feature #482 [Store] Add constructor with configurable chunk size and overlap to TextSplitTransformer (OskarStark)

This PR was merged into the main branch.

Discussion
----------

[Store] Add constructor with configurable chunk size and overlap to `TextSplitTransformer`

| Q             | A
| ------------- | ---
| Bug fix?      | no
| New feature?  | yes
| Docs?         | no
| Issues        | --
| License       | MIT

Commits
-------

17b3adb Add constructor with configurable chunk size and overlap to TextSplitTransformer

Author: OskarStark

src/store/src/Document/Transformer/TextSplitTransformer.php

@@ -29,13 +29,22 @@
     public const OPTION_CHUNK_SIZE = 'chunk_size';
     public const OPTION_OVERLAP = 'overlap';
 
+    public function __construct(
+        private int $chunkSize = 1000,
+        private int $overlap = 200,
+    ) {
+        if ($this->overlap < 0 || $this->overlap >= $this->chunkSize) {
+            throw new InvalidArgumentException(\sprintf('Overlap must be non-negative and less than chunk size. Got chunk size: %d, overlap: %d', $this->chunkSize, $this->overlap));
+        }
+    }
+
     /**
      * @param array{chunk_size?: int, overlap?: int} $options
      */
     public function transform(iterable $documents, array $options = []): iterable
     {
-        $chunkSize = $options[self::OPTION_CHUNK_SIZE] ?? 1000;
-        $overlap = $options[self::OPTION_OVERLAP] ?? 200;
+        $chunkSize = $options[self::OPTION_CHUNK_SIZE] ?? $this->chunkSize;
+        $overlap = $options[self::OPTION_OVERLAP] ?? $this->overlap;
 
         if ($overlap < 0 || $overlap >= $chunkSize) {
             throw new InvalidArgumentException('Overlap must be non-negative and less than chunk size.');

src/store/tests/Document/Transformer/TextSplitTransformerTest.php

@@ -184,6 +184,63 @@ public function testSplitWithNegativeOverlap()
         ]));
     }
 
+    public function testConstructorWithValidParameters()
+    {
+        $transformer = new TextSplitTransformer(500, 100);
+        $document = new TextDocument(Uuid::v4(), 'short text');
+
+        $chunks = iterator_to_array($transformer->transform([$document]));
+
+        $this->assertCount(1, $chunks);
+        $this->assertSame('short text', $chunks[0]->content);
+    }
+
+    public function testConstructorWithDefaultParameters()
+    {
+        $transformer = new TextSplitTransformer();
+        $document = new TextDocument(Uuid::v4(), 'short text');
+
+        $chunks = iterator_to_array($transformer->transform([$document]));
+
+        $this->assertCount(1, $chunks);
+        $this->assertSame('short text', $chunks[0]->content);
+    }
+
+    public function testConstructorWithNegativeOverlap()
+    {
+        $this->expectException(InvalidArgumentException::class);
+        $this->expectExceptionMessage('Overlap must be non-negative and less than chunk size. Got chunk size: 1000, overlap: -1');
+
+        new TextSplitTransformer(1000, -1);
+    }
+
+    public function testConstructorWithOverlapEqualToChunkSize()
+    {
+        $this->expectException(InvalidArgumentException::class);
+        $this->expectExceptionMessage('Overlap must be non-negative and less than chunk size. Got chunk size: 500, overlap: 500');
+
+        new TextSplitTransformer(500, 500);
+    }
+
+    public function testConstructorWithOverlapGreaterThanChunkSize()
+    {
+        $this->expectException(InvalidArgumentException::class);
+        $this->expectExceptionMessage('Overlap must be non-negative and less than chunk size. Got chunk size: 100, overlap: 200');
+
+        new TextSplitTransformer(100, 200);
+    }
+
+    public function testConstructorParametersAreUsedAsDefaults()
+    {
+        $transformer = new TextSplitTransformer(150, 25);
+        $document = new TextDocument(Uuid::v4(), $this->getLongText());
+
+        $chunks = iterator_to_array($transformer->transform([$document]));
+
+        $this->assertCount(12, $chunks);
+        $this->assertSame(150, mb_strlen($chunks[0]->content));
+    }
+
     private function getLongText(): string
     {
         return trim(file_get_contents(\dirname(__DIR__, 5).'/fixtures/lorem.txt'));