lsst-daf-butler 30.2025.5000__tar.gz → 30.2025.5200__tar.gz

{lsst_daf_butler-30.2025.5000/python/lsst_daf_butler.egg-info → lsst_daf_butler-30.2025.5200}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lsst-daf-butler
-Version: 30.2025.5000
+Version: 30.2025.5200
 Summary: An abstraction layer for reading and writing astronomical data to datastores.
 Author-email: Rubin Observatory Data Management <dm-admin@lists.lsst.org>
 License-Expression: BSD-3-Clause OR GPL-3.0-or-later

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/python/lsst/daf/butler/_formatter.py

@@ -54,6 +54,7 @@ from ._config import Config
 from ._config_support import LookupKey, processLookupConfigs
 from ._file_descriptor import FileDescriptor
 from ._location import Location
+from ._rubin.temporary_for_ingest import TemporaryForIngest
 from .dimensions import DataCoordinate, DimensionUniverse
 from .mapping_factory import MappingFactory
 
@@ -1031,15 +1032,7 @@ class FormatterV2:
         """
         cache_manager = self._ensure_cache(cache_manager)
 
-        # Always write to a temporary even if
-        # using a local file system -- that gives us atomic writes.
-        # If a process is killed as the file is being written we do not
-        # want it to remain in the correct place but in corrupt state.
-        # For local files write to the output directory not temporary dir.
-        prefix = uri.dirname() if uri.isLocal else None
-        if prefix is not None:
-            prefix.mkdir()
-        with ResourcePath.temporary_uri(suffix=uri.getExtension(), prefix=prefix) as temporary_uri:
+        with TemporaryForIngest.make_path(uri) as temporary_uri:
             # Need to configure the formatter to write to a different
             # location and that needs us to overwrite internals
             log.debug("Writing dataset to temporary location at %s", temporary_uri)

lsst_daf_butler-30.2025.5200/python/lsst/daf/butler/_rubin/temporary_for_ingest.py

