lsst-daf-butler 30.0.0rc2__py3-none-any.whl → 30.0.0rc3__py3-none-any.whl

lsst/daf/butler/direct_butler/_direct_butler.py

@@ -1822,12 +1822,25 @@ class DirectButler(Butler):  # numpydoc ignore=PR02
                     f" Example: {existing_datasets[0]}"
                 )
 
+        # Calculate some statistics based on the given list of datasets.
+        n_files = len(datasets)
+        n_datasets = 0
+        for d in datasets:
+            n_datasets += len(d.refs)
+        sfiles = "s" if n_files != 1 else ""
+        srefs = "s" if n_datasets != 1 else ""
+
         # We use `datasets` rather `new_datasets` for the Registry
         # portion of this, to let it confirm that everything matches the
         # existing datasets.
         import_info = self._prepare_ingest_file_datasets(datasets, progress)
 
-        with self.transaction():
+        with (
+            self._metrics.instrument_ingest(
+                n_datasets, _LOG, msg=f"Ingesting {n_files} file{sfiles} with {n_datasets} dataset{srefs}"
+            ),
+            self.transaction(),
+        ):
             self._ingest_file_datasets(datasets, import_info, progress)
 
             # Bulk-insert everything into Datastore.
@@ -1982,7 +1995,7 @@ class DirectButler(Butler):  # numpydoc ignore=PR02
             doImport(filename)  # type: ignore
 
     def transfer_dimension_records_from(
-        self, source_butler: LimitedButler | Butler, source_refs: Iterable[DatasetRef]
+        self, source_butler: LimitedButler | Butler, source_refs: Iterable[DatasetRef | DataCoordinate]
     ) -> None:
         # Allowed dimensions in the target butler.
         elements = frozenset(element for element in self.dimensions.elements if element.has_own_table)
@@ -2012,16 +2025,13 @@ class DirectButler(Butler):  # numpydoc ignore=PR02
             source_butler, data_ids, allowed_elements
         )
 
-        can_query = True if isinstance(source_butler, Butler) else False
-
         additional_records: dict[DimensionElement, dict[DataCoordinate, DimensionRecord]] = defaultdict(dict)
         for original_element, record_mapping in primary_records.items():
             # Get dimensions that depend on this dimension.
             populated_by = self.dimensions.get_elements_populated_by(
                 self.dimensions[original_element.name]  # type: ignore
             )
-
-            for data_id in record_mapping.keys():
+            if populated_by:
                 for element in populated_by:
                     if element not in allowed_elements:
                         continue
@@ -2040,28 +2050,32 @@ class DirectButler(Butler):  # numpydoc ignore=PR02
                         # have to be scanned.
                         continue
 
-                    if not can_query:
-                        raise RuntimeError(
-                            f"Transferring populated_by records like {element.name} requires a full Butler."
-                        )
+                    if record_mapping:
+                        if not isinstance(source_butler, Butler):
+                            raise RuntimeError(
+                                f"Transferring populated_by records like {element.name}"
+                                " requires a full Butler."
+                            )
 
-                    records = source_butler.query_dimension_records(  # type: ignore
-                        element.name,
-                        explain=False,
-                        **data_id.mapping,  # type: ignore
-                    )
-                    for record in records:
-                        additional_records[record.definition].setdefault(record.dataId, record)
+                        with source_butler.query() as query:
+                            records = query.join_data_coordinates(record_mapping.keys()).dimension_records(
+                                element.name
+                            )
+                            for record in records:
+                                additional_records[record.definition].setdefault(record.dataId, record)
 
         # The next step is to walk back through the additional records to
         # pick up any missing content (such as visit_definition needing to
         # know the exposure). Want to ensure we do not request records we
         # already have.
         missing_data_ids = set()
-        for name, record_mapping in additional_records.items():
+        for record_mapping in additional_records.values():
             for data_id in record_mapping.keys():
-                if data_id not in primary_records[name]:
-                    missing_data_ids.add(data_id)
+                for dimension in data_id.dimensions.required:
+                    element = source_butler.dimensions[dimension]
+                    dimension_key = data_id.subset(dimension)
+                    if dimension_key not in primary_records[element]:
+                        missing_data_ids.add(dimension_key)
 
         # Fill out the new records. Assume that these new records do not
         # also need to carry over additional populated_by records.
@@ -2078,19 +2092,19 @@ class DirectButler(Butler):  # numpydoc ignore=PR02
     def _extract_dimension_records_from_data_ids(
         self,
         source_butler: LimitedButler | Butler,
-        data_ids: set[DataCoordinate],
+        data_ids: Iterable[DataCoordinate],
         allowed_elements: frozenset[DimensionElement],
     ) -> dict[DimensionElement, dict[DataCoordinate, DimensionRecord]]:
         dimension_records: dict[DimensionElement, dict[DataCoordinate, DimensionRecord]] = defaultdict(dict)
 
