Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Allow to group by uuid/datetime objects without casting them to scalar first #998

Merged
merged 1 commit into from
Feb 21, 2024
Merged

Allow to group by uuid/datetime objects without casting them to scalar first #998

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 24 additions & 14 deletions src/core/etl/src/Flow/ETL/GroupBy.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
use Flow\ETL\Exception\InvalidArgumentException;
use Flow\ETL\Exception\RuntimeException;
use Flow\ETL\Function\AggregatingFunction;
use Flow\ETL\Row\Entry;
use Flow\ETL\Row\Reference;
use Flow\ETL\Row\References;

Expand Down Expand Up @@ -59,13 +60,7 @@ public function group(Rows $rows) : void
if ($this->pivot) {
foreach ($rows as $row) {
try {
$pivotValue = $row->valueOf($this->pivot);

if (!\is_scalar($pivotValue) && null !== $pivotValue) {
throw new RuntimeException('Pivoting by non scalar values is not supported, given: ' . \gettype($pivotValue));
}

$this->pivotColumns[] = $pivotValue;
$this->pivotColumns[] = $this->toScalar($row->get($this->pivot));
} catch (InvalidArgumentException) {
$this->pivotColumns[] = null;
}
Expand Down Expand Up @@ -99,13 +94,7 @@ public function group(Rows $rows) : void

foreach ($this->refs as $ref) {
try {
$value = $row->valueOf($ref);

if (!\is_scalar($value) && null !== $value) {
throw new RuntimeException('Grouping by non scalar values is not supported, given: ' . \gettype($value));
}

$values[$ref->name()] = $value;
$values[$ref->name()] = $this->toScalar($row->get($ref));
} catch (InvalidArgumentException) {
$values[$ref->name()] = null;
}
Expand Down Expand Up @@ -204,4 +193,25 @@ private function hash(array $values) : string

return \hash('xxh128', \implode('', $stringValues));
}

private function toScalar(Entry $entry) : int|string|float|null
{
if ($entry->value() === null) {
return null;
}

if (\is_bool($entry->value())) {
return $entry->toString();
}

if (\is_scalar($entry->value())) {
return $entry->value();
}

return match ($entry::class) {
Entry\UuidEntry::class => $entry->value()->toString(),
Entry\DateTimeEntry::class => $entry->value()->format(\DateTimeImmutable::ATOM),
default => $entry->toString()
};
}
}
24 changes: 24 additions & 0 deletions src/core/etl/tests/Flow/ETL/Tests/Integration/DataFrame/GroupByTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
use function Flow\ETL\DSL\from_memory;
use function Flow\ETL\DSL\from_rows;
use function Flow\ETL\DSL\int_entry;
use function Flow\ETL\DSL\integer_entry;
use function Flow\ETL\DSL\lit;
use function Flow\ETL\DSL\max;
use function Flow\ETL\DSL\null_entry;
Expand All @@ -24,6 +25,7 @@
use Flow\ETL\Row;
use Flow\ETL\Rows;
use Flow\ETL\Tests\Integration\IntegrationTestCase;
use Ramsey\Uuid\Uuid;

final class GroupByTest extends IntegrationTestCase
{
Expand Down Expand Up @@ -216,6 +218,28 @@ public function test_group_by_twice() : void
);
}

public function test_group_by_uuid() : void
{
$rows = df()
->read(from_array([
['id' => Uuid::uuid4()->toString()],
['id' => Uuid::uuid4()->toString()],
['id' => Uuid::uuid4()->toString()],
['id' => Uuid::uuid4()->toString()],
['id' => Uuid::uuid4()->toString()],
['id' => Uuid::uuid4()->toString()],
['id' => Uuid::uuid4()->toString()],
['id' => Uuid::uuid4()->toString()],
]))
->aggregate(count(ref('id')))
->fetch();

$this->assertEquals(
new Rows(Row::create(integer_entry('id_count', 8))),
$rows
);
}

public function test_pivot() : void
{
$dataset1 = [
Expand Down
15 changes: 0 additions & 15 deletions src/core/etl/tests/Flow/ETL/Tests/Unit/GroupByTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@

namespace Flow\ETL\Tests\Unit;

use function Flow\ETL\DSL\array_entry;
use function Flow\ETL\DSL\int_entry;
use function Flow\ETL\DSL\null_entry;
use function Flow\ETL\DSL\ref;
Expand All @@ -21,20 +20,6 @@

final class GroupByTest extends TestCase
{
public function test_group_by_array_entry() : void
{
$this->expectExceptionMessage('Grouping by non scalar values is not supported, given: array');
$this->expectException(RuntimeException::class);

$groupBy = new GroupBy('array');

$groupBy->group(new Rows(
Row::create(array_entry('array', [1, 2, 3])),
Row::create(array_entry('array', [1, 2, 3])),
Row::create(array_entry('array', [4, 5, 6]))
));
}

public function test_group_by_missing_entry() : void
{
$groupBy = new GroupBy('type');
Expand Down
Loading