ingestify 0.7.0__py3-none-any.whl → 0.9.0__py3-none-any.whl

ingestify/tests/test_file_cache.py

@@ -0,0 +1,98 @@
+import pytest
+from io import BytesIO
+from unittest.mock import patch
+from datetime import datetime, timezone
+
+from ingestify.main import get_engine
+from ingestify.domain import Dataset, Identifier, Revision, File
+from ingestify.domain.models.dataset.revision import RevisionSource, SourceType
+
+
+def test_file_cache(config_file):
+    """Test file caching with the with_file_cache context manager."""
+    # Get engine from the fixture
+    engine = get_engine(config_file, "main")
+    store = engine.store
+
+    # Create a timestamp for test data
+    now = datetime.now(timezone.utc)
+
+    # Create a test file
+    test_file = File(
+        file_id="test_file_id",
+        data_feed_key="test_file",
+        tag="test_tag",
+        data_serialization_format="txt",
+        storage_path="test/path",
+        storage_size=100,
+        storage_compression_method="none",
+        created_at=now,
+        modified_at=now,
+        size=100,
+        content_type="text/plain",
+        data_spec_version="v1",
+    )
+
+    # Create a test revision with the file
+    revision = Revision(
+        revision_id=1,
+        created_at=now,
+        description="Test revision",
+        modified_files=[test_file],
+        source={"source_type": SourceType.MANUAL, "source_id": "test"},
+    )
+
+    # Create a test dataset with the revision
+    dataset = Dataset(
+        bucket="test-bucket",
+        dataset_id="test-dataset",
+        name="Test Dataset",
+        state="COMPLETE",
+        identifier=Identifier(test_id=1),
+        dataset_type="test",
+        provider="test-provider",
+        metadata={},
+        created_at=now,
+        updated_at=now,
+        last_modified_at=now,
+        revisions=[revision],
+    )
+
+    # Create a simple pass-through reader function to replace the gzip reader
+    def simple_reader(stream):
+        return stream
+
+    # Mock both the file repository and the _prepare_read_stream method
+    with patch.object(
+        store.file_repository, "load_content"
+    ) as mock_load_content, patch.object(
+        store, "_prepare_read_stream"
+    ) as mock_prepare_read_stream:
+
+        # Set up the mocks
+        mock_load_content.return_value = BytesIO(b"test content")
+        mock_prepare_read_stream.return_value = (simple_reader, "")
+
+        # Test without caching - should load files twice
+        store.load_files(dataset)
+        store.load_files(dataset)
+
+        # Should have called load_content twice (without caching)
+        assert mock_load_content.call_count == 2
+
+        # Reset the mock
+        mock_load_content.reset_mock()
+
+        # Test with caching - should load files only once
+        with store.with_file_cache():
+            store.load_files(dataset)
+            store.load_files(dataset)
+
+            # Should have called load_content only once (with caching)
+            assert mock_load_content.call_count == 1
+
+        # After exiting context, caching should be disabled
+        store.load_files(dataset)
+
+        # Should have called load_content again
+        assert mock_load_content.call_count == 2

ingestify/tests/test_pagination.py

@@ -0,0 +1,162 @@
+import pytest
+from datetime import datetime, timedelta
+import pytz
+
+from ingestify.domain import Dataset, Identifier, DatasetState
+from ingestify.main import get_engine
+
+
+def test_iter_dataset_collection_batches(config_file):
+    """Test iteration over datasets with batches using iter_dataset_collection_batches."""
+    # Get engine from the fixture
+    engine = get_engine(config_file, "main")
+    store = engine.store
+    bucket = store.bucket
+
+    # Create 30 datasets with different creation times
+    now = datetime.now(pytz.utc)
+
+    # Save datasets with ascending created_at timestamps
+    for i in range(30):
+        dataset = Dataset(
+            bucket=bucket,
+            dataset_id=f"dataset-{i}",
+            name=f"Dataset {i}",
+            state="COMPLETE",
+            identifier=Identifier(test_id=i),
+            dataset_type="test",
+            provider="test-provider",
+            metadata={},
+            created_at=now
+            + timedelta(minutes=i),  # Each dataset created 1 minute apart
+            updated_at=now + timedelta(minutes=i),
+            last_modified_at=now + timedelta(minutes=i),
+        )
+        store.dataset_repository.save(bucket, dataset)
+
+    # Test iteration with small batch_size (yields individual datasets)
+    dataset_ids = []
+    for dataset in store.iter_dataset_collection_batches(
+        dataset_type="test",
+        provider="test-provider",
+        batch_size=5,  # Small batch size to force multiple batches
+    ):
+        dataset_ids.append(dataset.dataset_id)
+
+    # Should get all 30 datasets
+    assert len(dataset_ids) == 30
+
+    # Make sure we have all datasets from 0 to 29
+    expected_ids = [f"dataset-{i}" for i in range(30)]
+    assert set(dataset_ids) == set(expected_ids)
+
+    # Test iteration yielding entire DatasetCollection objects
+    collections = []
+    for collection in store.iter_dataset_collection_batches(
+        dataset_type="test",
+        provider="test-provider",
+        batch_size=5,  # Small batch size to force multiple batches
+        yield_dataset_collection=True,
+    ):
+        collections.append(collection)
+
+    # Should have 6 collections (30 datasets / 5 per batch = 6 batches)
+    assert len(collections) == 6
+
+    # Verify total dataset count across all collections
+    total_datasets = sum(len(collection) for collection in collections)
+    assert total_datasets == 30
+
+    # Test iteration with a filter that returns fewer results
+    filtered_dataset_ids = []
+    for dataset in store.iter_dataset_collection_batches(
+        dataset_type="test",
+        provider="test-provider",
+        test_id=5,  # Only get dataset with test_id=5
+        batch_size=10,
+    ):
+        filtered_dataset_ids.append(dataset.dataset_id)
+
+    assert len(filtered_dataset_ids) == 1
+    assert filtered_dataset_ids[0] == "dataset-5"
+
+
+def test_dataset_state_filter(config_file):
+    """Test filtering datasets by state."""
+    # Get engine from the fixture
+    engine = get_engine(config_file, "main")
+    store = engine.store
+    bucket = store.bucket
+
+    now = datetime.now(pytz.utc)
+
+    # Create datasets with different states
+    states = [
+        DatasetState.COMPLETE,
+        DatasetState.PARTIAL,
+        DatasetState.SCHEDULED,
+        DatasetState.MISSING,
+    ]
+    for i in range(12):  # 3 datasets per state
+        state = states[i % 4]
+        dataset = Dataset(
+            bucket=bucket,
+            dataset_id=f"state-test-{i}",
+            name=f"State Test {i}",
+            state=state,
+            identifier=Identifier(test_id=i),
+            dataset_type="state-test",
+            provider="test-provider",
+            metadata={},
+            created_at=now + timedelta(minutes=i),
+            updated_at=now + timedelta(minutes=i),
+            last_modified_at=now + timedelta(minutes=i),
+        )
+        store.dataset_repository.save(bucket, dataset)
+
+    # Test filtering by a single state using enum
+    complete_datasets = store.get_dataset_collection(
+        dataset_type="state-test", dataset_state=DatasetState.COMPLETE
+    )
+    assert len(complete_datasets) == 3
+
+    # Test filtering by a single state using string
+    partial_datasets = store.get_dataset_collection(
+        dataset_type="state-test", dataset_state="PARTIAL"
+    )
+    assert len(partial_datasets) == 3
+
+    # Test filtering by multiple states using a list of enums
+    mixed_datasets = store.get_dataset_collection(
+        dataset_type="state-test",
+        dataset_state=[
+            DatasetState.COMPLETE,
+            DatasetState.SCHEDULED,
+            DatasetState.MISSING,
+        ],
+    )
+    assert len(mixed_datasets) == 9
+
+    # Test filtering by multiple states using a list of strings
+    mixed_datasets_strings = store.get_dataset_collection(
+        dataset_type="state-test", dataset_state=["COMPLETE", "SCHEDULED"]
+    )
+    assert len(mixed_datasets_strings) == 6
+
+    # Test case-insensitivity
+    lowercase_state_datasets = store.get_dataset_collection(
+        dataset_type="state-test", dataset_state="complete"
+    )
+    assert len(lowercase_state_datasets) == 3
+
+    # Test with iter_dataset_collection
+    scheduled_dataset_ids = []
+    for dataset in store.iter_dataset_collection_batches(
+        dataset_type="state-test",
+        dataset_state=DatasetState.SCHEDULED,
+        batch_size=2,  # Small batch size to test pagination with filters
+    ):
+        scheduled_dataset_ids.append(dataset.dataset_id)
+        assert dataset.state == DatasetState.SCHEDULED
+
+    assert len(scheduled_dataset_ids) == 3

