]
public function display(int $limit = 20, int|bool $truncate = 20, Formatter $formatter = new AsciiTableFormatter()) : string
{
$clone = clone $this;
$clone->limit($limit);
$output = '';
foreach ($clone->pipeline->process($clone->context) as $rows) {
$output .= $formatter->format($rows, $truncate);
}
return $output;
}
/**
* Drop given entries.
*
* @lazy
*/
public function drop(string|Reference ...$entries) : self
{
$this->pipeline->add(new DropEntriesTransformer(...$entries));
return $this;
}
/**
* @param Reference|string ...$entries
*
* @lazy
*
* @return $this
*/
public function dropDuplicates(string|Reference ...$entries) : self
{
$this->pipeline->add(new DropDuplicatesTransformer(...$entries));
return $this;
}
/**
* Drop all partitions from Rows, additionally when $dropPartitionColumns is set to true, partition columns are also removed.
*
* @lazy
*/
public function dropPartitions(bool $dropPartitionColumns = false) : self
{
$this->pipeline->add(new DropPartitionsTransformer($dropPartitionColumns));
return $this;
}
/**
* Be aware that fetch is not memory safe and will load all rows into memory.
* If you want to safely iterate over Rows use oe of the following methods:.
*
* DataFrame::get() : \Generator
* DataFrame::getAsArray() : \Generator
* DataFrame::getEach() : \Generator
* DataFrame::getEachAsArray() : \Generator
*
* @trigger
*
* @throws InvalidArgumentException
*/
#[DSLMethod(exclude: true)]
public function fetch(?int $limit = null) : Rows
{
$clone = clone $this;
if ($limit !== null) {
$clone->limit($limit);
}
$rows = new Rows();
foreach ($clone->pipeline->process($clone->context) as $nextRows) {
$rows = $rows->merge($nextRows);
}
return $rows;
}
/**
* @lazy
*/
public function filter(ScalarFunction $function) : self
{
$this->pipeline->add(new ScalarFunctionFilterTransformer($function));
return $this;
}
/**
* @lazy
*
* @throws RuntimeException
*/
public function filterPartitions(Partition\PartitionFilter|ScalarFunction $filter) : self
{
$extractor = $this->pipeline->source();
if (!$extractor instanceof PartitionsExtractor) {
throw new RuntimeException('filterPartitions can be used only with extractors that implement PartitionsExtractor interface');
}
if ($filter instanceof Partition\PartitionFilter) {
$extractor->addPartitionFilter($filter);
return $this;
}
$extractor->addPartitionFilter(new ScalarFunctionFilter($filter, $this->context->entryFactory()));
return $this;
}
/**
* @trigger
*
* @param null|callable(Rows $rows) : void $callback
*/
#[DSLMethod(exclude: true)]
public function forEach(?callable $callback = null) : void
{
$clone = clone $this;
$clone->run($callback);
}
/**
* Yields each row as an instance of Rows.
*
* @trigger
*
* @return \Generator<Rows>
*/
#[DSLMethod(exclude: true)]
public function get() : \Generator
{
$clone = clone $this;
return $clone->pipeline->process($clone->context);
}
/**
* Yields each row as an array.
*
* @trigger
*
* @return \Generator<array<array>>
*/
#[DSLMethod(exclude: true)]
public function getAsArray() : \Generator
{
$clone = clone $this;
foreach ($clone->pipeline->process($clone->context) as $rows) {
yield $rows->toArray();
}
}
/**
* Yield each row as an instance of Row.
*
* @trigger
*
* @return \Generator<Row>
*/
#[DSLMethod(exclude: true)]
public function getEach() : \Generator
{
$clone = clone $this;
foreach ($clone->pipeline->process($clone->context) as $rows) {
foreach ($rows as $row) {
yield $row;
}
}
}
/**
* Yield each row as an array.
