PHP code example of simsoft / data-flow

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

simsoft / data-flow example snippets

(new DataFlow())
    ->from($source)         // Extract: where data comes from
    ->transform($logic)     // Transform: reshape, filter, validate
    ->load($destination)    // Load: where data goes
    ->run();

use Simsoft\DataFlow\DataFlow;

(new DataFlow())
    ->from([1, 2, 3])
    ->transform(function($num) {
        return $num * 2;
    })
    ->load(function($num) {
        echo $num . PHP_EOL;
    })
    ->run();

// Output:
// 2
// 4
// 6

use Simsoft\DataFlow\DataFlow;

(new DataFlow())
    ->from([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
    ->transform(function($num) {
        return $num * 2;
    })
    ->limit(5)  // output only 5 data.
    ->load(function($num) {
        echo $num . PHP_EOL;
    })
    ->run();

// Output:
// 2
// 4
// 6
// 8
// 10

use Simsoft\DataFlow\DataFlow;

(new DataFlow())
    ->from([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
    ->filter(function($num) {
        // The call back should return bool.
        // In this case, return even number only.
        return $num % 2 === 0;
    })
    ->load(function($num) {
        echo $num . PHP_EOL;
    })
    ->run();

// Output:
// 2
// 4
// 6
// 8
// 10

(new DataFlow())
    ->from([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
    ->chunk(3) // set chunk size
    ->load(function(array $chunk, $key) {
        echo $key . '=' . json_encode($chunk, JSON_THROW_ON_ERROR) . PHP_EOL;
    })
    ->run();

// Output:
// 0=[1,2,3]
// 1=[4,5,6]
// 2=[7,8,9]
// 3=[10]

(new DataFlow())
    ->from([
        ['First Name' => 'John', 'Last Name' => 'Doe', 'age' => 20],
        ['First Name' => 'Jane', 'Last Name' => 'Doe', 'age' => 30],
        ['First Name' => 'John', 'Last Name' => 'Smith', 'age' => 50],
        ['First Name' => 'Jane', 'Last Name' => 'Smith', 'age' => 60],
    ])
    ->map([
        // rename the key
        'first_name' => 'First Name',
        'last_name' => 'Last Name',

        // customise data via callback method.
        'full_name' => fn($data) => $data['first_name'] . ' ' . $data['last_name'],
        'senior' => fn($data) => $data['age'] > 30 ? 'Yes' : 'No',
    ])
    ->load(function($data) {
        echo $data['full_name'] . ' is ' . $data['age'] . ' years old. ' . $data['senior'] . PHP_EOL;
    })
    ->run();

// Output:
// John Doe is 20 years old. No
// Jane Doe is 30 years old. Yes
// John Smith is 50 years old. Yes
// Jane Smith is 60 years old. Yes

(new DataFlow())
    ->from([
        ['first_name' => 'John', 'last_name' => 'Doe', 'age' => 20, 'status' => 'active', 'internal_id' => 'x99'],
        ['first_name' => 'Jane', 'last_name' => 'Smith', 'age' => 30, 'status' => 'inactive', 'internal_id' => 'x42'],
    ])
    ->setNewMap([
        'name' => fn($row) => $row['first_name'] . ' ' . $row['last_name'],
        'age' => 'age',
    ])
    ->load(function($data) {
        // $data contains ONLY 'name' and 'age' — no 'status', 'internal_id', etc.
        echo json_encode($data) . PHP_EOL;
    })
    ->run();

// Output:
// {"name":"John Doe","age":20}
// {"name":"Jane Smith","age":30}

(new DataFlow())
    ->from([
        ['name' => 'John', 'email' => '[email protected]'],
        ['name' => 'Jane', 'email' => '[email protected]'],
        ['name' => 'Bob', 'email' => '[email protected]'],
    ])
    ->map(['full_name' => fn($row) => strtoupper($row['name'])])
    ->preview(2) // show first 2 rows then stop
    ->run();

// Output:
// Key: 0
// Value: array (
//   'name' => 'John',
//   'email' => '[email protected]',
//   'full_name' => 'JOHN',
// )
//
// Key: 1
// Value: array (
//   'name' => 'Jane',
//   'email' => '[email protected]',
//   'full_name' => 'JANE',
// )

$flow1 = (new DataFlow())
    ->from([1, 2, 3])
    ->transform(function($num) {
        return $num * 2;
    });

(new DataFlow())
    ->from($flow1) // connect flow1 to flow2.
    ->transform(function($num) {
        return $num * 3;
    })
    ->load(function($num) {
        echo $num . PHP_EOL;
    })
    ->run();

// Output:
// 6
// 12
// 18

use Simsoft\DataFlow\DataFlow;

$result = (new DataFlow())
    ->from([1, 2, 3, 4, 5])
    ->transform(fn($n) => $n * 2)
    ->load(fn($n) => $n)
    ->run();

echo "Processed: {$result->getProcessedRows()} rows\n";
echo "Duration: " . round($result->getDurationMs()) . "ms\n";
echo "Peak memory: " . round($result->getPeakMemoryBytes() / 1024) . " KB\n";

use Simsoft\DataFlow\DataFlow;
use Simsoft\DataFlow\Enums\ErrorStrategy;

$result = (new DataFlow())
    ->from($records)
    ->transform(
        (new MyTransformer())
            ->withErrorStrategy(ErrorStrategy::Skip) // skip failing rows
            ->withName('validator')
    )
    ->load(fn($row) => $row)
    ->run();

echo "Processed: {$result->getProcessedRows()}\n";
echo "Failed: {$result->getFailedRows()}\n";

$result = (new DataFlow())
    ->from($records)
    ->transform(fn($row) => $row)
    ->load(new DatabaseLoader())
    ->dryRun()
    ->run();

echo "Would process: {$result->getProcessedRows()} rows\n";
// No data was actually written

use Simsoft\DataFlow\DataFlow;

$result = (new DataFlow())
    ->from($largeDataset)
    ->withLogger($psrLogger)
    ->onProgress(function (int $count, float $elapsedMs) {
        echo "\r  Processed {$count} rows...";
    }, interval: 1000)
    ->onError(function (\Throwable $e, mixed $row, string $stage) {
        error_log("[{$stage}] {$e->getMessage()}");
    })
    ->transform(fn($row) => $row)
    ->load(fn($row) => $row)
    ->run();

shell
php scripts/verify-release.php <version>