ingestify/tests/test_store_version.py

@@ -0,0 +1,73 @@
+import pytest
+from unittest.mock import patch
+
+from ingestify.main import get_engine
+
+
+def test_store_version_tracking_new_store(config_file):
+    """Test that a new store gets initialized with the current version."""
+    with patch("ingestify.__version__", "1.0.0"):
+        engine = get_engine(config_file)
+
+        # Check that version was stored
+        stored_version = engine.store.dataset_repository.get_store_version()
+        assert stored_version == "1.0.0"
+
+
+def test_store_version_tracking_existing_store_same_version(config_file):
+    """Test that an existing store with same version doesn't cause issues."""
+    with patch("ingestify.__version__", "1.0.0"):
+        # Initialize store first time
+        engine1 = get_engine(config_file)
+        store1 = engine1.store
+
+        # Open store again with same version
+        engine2 = get_engine(config_file)
+        store2 = engine2.store
+
+        # Version should still be stored correctly
+        stored_version = store2.dataset_repository.get_store_version()
+        assert stored_version == "1.0.0"
+
+
+def test_store_version_tracking_version_mismatch(config_file, caplog):
+    """Test that version mismatch is logged as warning."""
+    # Initialize store with version 1.0.0
+    with patch("ingestify.__version__", "1.0.0"):
+        engine1 = get_engine(config_file)
+        store1 = engine1.store
+
+        stored_version = store1.dataset_repository.get_store_version()
+        assert stored_version == "1.0.0"
+
+    # Open store with different version
+    with patch("ingestify.__version__", "2.0.0"):
+        engine2 = get_engine(config_file)
+        store2 = engine2.store
+
+        # Version should still be the original one
+        stored_version = store2.dataset_repository.get_store_version()
+        assert stored_version == "1.0.0"
+
+        # Should have logged a warning about version mismatch
+        assert "Store version mismatch" in caplog.text
+        assert "stored=1.0.0, current=2.0.0" in caplog.text
+
+
+def test_store_version_methods(config_file):
+    """Test the repository version methods directly."""
+    engine = get_engine(config_file)
+    repo = engine.store.dataset_repository
+
+    from ingestify import __version__
+
+    # Initially the real version is stored
+    assert repo.get_store_version() == __version__
+
+    # Set a version
+    repo.set_store_version("1.2.3")
+    assert repo.get_store_version() == "1.2.3"
+
+    # Update version
+    repo.set_store_version("1.2.4")
+    assert repo.get_store_version() == "1.2.4"

ingestify/tests/test_table_prefix.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+"""End-to-end test for table_prefix configuration"""
+import tempfile
+import yaml
+from pathlib import Path
+from sqlalchemy import inspect
+
+from ingestify.main import get_datastore
+
+
+def test_table_prefix_from_config():
+    """Test that metadata_options.table_prefix is correctly applied from config"""
+    temp_dir = Path(tempfile.mkdtemp())
+
+    # Test 1: Config without metadata_options (default behavior)
+    config_no_prefix = {
+        "main": {
+            "metadata_url": f"sqlite:///{temp_dir / 'no_prefix.db'}",
+            "file_url": f"file://{temp_dir / 'files'}",
+            "default_bucket": "main",
+        }
+    }
+    config_path_no_prefix = temp_dir / "config_no_prefix.yaml"
+    config_path_no_prefix.write_text(yaml.dump(config_no_prefix))
+
+    store_no_prefix = get_datastore(str(config_path_no_prefix))
+    inspector = inspect(store_no_prefix.dataset_repository.session_provider.engine)
+    tables = inspector.get_table_names()
+
+    assert "dataset" in tables
+    assert "revision" in tables
+    assert "file" in tables
+    assert store_no_prefix.dataset_repository.dataset_table.name == "dataset"
+
+    # Test 2: Config with metadata_options.table_prefix
+    config_with_prefix = {
+        "main": {
+            "metadata_url": f"sqlite:///{temp_dir / 'with_prefix.db'}",
+            "file_url": f"file://{temp_dir / 'files'}",
+            "default_bucket": "main",
+            "metadata_options": {"table_prefix": "prod_"},
+        }
+    }
+    config_path_with_prefix = temp_dir / "config_with_prefix.yaml"
+    config_path_with_prefix.write_text(yaml.dump(config_with_prefix))
+
+    store_with_prefix = get_datastore(str(config_path_with_prefix))
+    inspector_prefixed = inspect(
+        store_with_prefix.dataset_repository.session_provider.engine
+    )
+    tables_prefixed = inspector_prefixed.get_table_names()
+
+    assert "prod_dataset" in tables_prefixed
+    assert "prod_revision" in tables_prefixed
+    assert "prod_file" in tables_prefixed
+    assert "prod_ingestion_job_summary" in tables_prefixed
+    assert "prod_task_summary" in tables_prefixed
+    assert "prod_store_version" in tables_prefixed
+    assert store_with_prefix.dataset_repository.dataset_table.name == "prod_dataset"
+
+    # Verify foreign keys reference prefixed tables
+    revision_fks = inspector_prefixed.get_foreign_keys("prod_revision")
+    assert revision_fks[0]["referred_table"] == "prod_dataset"
+
+    file_fks = inspector_prefixed.get_foreign_keys("prod_file")
+    assert file_fks[0]["referred_table"] == "prod_revision"
+
+    task_fks = inspector_prefixed.get_foreign_keys("prod_task_summary")
+    assert task_fks[0]["referred_table"] == "prod_ingestion_job_summary"
+
+    import shutil
+
+    shutil.rmtree(temp_dir)
+
+
+if __name__ == "__main__":
+    test_table_prefix_from_config()
+    print("✓ All tests passed")