@@ -0,0 +1,207 @@
+# This file is part of daf_butler.
+#
+# Developed for the LSST Data Management System.
+# This product includes software developed by the LSST Project
+# (http://www.lsst.org).
+# See the COPYRIGHT file at the top-level directory of this distribution
+# for details of code ownership.
+#
+# This software is dual licensed under the GNU General Public License and also
+# under a 3-clause BSD license. Recipients may choose which of these licenses
+# to use; please see the files gpl-3.0.txt and/or bsd_license.txt,
+# respectively.  If you choose the GPL option then the following text applies
+# (but note that there is still no warranty even if you opt for BSD instead):
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+from __future__ import annotations
+
+__all__ = ("TemporaryForIngest",)
+
+import dataclasses
+import glob
+from contextlib import contextmanager
+from typing import TYPE_CHECKING, Self, cast
+
+from lsst.resources import ResourcePath
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+    from types import TracebackType
+
+    from .._butler import Butler
+    from .._dataset_ref import DatasetRef
+    from .._file_dataset import FileDataset
+    from .._limited_butler import LimitedButler
+
+
+@dataclasses.dataclass
+class TemporaryForIngest:
+    """A context manager for generating temporary paths that will be ingested
+    as butler datasets.
+
+    Notes
+    -----
+    Neither this class nor its `make_path` method run ingest automatically when
+    their context manager is exited; the `ingest` method must always be called
+    explicitly.
+    """
+
+    butler: Butler
+    """Full butler to obtain a predicted path from and ingest into."""
+
+    ref: DatasetRef
+    """Description of the dataset to ingest."""
+
+    dataset: FileDataset = dataclasses.field(init=False)
+    """The dataset that will be passed to `Butler.ingest`."""
+
+    @property
+    def path(self) -> ResourcePath:
+        """The temporary path.
+
+        Guaranteed to be a local POSIX path.
+        """
+        return cast(ResourcePath, self.dataset.path)
+
+    @property
+    def ospath(self) -> str:
+        """The temporary path as a complete filename."""
+        return self.path.ospath
+
+    @classmethod
+    @contextmanager
+    def make_path(cls, final_path: ResourcePath) -> Iterator[ResourcePath]:
+        """Return a temporary path context manager given the predicted final
+        path.
+
+        Parameters
+        ----------
+        final_path : `lsst.resources.ResourcePath`
+            Predicted final path.
+
+        Returns
+        -------
+        context : `contextlib.AbstractContextManager`
+            A context manager that yields the temporary
+            `~lsst.resources.ResourcePath` when entered and deletes that file
+            when exited.
+        """
+        # Always write to a temporary even if using a local file system -- that
+        # gives us atomic writes. If a process is killed as the file is being
+        # written we do not want it to remain in the correct place but in
+        # corrupt state. For local files write to the output directory not
+        # temporary dir.
+        prefix = final_path.dirname() if final_path.isLocal else None
+        if prefix is not None:
+            prefix.mkdir()
+        with ResourcePath.temporary_uri(
+            suffix=cls._get_temporary_suffix(final_path), prefix=prefix
+        ) as temporary_path:
+            yield temporary_path
+
+    def ingest(self, record_validation_info: bool = True) -> None:
+        """Ingest the file into the butler.
+
+        Parameters
+        ----------
+        record_validation_info : `bool`, optional
+            Whether to- record the file size and checksum upon ingest.
+        """
+        self.butler.ingest(self.dataset, transfer="move", record_validation_info=record_validation_info)
+
+    def __enter__(self) -> Self:
+        from .._file_dataset import FileDataset
+
+        final_path = self.butler.getURI(self.ref, predict=True).replace(fragment="")
+        prefix = final_path.dirname() if final_path.isLocal else None
+        if prefix is not None:
+            prefix.mkdir()
+        self._temporary_path_context = self.make_path(final_path)
+        temporary_path = self._temporary_path_context.__enter__()
+        self.dataset = FileDataset(temporary_path, [self.ref], formatter=None)
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_value: BaseException | None,
+        traceback: TracebackType | None,
+    ) -> bool | None:
+        return self._temporary_path_context.__exit__(exc_type, exc_value, traceback)
+
+    @classmethod
+    def find_orphaned_temporaries_by_path(cls, final_path: ResourcePath) -> list[ResourcePath]:
+        """Search for temporary files that were not successfully ingested.
+
+        Parameters
+        ----------
+        final_path : `lsst.resources.ResourcePath`
+            Final path a successfully-ingested file would have.
+
+        Returns
+        -------
+        paths : `list` [ `lsst.resources.ResourcePath` ]
+            Files that look like temporaries that might have been created while
+            trying to write the target dataset.
+
+        Notes
+        -----
+        Orphaned files are only possible when a context manager is interrupted
+        by a hard error that prevents any cleanup code from running (e.g.
+        sudden loss of power).
+        """
+        if not final_path.isLocal:
+            # We return true tempfile for non-local predicted paths, so orphans
+            # are not our problem (the OS etc. will take care of them).
+            return []
+        return [
+            ResourcePath(filename)
+            for filename in glob.glob(
+                f"{glob.escape(final_path.dirname().ospath)}*{glob.escape(cls._get_temporary_suffix(final_path))}"
+            )
+            if filename != final_path.ospath
+        ]
+
+    @classmethod
+    def find_orphaned_temporaries_by_ref(cls, ref: DatasetRef, butler: LimitedButler) -> list[ResourcePath]:
+        """Search for temporary files that were not successfully ingested.
+
+        Parameters
+        ----------
+        ref : `..DatasetRef`
+            A dataset reference the temporaries correspond to.
+        butler : `lsst.daf.butler.LimitedButler`
+            Butler that can be used to obtain a predicted URI for a dataset.
+
+        Returns
+        -------
+        paths : `list` [ `lsst.resources.ResourcePath` ]
+            Files that look like temporaries that might have been created while
+            trying to write the target dataset.
+
+        Notes
+        -----
+        Orphaned files are only possible when a context manager is interrupted
+        by a hard error that prevents any cleanup code from running (e.g.
+        sudden loss of power).
+        """
+        final_path = butler.getURI(ref, predict=True).replace(fragment="")
+        return cls.find_orphaned_temporaries_by_path(final_path)
+
+    @staticmethod
+    def _get_temporary_suffix(path: ResourcePath) -> str:
+        ext = path.getExtension()
+        basename = path.basename().removesuffix(ext)
+        return f"{basename}.tmp{ext}"