+        data_ids = set(data_ids)
+        if not all(data_id.hasRecords() for data_id in data_ids):
+            if isinstance(source_butler, Butler):
+                data_ids = source_butler._expand_data_ids(data_ids)
+            else:
+                raise TypeError("Input butler needs to be a full butler to expand DataId.")
+
         for data_id in data_ids:
-            # Need an expanded record, if not expanded that we need a full
-            # butler with registry (allow mocks with registry too).
-            if not data_id.hasRecords():
-                if registry := getattr(source_butler, "registry", None):
-                    data_id = registry.expandDataId(data_id)
-                else:
-                    raise TypeError("Input butler needs to be a full butler to expand DataId.")
             # If this butler doesn't know about a dimension in the source
             # butler things will break later.
             for element_name in data_id.dimensions.elements:
@@ -2569,6 +2583,9 @@ class DirectButler(Butler):  # numpydoc ignore=PR02
         """Immediately load caches that are used for common operations."""
         self._registry.preload_cache(load_dimension_record_cache=load_dimension_record_cache)
 
+    def _expand_data_ids(self, data_ids: Iterable[DataCoordinate]) -> list[DataCoordinate]:
+        return self._registry.expand_data_ids(data_ids)
+
     _config: ButlerConfig
     """Configuration for this Butler instance."""
 

lsst/daf/butler/logging.py

@@ -764,11 +764,17 @@ class ButlerLogRecords(MutableSequence[ButlerLogRecord]):
 
 
 class ButlerLogRecordHandler(StreamHandler):
-    """Python log handler that accumulates records."""
+    """Python log handler that accumulates records.
 
-    def __init__(self) -> None:
+    Parameters
+    ----------
+    records : `ButlerLogRecords`, optional
+        Container to store logs in.
+    """
+
+    def __init__(self, records: ButlerLogRecords | None = None) -> None:
         super().__init__()
-        self.records = ButlerLogRecords([])
+        self.records = ButlerLogRecords([]) if records is None else records
 
     def emit(self, record: LogRecord) -> None:
         self.records.append(record)

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/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/registry/expand_data_ids.py

@@ -0,0 +1,93 @@
+# 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
+
+from collections import defaultdict
+from collections.abc import Iterable
+
+from ..dimensions import (
+    DataCoordinate,
+    DimensionDataAttacher,
+    DimensionGroup,
+    DimensionUniverse,
+)
+from ..dimensions.record_cache import DimensionRecordCache
+from ..queries import QueryFactoryFunction
+
+
+def expand_data_ids(
+    data_ids: Iterable[DataCoordinate],
+    universe: DimensionUniverse,
+    query_func: QueryFactoryFunction,
+    cache: DimensionRecordCache | None,
+) -> list[DataCoordinate]:
+    """Expand the given data IDs to look up implied dimension values and attach
+    dimension records.
+
+    Parameters
+    ----------
+    data_ids : `~collections.abc.Iterable` [ `DataCoordinate` ]
+        Data coordinates to be expanded.
+    universe : `DimensionUniverse`
+        Dimension universe associated with the given ``data_ids`` values.
+    query_func : QueryFactoryFunction
+        Function used to set up a Butler query context for looking up required
+        information from the database.
+    cache : `DimensionRecordCache` | None
+        Cache containing already-known dimension records.  May be `None` if a
+        cache is not available.
+
+    Returns
+    -------
+    expanded : `list` [ `DataCoordinate` ]
+        List of `DataCoordinate` instances in the same order as the input
+        values.  It is guaranteed that each `DataCoordinate` has
+        ``hasRecords()=True`` and ``hasFull()=True``.
+    """
+    output = list(data_ids)
+
+    grouped_by_dimensions: defaultdict[DimensionGroup, list[int]] = defaultdict(list)
+    for i, data_id in enumerate(data_ids):
+        if not data_id.hasRecords():
+            grouped_by_dimensions[data_id.dimensions].append(i)
+
+    if not grouped_by_dimensions:
+        # All given DataCoordinate values are already expanded.
+        return output
+
+    attacher = DimensionDataAttacher(
+        cache=cache,
+        dimensions=DimensionGroup.union(*grouped_by_dimensions.keys(), universe=universe),
+    )
+    for dimensions, indexes in grouped_by_dimensions.items():
+        with query_func() as query:
+            expanded = attacher.attach(dimensions, (output[index] for index in indexes), query)
+            for index, data_id in zip(indexes, expanded):
+                output[index] = data_id
+
+    return output

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/registry/sql_registry.py

@@ -34,7 +34,6 @@ __all__ = ("SqlRegistry",)
 import contextlib
 import logging
 import warnings
-from collections import defaultdict
 from collections.abc import Iterable, Iterator, Mapping, Sequence
 from typing import TYPE_CHECKING, Any
 