{ingestify-0.7.0.dist-info → ingestify-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: ingestify
-Version: 0.7.0
+Version: 0.9.0
 Summary: Data Ingestion Framework
 Author: Koen Vossen
 Author-email: info@koenvossen.nl
@@ -10,12 +10,20 @@ Requires-Dist: requests<3,>=2.0.0
 Requires-Dist: SQLAlchemy<3,>=2
 Requires-Dist: click>=8
 Requires-Dist: python-dotenv
-Requires-Dist: pyaml-env
+Requires-Dist: pyaml_env
 Requires-Dist: boto3
 Requires-Dist: pydantic>=2.0.0
 Provides-Extra: test
 Requires-Dist: pytest<7,>=6.2.5; extra == "test"
 Requires-Dist: pytz; extra == "test"
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary
 
 # Ingestify
 
@@ -77,6 +85,43 @@ Ingestify fixes that by building **your own data lake** of untouched provider fi
 pip install ingestify            # or: pip install git+https://github.com/PySport/ingestify.git
 ```
 
+### Developing a new Source
+
+When developing a new `Source`, use the `debug_source()` helper for rapid iteration:
+
+```python
+from ingestify import Source, debug_source
+
+class MyCustomSource(Source):
+    provider = "my_provider"
+
+    def __init__(self, name: str, api_key: str):
+        super().__init__(name)
+        self.api_key = api_key
+
+    def find_datasets(self, dataset_type, data_spec_versions, **kwargs):
+        # Your source implementation
+        ...
+
+# Quick debug - runs full ingestion with temp storage
+if __name__ == "__main__":
+    source = MyCustomSource(name="test", api_key="...")
+
+    debug_source(
+        source,
+        dataset_type="match",
+        data_spec_versions={"events": "v1"},
+    )
+```
+
+The `debug_source()` helper:
+- ✅ Creates an ephemeral dev engine with temp storage
+- ✅ Configures logging automatically
+- ✅ Runs the full ingestion cycle
+- ✅ Shows storage location and results
+
+Perfect for testing your source before adding it to production config!
+
 ### Minimal `config.yaml`
 
 ```yaml
@@ -175,8 +220,16 @@ pip install kloppy
 ```
 
 ```python
+import logging, sys
+
 from ingestify.main import get_engine
 
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
+    stream=sys.stderr,
+)
+
 engine = get_engine(
     metadata_url="sqlite:///database_open_data/catalog.db",
     file_url="file://database_open_data/files/"
@@ -188,12 +241,13 @@ dataset_iter = engine.iter_datasets(
 
     provider="statsbomb",
     dataset_type="match",
-    competition_id=43,
-    season_id=281
+    competition_id=43,  # "FIFA World Cup"
+    #season_id=281
 )
 