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/python/lsst/daf/butler/datastore/record_data.py

@@ -49,7 +49,7 @@ if TYPE_CHECKING:
 # Pydantic requires the possible value types to be explicitly enumerated in
 # order for `uuid.UUID` in particular to work.  `typing.Any` does not work
 # here.
-_Record: TypeAlias = dict[str, int | str | uuid.UUID | None]
+_Record: TypeAlias = dict[str, int | str | None]
 
 
 class SerializedDatastoreRecordData(pydantic.BaseModel):

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/python/lsst/daf/butler/datastores/fileDatastore.py

@@ -3166,6 +3166,20 @@ class FileDatastore(GenericBaseDatastore[StoredFileInfo]):
 
     def export_records(self, refs: Iterable[DatasetIdRef]) -> Mapping[str, DatastoreRecordData]:
         # Docstring inherited from the base class.
+
+        # This call to 'bridge.check' filters out "partially deleted" datasets.
+        # Specifically, ones in the unusual edge state that:
+        # 1. They have an entry in the registry dataset tables
+        # 2. They were "trashed" from the datastore, so they are not
+        # present in the "dataset_location" table.)
+        # 3. But the trash has not been "emptied", so there are still entries
+        #  in the "opaque" datastore records table.
+        #
+        # As far as I can tell, this can only occur in the case of a concurrent
+        # or aborted call to `Butler.pruneDatasets(unstore=True, purge=False)`.
+        # Datasets (with or without files existing on disk) can persist in
+        # this zombie state indefinitely, until someone manually empties
+        # the trash.
         exported_refs = list(self._bridge.check(refs))
         ids = {ref.id for ref in exported_refs}
         records: dict[DatasetId, dict[str, list[StoredDatastoreItemInfo]]] = {id: {} for id in ids}

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/python/lsst/daf/butler/registry/bridge/monolithic.py

@@ -215,20 +215,24 @@ class MonolithicDatastoreRegistryBridge(DatastoreRegistryBridge):
     def check(self, refs: Iterable[DatasetIdRef]) -> Iterable[DatasetIdRef]:
         # Docstring inherited from DatastoreRegistryBridge
         byId = {ref.id: ref for ref in refs}
-        sql = (
-            sqlalchemy.sql.select(self._tables.dataset_location.columns.dataset_id)
-            .select_from(self._tables.dataset_location)
-            .where(
-                sqlalchemy.sql.and_(
-                    self._tables.dataset_location.columns.datastore_name == self.datastoreName,
-                    self._tables.dataset_location.columns.dataset_id.in_(byId.keys()),
+        found: list[DatasetIdRef] = []
+        with self._db.session():
+            for batch in chunk_iterable(byId.keys(), 50000):
+                sql = (
+                    sqlalchemy.sql.select(self._tables.dataset_location.columns.dataset_id)
+                    .select_from(self._tables.dataset_location)
+                    .where(
+                        sqlalchemy.sql.and_(
+                            self._tables.dataset_location.columns.datastore_name == self.datastoreName,
+                            self._tables.dataset_location.columns.dataset_id.in_(batch),
+                        )
+                    )
                 )
-            )
-        )
-        with self._db.query(sql) as sql_result:
-            sql_rows = sql_result.fetchall()
-        for row in sql_rows:
-            yield byId[row.dataset_id]
+                with self._db.query(sql) as sql_result:
+                    sql_ids = sql_result.scalars().all()
+                found.extend(byId[id] for id in sql_ids)
+
+        return found
 
     @contextmanager
     def emptyTrash(

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/python/lsst/daf/butler/registry/datasets/byDimensions/_manager.py

@@ -12,6 +12,8 @@ from typing import TYPE_CHECKING, Any, ClassVar
 import astropy.time
 import sqlalchemy
 
+from lsst.utils.iteration import chunk_iterable
+
 from .... import ddl
 from ...._collection_type import CollectionType
 from ...._dataset_ref import DatasetId, DatasetIdFactory, DatasetIdGenEnum, DatasetRef
@@ -424,17 +426,18 @@ class ByDimensionsDatasetRecordStorageManagerUUID(DatasetRecordStorageManager):
         return result
 
     def get_dataset_refs(self, ids: list[DatasetId]) -> list[DatasetRef]:
-        # Look up the dataset types corresponding to the given Dataset IDs.
-        id_col = self._static.dataset.columns["id"]
-        sql = sqlalchemy.sql.select(
-            id_col,
-            self._static.dataset.columns["dataset_type_id"],
-        ).where(id_col.in_(ids))
-        with self._db.query(sql) as sql_result:
-            dataset_rows = sql_result.mappings().all()
-        dataset_type_map: dict[DatasetId, DatasetType] = {
-            row["id"]: self._get_dataset_type_by_id(row["dataset_type_id"]) for row in dataset_rows
-        }
+        dataset_type_map: dict[DatasetId, DatasetType] = {}
+        for batch in chunk_iterable(set(ids), 50000):
+            # Look up the dataset types corresponding to the given Dataset IDs.
+            id_col = self._static.dataset.columns["id"]
+            sql = sqlalchemy.sql.select(
+                id_col,
+                self._static.dataset.columns["dataset_type_id"],
+            ).where(id_col.in_(batch))
+            with self._db.query(sql) as sql_result:
+                dataset_rows = sql_result.mappings().all()
+            for row in dataset_rows:
+                dataset_type_map[row["id"]] = self._get_dataset_type_by_id(row["dataset_type_id"])
 
         # Group the given dataset IDs by the DimensionGroup of their dataset
         # types -- there is a separate tags table for each DimensionGroup.
@@ -448,40 +451,41 @@ class ByDimensionsDatasetRecordStorageManagerUUID(DatasetRecordStorageManager):
             # data IDs corresponding to the UUIDs found from the dataset table.
             dynamic_tables = self._get_dynamic_tables(dimension_group)
             tags_table = self._get_tags_table(dynamic_tables)
-            tags_sql = tags_table.select().where(tags_table.columns["dataset_id"].in_(datasets))
-            # Join in the collection table to fetch the run name.
-            collection_column = tags_table.columns[self._collections.getCollectionForeignKeyName()]
-            joined_collections = self._collections.join_collections_sql(collection_column, tags_sql)
-            tags_sql = joined_collections.joined_sql
-            run_name_column = joined_collections.name_column
-            tags_sql = tags_sql.add_columns(run_name_column)
-            # Tags table includes run collections and tagged
-            # collections.
-            # In theory the data ID for a given dataset should be the
-            # same in both, but nothing actually guarantees this.
-            # So skip any tagged collections, using the run collection
-            # as the definitive definition.
-            tags_sql = tags_sql.where(joined_collections.type_column == int(CollectionType.RUN))
-
-            with self._db.query(tags_sql) as sql_result:
-                data_id_rows = sql_result.mappings().all()
-
-            assert run_name_column.key is not None
-            for data_id_row in data_id_rows:
-                id = data_id_row["dataset_id"]
-                dataset_type = dataset_type_map[id]
-                run_name = data_id_row[run_name_column.key]
-                data_id = DataCoordinate.from_required_values(
-                    dimension_group,
-                    tuple(data_id_row[dimension] for dimension in dimension_group.required),
-                )
-                ref = DatasetRef(
-                    datasetType=dataset_type,
-                    dataId=data_id,
-                    id=id,
-                    run=run_name,
-                )
-                output_refs.append(ref)
+            for batch in chunk_iterable(datasets, 50000):
+                tags_sql = tags_table.select().where(tags_table.columns["dataset_id"].in_(batch))
+                # Join in the collection table to fetch the run name.
+                collection_column = tags_table.columns[self._collections.getCollectionForeignKeyName()]
+                joined_collections = self._collections.join_collections_sql(collection_column, tags_sql)
+                tags_sql = joined_collections.joined_sql
+                run_name_column = joined_collections.name_column
+                tags_sql = tags_sql.add_columns(run_name_column)
+                # Tags table includes run collections and tagged
+                # collections.
+                # In theory the data ID for a given dataset should be the
+                # same in both, but nothing actually guarantees this.
+                # So skip any tagged collections, using the run collection
+                # as the definitive definition.
+                tags_sql = tags_sql.where(joined_collections.type_column == int(CollectionType.RUN))
+
+                with self._db.query(tags_sql) as sql_result:
+                    data_id_rows = sql_result.mappings().all()
+
+                assert run_name_column.key is not None
+                for data_id_row in data_id_rows:
+                    id = data_id_row["dataset_id"]
+                    dataset_type = dataset_type_map[id]
+                    run_name = data_id_row[run_name_column.key]
+                    data_id = DataCoordinate.from_required_values(
+                        dimension_group,
+                        tuple(data_id_row[dimension] for dimension in dimension_group.required),
+                    )
+                    ref = DatasetRef(
+                        datasetType=dataset_type,
+                        dataId=data_id,
+                        id=id,
+                        run=run_name,
+                    )
+                    output_refs.append(ref)
 
