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.

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

Added ArrayLoader with usage example #1226

Merged
merged 2 commits into from
Sep 16, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
186 changes: 93 additions & 93 deletions composer.lock

Large diffs are not rendered by default.

23 changes: 23 additions & 0 deletions examples/topics/data_sink/array/code.php
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
<?php

declare(strict_types=1);

use function Flow\ETL\DSL\{data_frame, from_array, to_array};

require __DIR__ . '/../../../autoload.php';

$array = [];

data_frame()
->read(from_array([
['id' => 1],
['id' => 2],
['id' => 3],
['id' => 4],
['id' => 5],
]))
->collect()
->write(to_array($array))
->run();

\file_put_contents(__DIR__ . '/output.txt', \var_export($array, true));
2 changes: 2 additions & 0 deletions examples/topics/data_sink/array/description.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Write datasets directly to an associative array. Please pay attention to the memory usage when using array loader.
Large datasets may cause memory overflow.
22 changes: 22 additions & 0 deletions examples/topics/data_sink/array/output.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
array (
0 =>
array (
'id' => 1,
),
1 =>
array (
'id' => 2,
),
2 =>
array (
'id' => 3,
),
3 =>
array (
'id' => 4,
),
4 =>
array (
'id' => 5,
),
)
1 change: 1 addition & 0 deletions examples/topics/data_sink/array/priority.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
1
2 changes: 1 addition & 1 deletion examples/topics/data_sink/parquet/priority.txt
Original file line number Diff line number Diff line change
@@ -1 +1 @@
1
2
1 change: 1 addition & 0 deletions psalm.xml
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@
</projectFiles>
<issueHandlers>
<RedundantConditionGivenDocblockType errorLevel="suppress" />
<ReferenceConstraintViolation errorLevel="suppress" />
<DocblockTypeContradiction errorLevel="suppress" />
<RiskyTruthyFalsyComparison errorLevel="suppress" />
<LessSpecificReturnStatement errorLevel="suppress" />
Expand Down
14 changes: 13 additions & 1 deletion src/core/etl/src/Flow/ETL/DSL/functions.php
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@
When
};
use Flow\ETL\Loader\StreamLoader\Output;
use Flow\ETL\Loader\{CallbackLoader, MemoryLoader, StreamLoader, TransformerLoader};
use Flow\ETL\Loader\{ArrayLoader, CallbackLoader, MemoryLoader, StreamLoader, TransformerLoader};
use Flow\ETL\Memory\Memory;
use Flow\ETL\PHP\Type\Logical\List\ListElement;
use Flow\ETL\PHP\Type\Logical\Map\{MapKey, MapValue};
Expand Down Expand Up @@ -282,6 +282,18 @@ function to_memory(Memory $memory) : MemoryLoader
return new MemoryLoader($memory);
}

/**
* Convert rows to an array and store them in passed array variable.
*
* @param-out array<array<mixed>> $array
*/
#[DocumentationDSL(module: Module::CORE, type: DSLType::LOADER)]
#[DocumentationExample(topic: 'data_sink', example: 'array')]
function to_array(array &$array) : ArrayLoader
{
return new ArrayLoader($array);
}

#[DocumentationDSL(module: Module::CORE, type: DSLType::LOADER)]
function to_output(int|bool $truncate = 20, Output $output = Output::rows, Formatter $formatter = new Formatter\AsciiTableFormatter(), SchemaFormatter $schemaFormatter = new ASCIISchemaFormatter()) : StreamLoader
{
Expand Down
25 changes: 25 additions & 0 deletions src/core/etl/src/Flow/ETL/Loader/ArrayLoader.php
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
<?php

declare(strict_types=1);

namespace Flow\ETL\Loader;

use Flow\ETL\{FlowContext, Loader, Rows};

final class ArrayLoader implements Loader
{
/**
* @param-out array<array<mixed>> $array
*/
public function __construct(private array &$array)
{
}

public function load(Rows $rows, FlowContext $context) : void
{
$this->array = \array_merge(
$this->array,
$rows->toArray()
);
}
}
32 changes: 32 additions & 0 deletions src/core/etl/tests/Flow/ETL/Tests/Unit/Loader/ArrayLoaderTest.php
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
<?php

declare(strict_types=1);

namespace Flow\ETL\Tests\Unit\Loader;

use function Flow\ETL\DSL\{flow_context, int_entry, row, rows, str_entry, to_array};
use PHPUnit\Framework\TestCase;

final class ArrayLoaderTest extends TestCase
{
public function test_loads_rows_data_into_memory() : void
{
$rows1 = rows(
row(int_entry('number', 1), str_entry('name', 'one')),
row(int_entry('number', 2), str_entry('name', 'two')),
);

$rows2 = rows(
row(int_entry('number', 3), str_entry('name', 'three')),
row(int_entry('number', 4), str_entry('name', 'four')),
);

$array = [];

$loader = to_array($array);
$loader->load($rows1, flow_context());
$loader->load($rows2, flow_context());

self::assertEquals($rows1->merge($rows2)->toArray(), $array);
}
}
Loading