 for dataset in dataset_iter:
     kloppy_dataset = engine.load_dataset_with_kloppy(dataset)
+    logging.info(f"Loaded {kloppy_dataset}")
 ```
 
 

{ingestify-0.7.0.dist-info → ingestify-0.9.0.dist-info}/RECORD

@@ -1,14 +1,14 @@
-ingestify/__init__.py,sha256=IuO5KQRTWAjWxmJ6Knte5-Q2Ybq1BDDkM5UlZjYRl84,301
+ingestify/__init__.py,sha256=fVzksB6rrJmEm-2P5DvT2JbShYaTZ2nKdbbZf8KabC4,336
 ingestify/cmdline.py,sha256=Rs1_lSKSIJrcygH5fvtOGicOl_e0sZYW7deqp4_jGbY,6233
 ingestify/exceptions.py,sha256=izRzaLQmMy-4P8ZqGqVZyf4k6LFYOYqwYLuRaUH8BJw,187
-ingestify/main.py,sha256=YegWoI_xIgoz30BSS7N6Ew3SAXSr1-jPFMPqvFda3DI,9797
+ingestify/main.py,sha256=mMXDNzSl1dzN03BUiS97uP3XwFMdgadxP0hJlONsZ_g,15789
 ingestify/server.py,sha256=OVrf_XtpAQIn88MzqQzShXgsA9_jbnqYvD8YPBjn3cs,2413
 ingestify/source_base.py,sha256=GXAFCoT11Zov9M2v-fqQr9gFCXbtVfEIEH32V7r2oE8,382
 ingestify/utils.py,sha256=tsoo-GgeSrwK161WCqW793BAm5bjvnGwI8yGgLTJ1lk,6486
 ingestify/application/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestify/application/dataset_store.py,sha256=GP6wGjVirefEn6hlqWIkOBqdELad9L_mmTpdHdzj18M,20353
-ingestify/application/ingestion_engine.py,sha256=cG4JgU667PcsHBngOWUk58KffDrHkJOMv8LrVjaRQ1o,11163
-ingestify/application/loader.py,sha256=xImeaOdj97iCpprZ0WxRbQJ4w6nS1cEmPba7TN1lE6I,13038
+ingestify/application/ingestion_engine.py,sha256=we16yiDS9QGOlAUiP1vidDycihjWK3B2jo64uqKmrXE,11246
+ingestify/application/loader.py,sha256=K99ZJuHMEJFO6CIlxoyHKGSQtXw63JgOYu3moUD6sR0,13400
 ingestify/application/secrets_manager.py,sha256=5qCbPfUvRGP1Xbq6xPkMfpgYl8uPzF_0NbiKeRY5zxU,1757
 ingestify/domain/__init__.py,sha256=M7_fVTJjQUx53P4UQUPhowRKPKsIIjx4JYZL1yjHKsM,46
 ingestify/domain/models/__init__.py,sha256=WuKS34uiR1EwyczKujBHYGupqseJP-U2P5IQS4kpsA8,838
@@ -23,9 +23,9 @@ ingestify/domain/models/dataset/collection.py,sha256=YKGQv6hqm88MYlNp2c47CoWysyN
 ingestify/domain/models/dataset/collection_metadata.py,sha256=aWY6O3_JLj_jKfVfUTjmi3-E4heBmmmtqX81vhdzr0I,498
 ingestify/domain/models/dataset/dataset.py,sha256=OiP03nY0-m06y2GTrs_m-RiZE8HwypIHRwSqoM_DNnQ,4049
 ingestify/domain/models/dataset/dataset_repository.py,sha256=bf3F_1cKw0CvUberD3FMROE8iowAmYefnD4L6aPB39k,989
-ingestify/domain/models/dataset/dataset_state.py,sha256=IaYG02WzgooGaM_AuwRhZgljs-9NhCF_LpBZXkl5ELY,324
+ingestify/domain/models/dataset/dataset_state.py,sha256=AHJSoCXGVJeBe0eyFJMfvLdAZuf82xjdReCyCWZFlSY,348
 ingestify/domain/models/dataset/events.py,sha256=M8jrHWCm9iXapAy3xjvZZtiiOxXDnfefBixiMwkas24,786
-ingestify/domain/models/dataset/file.py,sha256=2wpBfluS8i_mCPQkdSu1x1Af3kc15bVBLAKXeogB4jA,4243
+ingestify/domain/models/dataset/file.py,sha256=cXDjSw19HRMCGFpVN4u1oejxE1V8SMQptfNVDVixj6o,4464
 ingestify/domain/models/dataset/file_collection.py,sha256=yaQmqFlmbajLCkU5QnjgqCvKzvVEZJrXVvinx5UGHcM,1193
