Progress bars for ingestion/deletion (#188)

* Rename timeseries dataset and collection to just dataset/collection

* Ingest/delete in batches

* Prepare release v0.35

Author: lukasbindreiter

CHANGELOG.md

@@ -7,9 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.35.0] - 2025-04-29
+
 ## Added
 
 - Support for ingestion of enum values into datasets
+- Pagination support for ingestion / deletion of large numbers of datapoints
+
+## Changed
+
+- Renamed `TimeseriesDataset` to `DatasetClient`
+- Renamed `TimeseriesCollection` to `CollectionClient`
 
 ## [0.34.0] - 2025-04-15
 
@@ -153,7 +161,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Released packages: `tilebox-datasets`, `tilebox-workflows`, `tilebox-storage`, `tilebox-grpc`
 
 
-[Unreleased]: https://github.com/tilebox/tilebox-python/compare/v0.34.0...HEAD
+[Unreleased]: https://github.com/tilebox/tilebox-python/compare/v0.35.0...HEAD
+[0.35.0]: https://github.com/tilebox/tilebox-python/compare/v0.34.0...v0.35.0
 [0.34.0]: https://github.com/tilebox/tilebox-python/compare/v0.33.1...v0.34.0
 [0.33.1]: https://github.com/tilebox/tilebox-python/compare/v0.33.0...v0.33.1
 [0.33.0]: https://github.com/tilebox/tilebox-python/compare/v0.32.1...v0.33.0

tilebox-datasets/tests/test_client.py

@@ -9,7 +9,7 @@
 
 from _tilebox.grpc.error import NotFoundError
 from _tilebox.grpc.replay import open_recording_channel, open_replay_channel
-from tilebox.datasets import Client, TimeseriesDataset
+from tilebox.datasets import Client, DatasetClient
 from tilebox.datasets.data.datapoint import DatapointPage
 from tilebox.datasets.data.time_interval import us_to_datetime
 
@@ -53,7 +53,7 @@ def test_list_datasets() -> None:
 
     datasets = client.datasets()
     # let's check that we can access a dataset
-    assert isinstance(datasets.open_data.copernicus.sentinel2_msi, TimeseriesDataset)
+    assert isinstance(datasets.open_data.copernicus.sentinel2_msi, DatasetClient)
     # let's check that the repr contains the summaries of the datasets
     assert "sentinel2_msi" in repr(datasets)
     assert "Sentinel-2 is equipped with an optical instrument payload that samples" in repr(datasets)

tilebox-datasets/tests/test_timeseries.py

@@ -14,7 +14,7 @@
 from tests.data.collection import collection_infos, collection_names
 from tests.data.datapoint import datapoints, paginated_datapoint_for_interval_responses
 from tests.data.datasets import example_dataset_type
-from tilebox.datasets import TimeseriesCollection, TimeseriesDataset
+from tilebox.datasets import CollectionClient, DatasetClient
 from tilebox.datasets.data.collection import Collection, CollectionInfo
 from tilebox.datasets.data.datapoint import Datapoint, DatapointPage
 from tilebox.datasets.data.datasets import Dataset
@@ -37,13 +37,13 @@
 from tilebox.datasets.service import TileboxDatasetService
 
 
-def _mocked_dataset() -> tuple[TimeseriesDataset, MagicMock]:
+def _mocked_dataset() -> tuple[DatasetClient, MagicMock]:
     service = MagicMock()
 
     # we do not sample/draw from datasets() here, because the values themselves are irrelevant for the tests
     # (we are not testing properties, but rather writing conventional unit tests here, so it doesn't make sense to
     # run them multiple times)
-    dataset = TimeseriesDataset(
+    dataset = DatasetClient(
         service,
         Dataset(
             id=uuid4(),
@@ -85,7 +85,7 @@ def test_timeseries_dataset_list_collections(infos: list[CollectionInfo]) -> Non
 
     for info in infos:
         collection = collections[info.collection.name]
-        assert isinstance(collection, TimeseriesCollection), "Expected a RemoteTimeseriesDatasetCollection"
+        assert isinstance(collection, CollectionClient), "Expected a RemoteTimeseriesDatasetCollection"
         assert collection.name == info.collection.name, "Name mismatch in collection"
         assert repr(info) in repr(collection), "Expected info to be in collection repr"
         assert collection._info == info, "Expected info to be cached"
@@ -108,9 +108,9 @@ def test_timeseries_dataset_get_collection(collection_name: str) -> None:
 
 @dataclass
 class MockedCollection:
-    dataset: TimeseriesDataset
+    dataset: DatasetClient
     dataset_info: Dataset
-    collection: TimeseriesCollection
+    collection: CollectionClient
     collection_info: CollectionInfo
     service: MagicMock
 