         return output_refs
 

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/python/lsst/daf/butler/registry/interfaces/_database.py

@@ -1562,7 +1562,12 @@ class Database(ABC):
                 return None
             else:
                 sql = table.insert()
-                return [connection.execute(sql, row).inserted_primary_key[0] for row in rows]
+                ids = []
+                for row in rows:
+                    key = connection.execute(sql, row).inserted_primary_key
+                    assert key is not None
+                    ids.append(key[0])
+                return ids
 
     @abstractmethod
     def replace(self, table: sqlalchemy.schema.Table, *rows: dict) -> None:

lsst_daf_butler-30.2025.5200/python/lsst/daf/butler/version.py

@@ -0,0 +1,2 @@
+__all__ = ["__version__"]
+__version__ = "30.2025.5200"

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200/python/lsst_daf_butler.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lsst-daf-butler
-Version: 30.2025.5000
+Version: 30.2025.5200
 Summary: An abstraction layer for reading and writing astronomical data to datastores.
 Author-email: Rubin Observatory Data Management <dm-admin@lists.lsst.org>
 License-Expression: BSD-3-Clause OR GPL-3.0-or-later

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/python/lsst_daf_butler.egg-info/SOURCES.txt

@@ -73,6 +73,7 @@ python/lsst/daf/butler/utils.py
 python/lsst/daf/butler/version.py
 python/lsst/daf/butler/_rubin/__init__.py
 python/lsst/daf/butler/_rubin/file_datasets.py
+python/lsst/daf/butler/_rubin/temporary_for_ingest.py
 python/lsst/daf/butler/_utilities/__init__.py
 python/lsst/daf/butler/_utilities/locked_object.py
 python/lsst/daf/butler/_utilities/named_locks.py

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/tests/test_butler.py

@@ -90,6 +90,7 @@ from lsst.daf.butler import (
     script,
 )
 from lsst.daf.butler._rubin.file_datasets import transfer_datasets_to_datastore
+from lsst.daf.butler._rubin.temporary_for_ingest import TemporaryForIngest
 from lsst.daf.butler.datastore import NullDatastore
 from lsst.daf.butler.datastore.file_templates import FileTemplate, FileTemplateValidationError
 from lsst.daf.butler.datastores.file_datastore.retrieve_artifacts import ZipIndex
@@ -2441,6 +2442,21 @@ class PosixDatastoreButlerTestCase(FileDatastoreButlerTests, unittest.TestCase):
             self.assertIsNotNone(target_butler.get(repo.ref2))
             self.assertIsNotNone(target_butler.get(other_ref))
 