 ingestify/domain/models/dataset/file_repository.py,sha256=9EQprch9isAH2pbK7e7tfOKl6ulip4Ij1kBCTbO_rTc,1721
 ingestify/domain/models/dataset/identifier.py,sha256=EJYsxt0OS_43Y989DZQq8U9NjwmtvnHGYGMe6-hOBlI,575
@@ -39,11 +39,11 @@ ingestify/domain/models/event/event_bus.py,sha256=feVXsbBcRNkbWYvXbmz-Yi9-3R690y
 ingestify/domain/models/event/publisher.py,sha256=TOAawYYiPQCLR2Gm17LumMEzeapMDYcAYeklLFmwqAY,620
 ingestify/domain/models/event/subscriber.py,sha256=tP1ZFSvpJWKUITnATYekRxJzepz85UY7egBTMiP-dwg,1039
 ingestify/domain/models/ingestion/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ingestify/domain/models/ingestion/ingestion_job.py,sha256=KaKpAu0XKvWV1YoWaTlOjbapcs-CCAvOHlSxUHZxZwI,15450
+ingestify/domain/models/ingestion/ingestion_job.py,sha256=Ou8v_FXDNnbrzPjHYiLoXMEg7ZRNFPjK1BMk9DY7L2E,15574
 ingestify/domain/models/ingestion/ingestion_job_summary.py,sha256=7dmkWEvE7lMSv1ILWcSvys1bUGuGe_s-YbOFC6eYMBI,4794
 ingestify/domain/models/ingestion/ingestion_plan.py,sha256=KAvITBMQt3zmMFokESQJyp3rMuz1Hxr6msfZK1_faZM,648
 ingestify/domain/models/resources/__init__.py,sha256=ZuY9DPRfwk-aLB3Lj6DYP_NqMkcQfcYjZp4VejTtcbU,46
-ingestify/domain/models/resources/dataset_resource.py,sha256=Le_C4nPzPPTDq75_amKSNsR94QvVWdZ_ZkjYIKa6whM,3084
+ingestify/domain/models/resources/dataset_resource.py,sha256=zhTCM4bX6Wf4iWG2g8_SBx2U05YFxTxiZK3f6EqwD6I,3598
 ingestify/domain/models/task/__init__.py,sha256=BdlyIPvE07Xax_IzLgO9DUw0wsz9OZutxnxdDNyRlys,79
 ingestify/domain/models/task/set.py,sha256=04txDYgS5rotXofD9TqChKdW0VZIYshrkfPIpXtlhW4,430
 ingestify/domain/models/task/task.py,sha256=OwLZQi9GGe0O8m1dKvJdN2Rham5oilI49KyKc5uV20A,161
@@ -54,7 +54,7 @@ ingestify/domain/services/transformers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JC
 ingestify/domain/services/transformers/kloppy_to_pandas.py,sha256=NcN6nTBGVn9gz-_hWZJTMcduS1Gg7EM4X95Cqxi1QIM,809
 ingestify/infra/__init__.py,sha256=V0hpLzPVTcOHRVh0gguF6FT30YIgEOUd5v87xUHkfZ4,88
 ingestify/infra/fetch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ingestify/infra/fetch/http.py,sha256=MkD59snSvqQOPwp1dJa0jJTS_3z3-OWrCDlUOjvEh2o,4653
+ingestify/infra/fetch/http.py,sha256=oaERHk-0Azu3T2-r5gHPuC9qvmD4cPURGY02q3GoI00,4647
 ingestify/infra/serialization/__init__.py,sha256=UqXWJmKTp7Mi58ZyDASGguPFlqdVWVUbm_sg9GWx9eI,702
 ingestify/infra/sink/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestify/infra/sink/postgresql.py,sha256=SxuM3LntfYcpCriUpqJhMvgAf0s9cohXf6WkxSEDYDY,1816
@@ -66,14 +66,23 @@ ingestify/infra/source/statsbomb/match.py,sha256=8Zpdys6-bB_ral2AmjGKhF4BnXW3F0Y
 ingestify/infra/store/__init__.py,sha256=3dA6NWfB6FS5SFdQiSlJ0ZghBfnUAUuGIP5Vr4rkCqk,43
 ingestify/infra/store/dataset/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestify/infra/store/dataset/sqlalchemy/__init__.py,sha256=Z5JHWGO_hwT6rO-ecMOOAmOKjFFJi449KZvJTQgt6vQ,52
-ingestify/infra/store/dataset/sqlalchemy/repository.py,sha256=cMmhXqUNp_HUg_IgsUlJ439VXX_H67pnivaToUlqlA4,22552
-ingestify/infra/store/dataset/sqlalchemy/tables.py,sha256=ffHop9DQeVE9JrCMLJ2EvF7MD7j8thfjVwv2xcsbJtY,10954
+ingestify/infra/store/dataset/sqlalchemy/repository.py,sha256=6WPHKxA6UhgzO3P4Sdbq7W14tTMxisC8Js3MZilPoNc,24160
+ingestify/infra/store/dataset/sqlalchemy/tables.py,sha256=1FewCsN7jdk1ITzL_neOwJWtHD03NxCS9E8dhZcz4oY,12236
 ingestify/infra/store/file/__init__.py,sha256=DuEekZa2pmDuRCFiulbgoGotN0wGv3OrRXSvokY0PhY,104
 ingestify/infra/store/file/dummy_file_repository.py,sha256=azUq9c43Mz9-GWk9j0E97BaqyUKu-ZMrcuaIednLq5E,723
 ingestify/infra/store/file/local_file_repository.py,sha256=1hhLqds5LlppJq2QBB0oN0Q98j6aXreCtYQYz3Q1P8g,819
 ingestify/infra/store/file/s3_file_repository.py,sha256=tz_EZ_gun7W2qJMlI3j_R03iKBZlJSDcG7AUJ1JkdpE,1501
-ingestify-0.7.0.dist-info/METADATA,sha256=cNjbTVDpw0MTkPj-xoywVXzdrynoRAO5z7qyu1LftLg,6871
-ingestify-0.7.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-ingestify-0.7.0.dist-info/entry_points.txt,sha256=czYYXeX2ul4zdeB6bKlz3HaUF7zyVVcj9E_sRNDisI0,53
-ingestify-0.7.0.dist-info/top_level.txt,sha256=Lwnjgns4KequS7KiicXhh6mLUvcdfjzLyPI4qf_s4A0,10
-ingestify-0.7.0.dist-info/RECORD,,
+ingestify/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ingestify/tests/conftest.py,sha256=Cr768nLMWUfIP6FMR7aFhUCY4uQ9Tz_bXOq0udpiDEE,411
+ingestify/tests/test_auto_ingest.py,sha256=coMOzJBTbeDwUSYDLnqmkaCXpG-6WQeKqf_nj9XFiA4,14502
+ingestify/tests/test_engine.py,sha256=x3_o6M3satos029Er84ptbzxRKoBw5KB0am2KJSQ16Q,15738
+ingestify/tests/test_events.py,sha256=A1f8H4HRyn52SWo3wV_MgSeb6IbT_lNi9wWAK8EGsK4,7806
+ingestify/tests/test_file_cache.py,sha256=Xbh_VLLDH-KQXE3MeujDeOjjYYbAnjGR6wsHwMInKco,3049
+ingestify/tests/test_pagination.py,sha256=uAKDMsM6fYSa4NcAlXDllu2y-8lnh0AclhPZ5MWJKn8,5539
+ingestify/tests/test_store_version.py,sha256=4czUG8LtaGxgjW4trw7BzYJA8blQp3-HM8w-7HjqFl0,2508
+ingestify/tests/test_table_prefix.py,sha256=6N42T6hfulqTlsUlrwhNmZ-TK-ZOt4U8Jx9NxKyLS4I,2844
+ingestify-0.9.0.dist-info/METADATA,sha256=1j8178-ZiJrZb3CkWSiKU4rlBfRnmSMdAaVytjrKc9w,8263
+ingestify-0.9.0.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+ingestify-0.9.0.dist-info/entry_points.txt,sha256=czYYXeX2ul4zdeB6bKlz3HaUF7zyVVcj9E_sRNDisI0,53
+ingestify-0.9.0.dist-info/top_level.txt,sha256=Lwnjgns4KequS7KiicXhh6mLUvcdfjzLyPI4qf_s4A0,10
+ingestify-0.9.0.dist-info/RECORD,,

{ingestify-0.7.0.dist-info → ingestify-0.9.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.45.1)
+Generator: setuptools (79.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any