*
* @trigger
*
* @return \Generator<array>
*/
#[DSLMethod(exclude: true)]
public function getEachAsArray() : \Generator
{
$clone = clone $this;
foreach ($clone->pipeline->process($clone->context) as $rows) {
foreach ($rows as $row) {
yield $row->toArray();
}
}
}
/**
* @lazy
*/
public function groupBy(string|Reference ...$entries) : GroupedDataFrame
{
return new GroupedDataFrame($this, new GroupBy(...$entries));
}
/**
* @lazy
*
* @psalm-param string|Join $type
*/
public function join(self $dataFrame, Expression $on, string|Join $type = Join::left) : self
{
if (\is_string($type)) {
$type = Join::from($type);
}
$this->pipeline = new LinkedPipeline(new HashJoinPipeline($this->pipeline, $dataFrame, $on, $type));
return $this;
}
/**
* @lazy
*
* @psalm-param string|Join $type
*/
public function joinEach(DataFrameFactory $factory, Expression $on, string|Join $type = Join::left) : self
{
if ($type instanceof Join) {
$type = $type->name;
}
$transformer = match ($type) {
Join::left->value => JoinEachRowsTransformer::left($factory, $on),
Join::left_anti->value => JoinEachRowsTransformer::leftAnti($factory, $on),
Join::right->value => JoinEachRowsTransformer::right($factory, $on),
Join::inner->value => JoinEachRowsTransformer::inner($factory, $on),
default => throw new InvalidArgumentException('Unsupported join type')
};
$this->pipeline->add($transformer);
return $this;
}
/**
* @lazy
*
* @throws InvalidArgumentException
*/
public function limit(int $limit) : self
{
$this->pipeline = $this->context->config->optimizer()->optimize(new LimitTransformer($limit), $this->pipeline);
return $this;
}
/**
* @lazy
*/
public function load(Loader $loader) : self
{
$this->pipeline = $this->context->config->optimizer()->optimize($loader, $this->pipeline);
return $this;
}
/**
* @lazy
*
* @param callable(Row $row) : Row $callback
*/
#[DSLMethod(exclude: true)]
public function map(callable $callback) : self
{
$this->pipeline->add(new CallbackRowTransformer($callback));
return $this;
}
/**
* SaveMode defines how Flow should behave when writing to a file/files that already exists.
* For more details please see SaveMode enum.
*
* @param SaveMode $mode
*
* @lazy
*
* @return $this
*/
public function mode(SaveMode $mode) : self
{
$this->context->streams()->setSaveMode($mode);
return $this;
}
/**
* @lazy
*/
public function onError(ErrorHandler $handler) : self
{
$this->context->setErrorHandler($handler);
return $this;
}
/**
* @lazy
*/
public function partitionBy(string|Reference $entry, string|Reference ...$entries) : self
{
\array_unshift($entries, $entry);
$this->pipeline = new LinkedPipeline(new PartitioningPipeline($this->pipeline, References::init(...$entries)->all()));
return $this;
}
public function pivot(Reference $ref) : self
{
if (!$this->pipeline instanceof GroupByPipeline) {
throw new RuntimeException('Pivot can be used only after groupBy');
}
$this->pipeline->groupBy->pivot($ref);
return $this;
}
/**
* @trigger
*/
#[DSLMethod(exclude: true)]
public function printRows(?int $limit = 20, int|bool $truncate = 20, Formatter $formatter = new AsciiTableFormatter()) : void
{
$clone = clone $this;
if ($limit !== null) {
$clone->limit($limit);
}
$clone->load(to_output($truncate, Output::rows, $formatter));
$clone->run();
}
/**
* @trigger
*/
#[DSLMethod(exclude: true)]
public function printSchema(?int $limit = 20, Schema\SchemaFormatter $formatter = new Schema\Formatter\ASCIISchemaFormatter()) : void
{
$clone = clone $this;
if ($limit !== null) {
$clone->limit($limit);
}
$clone->load(to_output(false, Output::schema, schemaFormatter: $formatter));
$clone->run();
}
/**
* @lazy
*/
public function rename(string $from, string $to) : self
{
$this->pipeline->add(new RenameEntryTransformer($from, $to));
return $this;
}
/**
* @lazy
* Iterate over all entry names and replace given search string with replace string.
*/
public function renameAll(string $search, string $replace) : self
{
$this->pipeline->add(new RenameStrReplaceAllEntriesTransformer($search, $replace));
return $this;
}
/**
* @lazy
*/
public function renameAllLowerCase() : self
{
$this->pipeline->add(new RenameAllCaseTransformer(lower: true));
return $this;
}
/**
* @lazy
* Rename all entries to given style.
* Please look into \Flow\ETL\Transformer\StyleConverter\StringStyles class for all available styles.
*/
public function renameAllStyle(StringStyles|string $style) : self
{
$this->pipeline->add(new EntryNameStyleConverterTransformer(\is_string($style) ? StringStyles::fromString($style) : $style));
return $this;
}
/**
* @lazy
*/
public function renameAllUpperCase() : self
{
$this->pipeline->add(new RenameAllCaseTransformer(upper: true));
return $this;
}
/**
* @lazy
*/
public function renameAllUpperCaseFirst() : self
{
$this->pipeline->add(new RenameAllCaseTransformer(ucfirst: true));
return $this;
}
/**
* @lazy
*/
public function renameAllUpperCaseWord() : self
{
$this->pipeline->add(new RenameAllCaseTransformer(ucwords: true));
return $this;
}
public function reorderEntries(Comparator $comparator = new TypeComparator()) : self
{
$this->pipeline->add(new OrderEntriesTransformer($comparator));
return $this;
}
/**
* @lazy
* Alias for ETL::transform method.
*/
public function rows(Transformer|Transformation $transformer) : self
{
return $this->transform($transformer);
}
/**
* @trigger
*
* @param null|callable(Rows $rows): void $callback
* @param bool $analyze - when set to true, run will return Report
*/
#[DSLMethod(exclude: true)]
public function run(?callable $callback = null, bool $analyze = false) : ?Report
{
$clone = clone $this;
$totalRows = 0;
$schema = new Schema();
foreach ($clone->pipeline->process($clone->context) as $rows) {
if ($callback !== null) {
$callback($rows);
}
if ($analyze) {
$schema = $schema->merge($rows->schema());
$totalRows += $rows->count();
}
}
if ($analyze) {
return new Report($schema, new Statistics($totalRows));
}
return null;
}
/**
* Alias for DataFrame::mode.
*
* @lazy
*/
public function saveMode(SaveMode $mode) : self
{
return $this->mode($mode);
}
/**
* @trigger
*/
public function schema() : Schema
{
$schema = new Schema();
foreach ($this->pipeline->process($this->context) as $rows) {
$schema = $schema->merge($rows->schema());
}
return $schema;
}
/**
* @lazy
* Keep only given entries.
*/
public function select(string|Reference ...$entries) : self
{
$this->pipeline->add(new SelectEntriesTransformer(...$entries));
return $this;
}
/**
* @lazy
*/
public function sortBy(Reference ...$entries) : self
{
$this
->cache($this->context->config->id())
->run();
$this->pipeline = new SynchronousPipeline($this->context->config->externalSort()->sortBy(...$entries));
return $this;
}
/**
* @lazy
*/
public function transform(Transformer|Transformation $transformer) : self
{
if ($transformer instanceof Transformer) {
$this->pipeline->add($transformer);
return $this;
}
return $transformer->transform($this);
}
/**
* The difference between filter and until is that filter will keep filtering rows until extractors finish yielding rows.
* Until will send a STOP signal to the Extractor when the condition is not met.
*
* @lazy
*/
public function until(ScalarFunction $function) : self
{
$this->pipeline->add(new UntilTransformer($function));
return $this;
}
/**
* @lazy
*
* @param null|SchemaValidator $validator - when null, StrictValidator gets initialized
*/
public function validate(Schema $schema, ?SchemaValidator $validator = null) : self
{
$this->pipeline->add(new SchemaValidationLoader($schema, $validator ?? new Schema\StrictValidator()));
return $this;
}
/**
* @lazy
* This method is useful mostly in development when
* you want to pause processing at certain moment without
* removing code. All operations will get processed up to this point,
* from here no rows are passed forward.
*/
public function void() : self
{
$this->pipeline = new VoidPipeline($this->pipeline);
return $this;
}
/**
* @lazy
*
* @param array<string, ScalarFunction> $refs
*/
public function withEntries(array $refs) : self
{
foreach ($refs as $entryName => $ref) {
$this->withEntry($entryName, $ref);
}
return $this;
}
/**
* @lazy
*/
public function withEntry(string $entryName, ScalarFunction|WindowFunction $ref) : self
{
if ($ref instanceof WindowFunction) {
if (\count($ref->window()->partitions())) {
$this->pipeline = new LinkedPipeline(new PartitioningPipeline($this->pipeline, $ref->window()->partitions(), $ref->window()->order()));
} else {
$this->collect();
if (\count($ref->window()->order())) {
$this->sortBy(...$ref->window()->order());
}
}
$this->pipeline->add(new WindowFunctionTransformer($entryName, $ref));
} else {
$this->transform(new ScalarFunctionTransformer($entryName, $ref));
}
return $this;
}
/**
* @lazy
* Alias for ETL::load function.
*/
public function write(Loader $loader) : self
{
return $this->load($loader);
}
}