+    def test_temporary_for_ingest(self) -> None:
+        """Test the `lsst.daf.butler._rubin.ingest_from_temporary` module."""
+        with self.create_empty_butler("example_run") as butler:
+            dataset_type = DatasetType("example", butler.dimensions.empty, "StructuredDataDict")
+            butler.registry.registerDatasetType(dataset_type)
+            ref = DatasetRef(dataset_type, DataCoordinate.make_empty(butler.dimensions), "example_run")
+            with TemporaryForIngest(butler, ref) as temporary:
+                temporary.path.write(b"three: 3")
+                found = TemporaryForIngest.find_orphaned_temporaries_by_ref(ref, butler)
+                self.assertEqual(found, [temporary.path])
+                self.assertIn(".tmp", temporary.ospath)
+                temporary.ingest()
+            loaded = butler.get(ref)
+            self.assertEqual(loaded, {"three": 3})
+
 
 class PostgresPosixDatastoreButlerTestCase(FileDatastoreButlerTests, unittest.TestCase):
     """PosixDatastore specialization of a butler using Postgres"""

{lsst_daf_butler-30.2025.5000 → lsst_daf_butler-30.2025.5200}/tests/test_datastore.py

@@ -61,6 +61,7 @@ from lsst.daf.butler.datastore.cache_manager import (
     DatastoreCacheManagerConfig,
     DatastoreDisabledCacheManager,
 )
+from lsst.daf.butler.datastore.record_data import DatastoreRecordData, SerializedDatastoreRecordData
 from lsst.daf.butler.datastore.stored_file_info import StoredFileInfo, make_datastore_path_relative
 from lsst.daf.butler.formatters.yaml import YamlFormatter
 from lsst.daf.butler.tests import (
@@ -77,6 +78,7 @@ from lsst.daf.butler.tests.dict_convertible_model import DictConvertibleModel
 from lsst.daf.butler.tests.utils import TestCaseMixin
 from lsst.resources import ResourcePath
 from lsst.utils import doImport
+from lsst.utils.introspection import get_full_type_name
 
 TESTDIR = os.path.dirname(__file__)
 
@@ -2252,6 +2254,44 @@ class StoredFileInfoTestCase(DatasetTestHelper, unittest.TestCase):
         self.assertEqual(make_datastore_path_relative("http://server.com/some/path"), "some/path")
         self.assertEqual(make_datastore_path_relative("http://server.com/some/path#frag"), "some/path#frag")
 
+    def test_datastore_record_data_json_types(self):
+        """Test that we don't round-trip checksums to UUIDs when deserializing
+        datastore record data.
+        """
+        test_json = """
+            {
+                "dataset_ids": [
+                    "74478304-abf1-4a9c-9eb2-926090a84446"
+                ],
+                "records": {
+                    "lsst.daf.butler.datastore.stored_file_info.StoredFileInfo": {
+                    "74478304abf14a9c9eb2926090a84446": {
+                        "file_datastore_records": [
+                        {
+                            "formatter": "lsst.daf.butler.formatters.yaml.YamlFormatter",
+                            "path": "gain_factors/base-2025-158/gain_factors_spx_base-2025-158.yaml",
+                            "storage_class": "GainFactors",
+                            "component": "__NULL_STRING__",
+                            "checksum": "cab515f6-ab67-0484-393f-aaa525dd526f",
+                            "file_size": 5412
+                        }
+                        ]
+                    }
+                    }
+                }
+            }
+        """
+        id_str = "74478304abf14a9c9eb2926090a84446"
+        s = SerializedDatastoreRecordData.model_validate_json(test_json)
+        self.assertIsInstance(
+            s.records[get_full_type_name(StoredFileInfo)][id_str]["file_datastore_records"][0]["checksum"],
+            str,
+        )
+        id = uuid.UUID(id_str)
+        d = DatastoreRecordData.from_simple(s)
+        self.assertIsInstance(d.records[id]["file_datastore_records"][0], StoredFileInfo)
+        self.assertIsInstance(d.records[id]["file_datastore_records"][0].checksum, str)
+
 
 @contextlib.contextmanager
 def _temp_yaml_file(data: Any) -> Iterator[str]:

lsst_daf_butler-30.2025.5000/python/lsst/daf/butler/version.py

@@ -1,2 +0,0 @@
-__all__ = ["__version__"]
-__version__ = "30.2025.5000"