@@ -312,31 +312,31 @@ def __init__(self) -> None:
         self.dataset_client = dataset_client
         self.count_collections = 0
 
-    inserted_collections: Bundle[TimeseriesCollection] = Bundle("collections")
+    inserted_collections: Bundle[CollectionClient] = Bundle("collections")
 
     @rule(target=inserted_collections, collection=collection_infos())
-    def get_or_create_collection_enfore_create(self, collection: CollectionInfo) -> TimeseriesCollection:
+    def get_or_create_collection_enfore_create(self, collection: CollectionInfo) -> CollectionClient:
         collections = self.dataset_client.collections()
         assume(collection.collection.name not in collections)
 
         self.count_collections += 1
         return self.dataset_client.get_or_create_collection(collection.collection.name)
 
     @rule(collection=inserted_collections)
-    def get_or_create_collection_enfore_get(self, collection: TimeseriesCollection) -> None:
+    def get_or_create_collection_enfore_get(self, collection: CollectionClient) -> None:
         got = self.dataset_client.get_or_create_collection(collection.name)
         assert got.info() == collection.info()
 
     @rule(target=inserted_collections, collection=collection_infos())
-    def create_collection(self, collection: CollectionInfo) -> TimeseriesCollection:
+    def create_collection(self, collection: CollectionInfo) -> CollectionClient:
         collections = self.dataset_client.collections()
         assume(collection.collection.name not in collections)
 
         self.count_collections += 1
         return self.dataset_client.create_collection(collection.collection.name)
 
     @rule(collection=inserted_collections)
-    def get_collection(self, collection: TimeseriesCollection) -> None:
+    def get_collection(self, collection: CollectionClient) -> None:
         got = self.dataset_client.collection(collection.name)
         assert got.info() == collection.info()
 

tilebox-datasets/tilebox/datasets/__init__.py

@@ -3,10 +3,12 @@
 
 from loguru import logger
 
+# only here for backwards compatibility, to preserve backwards compatibility with older imports
+from tilebox.datasets.aio.timeseries import TimeseriesCollection, TimeseriesDataset
 from tilebox.datasets.sync.client import Client
-from tilebox.datasets.sync.timeseries import TimeseriesCollection, TimeseriesDataset
+from tilebox.datasets.sync.dataset import CollectionClient, DatasetClient
 
-__all__ = ["Client", "TimeseriesCollection", "TimeseriesDataset"]
+__all__ = ["Client", "CollectionClient", "DatasetClient", "TimeseriesCollection", "TimeseriesDataset"]
 
 
 def _init_logging(level: str = "INFO") -> None:

tilebox-datasets/tilebox/datasets/aio/__init__.py

@@ -1,4 +1,7 @@
 from tilebox.datasets.aio.client import Client
+from tilebox.datasets.aio.dataset import CollectionClient, DatasetClient
+
+# only here for backwards compatibility, to preserve backwards compatibility with older imports
 from tilebox.datasets.aio.timeseries import TimeseriesCollection, TimeseriesDataset
 
-__all__ = ["Client", "TimeseriesCollection", "TimeseriesDataset"]
+__all__ = ["Client", "CollectionClient", "DatasetClient", "TimeseriesCollection", "TimeseriesDataset"]

tilebox-datasets/tilebox/datasets/aio/client.py

@@ -2,7 +2,7 @@
 
 from _tilebox.grpc.aio.channel import open_channel
 from _tilebox.grpc.aio.error import with_pythonic_errors
-from tilebox.datasets.aio.timeseries import TimeseriesDataset
+from tilebox.datasets.aio.dataset import DatasetClient
 from tilebox.datasets.client import Client as BaseClient
 from tilebox.datasets.client import token_from_env
 from tilebox.datasets.datasetsv1.collections_pb2_grpc import CollectionServiceStub
@@ -33,10 +33,10 @@ def __init__(self, *, url: str = "https://api.tilebox.com", token: str | None =
         self._client = BaseClient(service)
 
     async def datasets(self) -> Group:
-        return await self._client.datasets(TimeseriesDataset)
+        return await self._client.datasets(DatasetClient)
 
-    async def dataset(self, slug: str) -> TimeseriesDataset:
-        return await self._client.dataset(slug, TimeseriesDataset)
+    async def dataset(self, slug: str) -> DatasetClient:
+        return await self._client.dataset(slug, DatasetClient)
 
-    async def _dataset_by_id(self, dataset_id: str | UUID) -> TimeseriesDataset:
-        return await self._client._dataset_by_id(dataset_id, TimeseriesDataset)  # noqa: SLF001
+    async def _dataset_by_id(self, dataset_id: str | UUID) -> DatasetClient:
+        return await self._client._dataset_by_id(dataset_id, DatasetClient)  # noqa: SLF001