@@ -54,7 +53,6 @@ from ..dimensions import (
     DataCoordinate,
     DataId,
     DimensionConfig,
-    DimensionDataAttacher,
     DimensionElement,
     DimensionGroup,
     DimensionRecord,
@@ -78,6 +76,7 @@ from ..registry.interfaces import ChainedCollectionRecord, ReadOnlyDatabaseError
 from ..registry.managers import RegistryManagerInstances, RegistryManagerTypes
 from ..registry.wildcards import CollectionWildcard, DatasetTypeWildcard
 from ..utils import transactional
+from .expand_data_ids import expand_data_ids
 
 if TYPE_CHECKING:
     from .._butler_config import ButlerConfig
@@ -1415,28 +1414,7 @@ class SqlRegistry:
         return DataCoordinate.standardize(keys, dimensions=standardized.dimensions).expanded(records=records)
 
     def expand_data_ids(self, data_ids: Iterable[DataCoordinate]) -> list[DataCoordinate]:
-        output = list(data_ids)
-
-        grouped_by_dimensions: defaultdict[DimensionGroup, list[int]] = defaultdict(list)
-        for i, data_id in enumerate(data_ids):
-            if not data_id.hasRecords():
-                grouped_by_dimensions[data_id.dimensions].append(i)
-
-        if not grouped_by_dimensions:
-            # All given DataCoordinate values are already expanded.
-            return output
-
-        attacher = DimensionDataAttacher(
-            cache=self.dimension_record_cache,
-            dimensions=DimensionGroup.union(*grouped_by_dimensions.keys(), universe=self.dimensions),
-        )
-        with self._query() as query:
-            for dimensions, indexes in grouped_by_dimensions.items():
-                expanded = attacher.attach(dimensions, (output[index] for index in indexes), query)
-                for index, data_id in zip(indexes, expanded):
-                    output[index] = data_id
-
-        return output
+        return expand_data_ids(data_ids, self.dimensions, self._query, self.dimension_record_cache)
 
     def expand_refs(self, dataset_refs: list[DatasetRef]) -> list[DatasetRef]:
         expanded_ids = self.expand_data_ids([ref.dataId for ref in dataset_refs])

lsst/daf/butler/remote_butler/_remote_butler.py

@@ -65,6 +65,7 @@ from ..dimensions import DataCoordinate, DataIdValue, DimensionConfig, Dimension
 from ..queries import Query
 from ..queries.tree import make_column_literal
 from ..registry import CollectionArgType, NoDefaultCollectionError, Registry, RegistryDefaults
+from ..registry.expand_data_ids import expand_data_ids
 from ._collection_args import convert_collection_arg_to_glob_string_list
 from ._defaults import DefaultsHolder
 from ._get import convert_http_url_to_resource_path, get_dataset_as_python_object
@@ -633,7 +634,7 @@ class RemoteButler(Butler):  # numpydoc ignore=PR02
         raise NotImplementedError()
 
     def transfer_dimension_records_from(
-        self, source_butler: LimitedButler | Butler, source_refs: Iterable[DatasetRef]
+        self, source_butler: LimitedButler | Butler, source_refs: Iterable[DatasetRef | DataCoordinate]
     ) -> None:
         # Docstring inherited.
         raise NotImplementedError()
@@ -738,6 +739,9 @@ class RemoteButler(Butler):  # numpydoc ignore=PR02
     def close(self) -> None:
         pass
 
+    def _expand_data_ids(self, data_ids: Iterable[DataCoordinate]) -> list[DataCoordinate]:
+        return expand_data_ids(data_ids, self.dimensions, self.query, None)
+
     @property
     def _file_transfer_source(self) -> RemoteFileTransferSource:
         return RemoteFileTransferSource(self._connection)

lsst/daf/butler/tests/hybrid_butler.py

@@ -338,7 +338,7 @@ class HybridButler(Butler):
         )
 
     def transfer_dimension_records_from(
-        self, source_butler: LimitedButler | Butler, source_refs: Iterable[DatasetRef]
+        self, source_butler: LimitedButler | Butler, source_refs: Iterable[DatasetRef | DataCoordinate]
     ) -> None:
         return self._direct_butler.transfer_dimension_records_from(source_butler, source_refs)
 
@@ -425,6 +425,9 @@ class HybridButler(Butler):
             source_butler, data_ids, allowed_elements
         )
 
+    def _expand_data_ids(self, data_ids: Iterable[DataCoordinate]) -> list[DataCoordinate]:
+        return self._remote_butler._expand_data_ids(data_ids)
+
     @property
     def collection_chains(self) -> ButlerCollections:
         return HybridButlerCollections(self)