Dataset untag (#323)

Adds the dataset untag functionality. Introduces two endpoints:

- `POST /datasets/untag` which mimicks the I/O of the PHP API (modulo
error handling)
 - `DEL /datasets/{id}/tag?tag=...` which is more semantically correct.

Author: PGijsbers

pyproject.toml

@@ -6,7 +6,7 @@ authors = [
 ]
 description = "The Python-based REST API for OpenML."
 readme = "README.md"
-requires-python = ">=3.12"
+requires-python = ">=3.14"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",

src/core/access.py

@@ -1,10 +1,11 @@
-from typing import Any
-
-from sqlalchemy.engine import Row
+from typing import TYPE_CHECKING, Any
 
 from database.users import User
 from schemas.datasets.openml import Visibility
 
+if TYPE_CHECKING:
+    from sqlalchemy.engine import Row
+
 
 async def _user_has_access(
     dataset: Row[Any],

src/core/errors.py

@@ -5,11 +5,14 @@
 """
 
 from http import HTTPStatus
+from typing import TYPE_CHECKING
 
-from fastapi import Request
-from fastapi.exceptions import RequestValidationError
 from fastapi.responses import JSONResponse
 
+if TYPE_CHECKING:
+    from fastapi import Request
+    from fastapi.exceptions import RequestValidationError
+
 # =============================================================================
 # Base Exception
 # =============================================================================

src/core/formatting.py

@@ -1,10 +1,12 @@
 import html
-
-from sqlalchemy.engine import Row
+from typing import TYPE_CHECKING
 
 from config import load_routing_configuration
 from schemas.datasets.openml import DatasetFileFormat
 
+if TYPE_CHECKING:
+    from sqlalchemy.engine import Row
+
 
 def _str_to_bool(string: str) -> bool:
     if string.casefold() in ["true", "1", "yes", "y"]:

src/core/logging.py

@@ -5,13 +5,16 @@
 import uuid
 from collections.abc import Awaitable, Callable
 from pathlib import Path
+from typing import TYPE_CHECKING
 
 from loguru import logger
-from starlette.requests import Request
-from starlette.responses import Response
 
 from config import load_configuration
 
+if TYPE_CHECKING:
+    from starlette.requests import Request
+    from starlette.responses import Response
+
 
 def setup_log_sinks(configuration_file: Path | None = None) -> None:
     """Configure loguru based on app configuration."""

src/database/datasets.py

@@ -2,11 +2,10 @@
 
 import datetime
 from collections import defaultdict
+from typing import TYPE_CHECKING
 
 from sqlalchemy import text
-from sqlalchemy.engine import Row
 from sqlalchemy.exc import IntegrityError
-from sqlalchemy.ext.asyncio import AsyncConnection
 
 from database.exceptions import (
     _DUPLICATE_ENTRY,
@@ -16,6 +15,10 @@
 )
 from schemas.datasets.openml import Feature
 
+if TYPE_CHECKING:
+    from sqlalchemy.engine import Row
+    from sqlalchemy.ext.asyncio import AsyncConnection
+
 
 async def get(id_: int, connection: AsyncConnection) -> Row | None:
     row = await connection.execute(
@@ -45,6 +48,33 @@ async def get_file(*, file_id: int, connection: AsyncConnection) -> Row | None:
     return row.one_or_none()
 
 
+async def get_tag(dataset_id: int, tag: str, connection: AsyncConnection) -> Row | None:
+    return (
+        await connection.execute(
+            text(
+                """
+    SELECT *
+    FROM dataset_tag
+    WHERE id = :dataset_id AND tag = :tag
+    """,
+            ),
+            parameters={"dataset_id": dataset_id, "tag": tag},
+        )
+    ).first()
+
+
+async def delete_tag(dataset_id: int, tag: str, connection: AsyncConnection) -> None:
+    await connection.execute(
+        text(
+            """
+    DELETE FROM dataset_tag
+    WHERE id = :dataset_id AND tag = :tag
+    """,
+        ),
+        parameters={"dataset_id": dataset_id, "tag": tag},
+    )
+
+
 async def get_tags_for(id_: int, connection: AsyncConnection) -> list[str]:
     row = await connection.execute(
         text(

src/database/evaluations.py

@@ -1,12 +1,14 @@
 from collections.abc import Sequence
-from typing import cast
+from typing import TYPE_CHECKING, cast
 
 from sqlalchemy import Row, text
-from sqlalchemy.ext.asyncio import AsyncConnection
 
 from core.formatting import _str_to_bool
 from schemas.datasets.openml import EstimationProcedure
 
+if TYPE_CHECKING:
+    from sqlalchemy.ext.asyncio import AsyncConnection
+
 
 async def get_math_functions(function_type: str, connection: AsyncConnection) -> Sequence[Row]:
     rows = await connection.execute(

src/database/flows.py

@@ -1,8 +1,10 @@
 from collections.abc import Sequence
-from typing import cast
+from typing import TYPE_CHECKING, cast
 
 from sqlalchemy import Row, text
-from sqlalchemy.ext.asyncio import AsyncConnection
+
+if TYPE_CHECKING:
+    from sqlalchemy.ext.asyncio import AsyncConnection
 
 
 async def get_subflows(for_flow: int, expdb: AsyncConnection) -> Sequence[Row]:

src/database/qualities.py

@@ -1,11 +1,14 @@
 from collections import defaultdict
 from collections.abc import Iterable
+from typing import TYPE_CHECKING
 
 from sqlalchemy import text
-from sqlalchemy.ext.asyncio import AsyncConnection
 
 from schemas.datasets.openml import Quality
 
+if TYPE_CHECKING:
+    from sqlalchemy.ext.asyncio import AsyncConnection
+
 
 async def get_for_dataset(dataset_id: int, connection: AsyncConnection) -> list[Quality]:
     row = await connection.execute(

src/database/runs.py

@@ -1,10 +1,12 @@
 """Database queries for run-related data."""
 
 from collections.abc import Sequence
-from typing import cast
+from typing import TYPE_CHECKING, cast
 
 from sqlalchemy import Row, text
-from sqlalchemy.ext.asyncio import AsyncConnection
+
+if TYPE_CHECKING:
+    from sqlalchemy.ext.asyncio import AsyncConnection
 
 
 async def exist(id_: int, expdb: AsyncConnection) -> bool: