Coverage for python/lsst/daf/butler/registry/_registry.py : 12%

Hot-keys on this page
r m x p toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1# This file is part of daf_butler.
2#
3# Developed for the LSST Data Management System.
4# This product includes software developed by the LSST Project
5# (http://www.lsst.org).
6# See the COPYRIGHT file at the top-level directory of this distribution
7# for details of code ownership.
8#
9# This program is free software: you can redistribute it and/or modify
10# it under the terms of the GNU General Public License as published by
11# the Free Software Foundation, either version 3 of the License, or
12# (at your option) any later version.
13#
14# This program is distributed in the hope that it will be useful,
15# but WITHOUT ANY WARRANTY; without even the implied warranty of
16# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17# GNU General Public License for more details.
18#
19# You should have received a copy of the GNU General Public License
20# along with this program. If not, see <http://www.gnu.org/licenses/>.
22from __future__ import annotations
24__all__ = (
25 "Registry",
26)
28from collections import defaultdict
29import contextlib
30import logging
31from typing import (
32 Any,
33 Dict,
34 Iterable,
35 Iterator,
36 List,
37 Mapping,
38 Optional,
39 Set,
40 Type,
41 TYPE_CHECKING,
42 Union,
43)
45import sqlalchemy
47from ..core import (
48 Config,
49 DataCoordinate,
50 DataCoordinateIterable,
51 DataId,
52 DatasetAssociation,
53 DatasetRef,
54 DatasetType,
55 ddl,
56 Dimension,
57 DimensionElement,
58 DimensionGraph,
59 DimensionRecord,
60 DimensionUniverse,
61 NamedKeyMapping,
62 NameLookupMapping,
63 StorageClassFactory,
64 Timespan,
65)
66from . import queries
67from ..core.utils import doImport, iterable, transactional
68from ._config import RegistryConfig
69from ._collectionType import CollectionType
70from ._exceptions import ConflictingDefinitionError, InconsistentDataIdError, OrphanedRecordError
71from .wildcards import CategorizedWildcard, CollectionQuery, CollectionSearch, Ellipsis
72from .interfaces import ChainedCollectionRecord, RunRecord
73from .versions import ButlerVersionsManager, DigestMismatchError
75if TYPE_CHECKING: 75 ↛ 76line 75 didn't jump to line 76, because the condition on line 75 was never true
76 from ..butlerConfig import ButlerConfig
77 from .interfaces import (
78 ButlerAttributeManager,
79 CollectionManager,
80 Database,
81 OpaqueTableStorageManager,
82 DimensionRecordStorageManager,
83 DatasetRecordStorageManager,
84 DatastoreRegistryBridgeManager,
85 )
88_LOG = logging.getLogger(__name__)
91class Registry:
92 """Registry interface.
94 Parameters
95 ----------
96 database : `Database`
97 Database instance to store Registry.
98 universe : `DimensionUniverse`
99 Full set of dimensions for Registry.
100 attributes : `type`
101 Manager class implementing `ButlerAttributeManager`.
102 opaque : `type`
103 Manager class implementing `OpaqueTableStorageManager`.
104 dimensions : `type`
105 Manager class implementing `DimensionRecordStorageManager`.
106 collections : `type`
107 Manager class implementing `CollectionManager`.
108 datasets : `type`
109 Manager class implementing `DatasetRecordStorageManager`.
110 datastoreBridges : `type`
111 Manager class implementing `DatastoreRegistryBridgeManager`.
112 writeable : `bool`, optional
113 If True then Registry will support write operations.
114 create : `bool`, optional
115 If True then database schema will be initialized, it must be empty
116 before instantiating Registry.
117 """
119 defaultConfigFile: Optional[str] = None
120 """Path to configuration defaults. Accessed within the ``configs`` resource
121 or relative to a search path. Can be None if no defaults specified.
122 """
124 @classmethod
125 def fromConfig(cls, config: Union[ButlerConfig, RegistryConfig, Config, str], create: bool = False,
126 butlerRoot: Optional[str] = None, writeable: bool = True) -> Registry:
127 """Create `Registry` subclass instance from `config`.
129 Uses ``registry.cls`` from `config` to determine which subclass to
130 instantiate.
132 Parameters
133 ----------
134 config : `ButlerConfig`, `RegistryConfig`, `Config` or `str`
135 Registry configuration
136 create : `bool`, optional
137 Assume empty Registry and create a new one.
138 butlerRoot : `str`, optional
139 Path to the repository root this `Registry` will manage.
140 writeable : `bool`, optional
141 If `True` (default) create a read-write connection to the database.
143 Returns
144 -------
145 registry : `Registry` (subclass)
146 A new `Registry` subclass instance.
147 """
148 if not isinstance(config, RegistryConfig):
149 if isinstance(config, str) or isinstance(config, Config):
150 config = RegistryConfig(config)
151 else:
152 raise ValueError("Incompatible Registry configuration: {}".format(config))
153 config.replaceRoot(butlerRoot)
154 DatabaseClass = config.getDatabaseClass()
155 database = DatabaseClass.fromUri(str(config.connectionString), origin=config.get("origin", 0),
156 namespace=config.get("namespace"), writeable=writeable)
157 universe = DimensionUniverse(config)
158 attributes = doImport(config["managers", "attributes"])
159 opaque = doImport(config["managers", "opaque"])
160 dimensions = doImport(config["managers", "dimensions"])
161 collections = doImport(config["managers", "collections"])
162 datasets = doImport(config["managers", "datasets"])
163 datastoreBridges = doImport(config["managers", "datastores"])
165 return cls(database, universe, dimensions=dimensions, attributes=attributes, opaque=opaque,
166 collections=collections, datasets=datasets, datastoreBridges=datastoreBridges,
167 writeable=writeable, create=create)
169 def __init__(self, database: Database, universe: DimensionUniverse, *,
170 attributes: Type[ButlerAttributeManager],
171 opaque: Type[OpaqueTableStorageManager],
172 dimensions: Type[DimensionRecordStorageManager],
173 collections: Type[CollectionManager],
174 datasets: Type[DatasetRecordStorageManager],
175 datastoreBridges: Type[DatastoreRegistryBridgeManager],
176 writeable: bool = True,
177 create: bool = False):
178 self._db = database
179 self.storageClasses = StorageClassFactory()
180 with self._db.declareStaticTables(create=create) as context:
181 self._attributes = attributes.initialize(self._db, context)
182 self._dimensions = dimensions.initialize(self._db, context, universe=universe)
183 self._collections = collections.initialize(self._db, context)
184 self._datasets = datasets.initialize(self._db, context,
185 collections=self._collections,
186 universe=self.dimensions)
187 self._opaque = opaque.initialize(self._db, context)
188 self._datastoreBridges = datastoreBridges.initialize(self._db, context,
189 opaque=self._opaque,
190 datasets=datasets,
191 universe=self.dimensions)
192 versions = ButlerVersionsManager(
193 self._attributes,
194 dict(
195 attributes=self._attributes,
196 opaque=self._opaque,
197 dimensions=self._dimensions,
198 collections=self._collections,
199 datasets=self._datasets,
200 datastores=self._datastoreBridges,
201 )
202 )
203 # store managers and their versions in attributes table
204 context.addInitializer(lambda db: versions.storeManagersConfig())
205 context.addInitializer(lambda db: versions.storeManagersVersions())
207 if not create:
208 # verify that configured versions are compatible with schema
209 versions.checkManagersConfig()
210 versions.checkManagersVersions(writeable)
211 try:
212 versions.checkManagersDigests()
213 except DigestMismatchError as exc:
214 # potentially digest mismatch is a serious error but during
215 # development it could be benign, treat this as warning for
216 # now.
217 _LOG.warning(f"Registry schema digest mismatch: {exc}")
219 self._collections.refresh()
220 self._datasets.refresh(universe=self._dimensions.universe)
222 def __str__(self) -> str:
223 return str(self._db)
225 def __repr__(self) -> str:
226 return f"Registry({self._db!r}, {self.dimensions!r})"
228 def isWriteable(self) -> bool:
229 """Return `True` if this registry allows write operations, and `False`
230 otherwise.
231 """
232 return self._db.isWriteable()
234 @property
235 def dimensions(self) -> DimensionUniverse:
236 """All dimensions recognized by this `Registry` (`DimensionUniverse`).
237 """
238 return self._dimensions.universe
240 @contextlib.contextmanager
241 def transaction(self, *, savepoint: bool = False) -> Iterator[None]:
242 """Return a context manager that represents a transaction.
243 """
244 try:
245 with self._db.transaction(savepoint=savepoint):
246 yield
247 except BaseException:
248 # TODO: this clears the caches sometimes when we wouldn't actually
249 # need to. Can we avoid that?
250 self._dimensions.clearCaches()
251 raise
253 def registerOpaqueTable(self, tableName: str, spec: ddl.TableSpec) -> None:
254 """Add an opaque (to the `Registry`) table for use by a `Datastore` or
255 other data repository client.
257 Opaque table records can be added via `insertOpaqueData`, retrieved via
258 `fetchOpaqueData`, and removed via `deleteOpaqueData`.
260 Parameters
261 ----------
262 tableName : `str`
263 Logical name of the opaque table. This may differ from the
264 actual name used in the database by a prefix and/or suffix.
265 spec : `ddl.TableSpec`
266 Specification for the table to be added.
267 """
268 self._opaque.register(tableName, spec)
270 @transactional
271 def insertOpaqueData(self, tableName: str, *data: dict) -> None:
272 """Insert records into an opaque table.
274 Parameters
275 ----------
276 tableName : `str`
277 Logical name of the opaque table. Must match the name used in a
278 previous call to `registerOpaqueTable`.
279 data
280 Each additional positional argument is a dictionary that represents
281 a single row to be added.
282 """
283 self._opaque[tableName].insert(*data)
285 def fetchOpaqueData(self, tableName: str, **where: Any) -> Iterator[dict]:
286 """Retrieve records from an opaque table.
288 Parameters
289 ----------
290 tableName : `str`
291 Logical name of the opaque table. Must match the name used in a
292 previous call to `registerOpaqueTable`.
293 where
294 Additional keyword arguments are interpreted as equality
295 constraints that restrict the returned rows (combined with AND);
296 keyword arguments are column names and values are the values they
297 must have.
299 Yields
300 ------
301 row : `dict`
302 A dictionary representing a single result row.
303 """
304 yield from self._opaque[tableName].fetch(**where)
306 @transactional
307 def deleteOpaqueData(self, tableName: str, **where: Any) -> None:
308 """Remove records from an opaque table.
310 Parameters
311 ----------
312 tableName : `str`
313 Logical name of the opaque table. Must match the name used in a
314 previous call to `registerOpaqueTable`.
315 where
316 Additional keyword arguments are interpreted as equality
317 constraints that restrict the deleted rows (combined with AND);
318 keyword arguments are column names and values are the values they
319 must have.
320 """
321 self._opaque[tableName].delete(**where)
323 def registerCollection(self, name: str, type: CollectionType = CollectionType.TAGGED) -> None:
324 """Add a new collection if one with the given name does not exist.
326 Parameters
327 ----------
328 name : `str`
329 The name of the collection to create.
330 type : `CollectionType`
331 Enum value indicating the type of collection to create.
333 Notes
334 -----
335 This method cannot be called within transactions, as it needs to be
336 able to perform its own transaction to be concurrent.
337 """
338 self._collections.register(name, type)
340 def getCollectionType(self, name: str) -> CollectionType:
341 """Return an enumeration value indicating the type of the given
342 collection.
344 Parameters
345 ----------
346 name : `str`
347 The name of the collection.
349 Returns
350 -------
351 type : `CollectionType`
352 Enum value indicating the type of this collection.
354 Raises
355 ------
356 MissingCollectionError
357 Raised if no collection with the given name exists.
358 """
359 return self._collections.find(name).type
361 def registerRun(self, name: str) -> None:
362 """Add a new run if one with the given name does not exist.
364 Parameters
365 ----------
366 name : `str`
367 The name of the run to create.
369 Notes
370 -----
371 This method cannot be called within transactions, as it needs to be
372 able to perform its own transaction to be concurrent.
373 """
374 self._collections.register(name, CollectionType.RUN)
376 @transactional
377 def removeCollection(self, name: str) -> None:
378 """Completely remove the given collection.
380 Parameters
381 ----------
382 name : `str`
383 The name of the collection to remove.
385 Raises
386 ------
387 MissingCollectionError
388 Raised if no collection with the given name exists.
390 Notes
391 -----
392 If this is a `~CollectionType.RUN` collection, all datasets and quanta
393 in it are also fully removed. This requires that those datasets be
394 removed (or at least trashed) from any datastores that hold them first.
396 A collection may not be deleted as long as it is referenced by a
397 `~CollectionType.CHAINED` collection; the ``CHAINED`` collection must
398 be deleted or redefined first.
399 """
400 self._collections.remove(name)
402 def getCollectionChain(self, parent: str) -> CollectionSearch:
403 """Return the child collections in a `~CollectionType.CHAINED`
404 collection.
406 Parameters
407 ----------
408 parent : `str`
409 Name of the chained collection. Must have already been added via
410 a call to `Registry.registerCollection`.
412 Returns
413 -------
414 children : `CollectionSearch`
415 An object that defines the search path of the collection.
416 See :ref:`daf_butler_collection_expressions` for more information.
418 Raises
419 ------
420 MissingCollectionError
421 Raised if ``parent`` does not exist in the `Registry`.
422 TypeError
423 Raised if ``parent`` does not correspond to a
424 `~CollectionType.CHAINED` collection.
425 """
426 record = self._collections.find(parent)
427 if record.type is not CollectionType.CHAINED:
428 raise TypeError(f"Collection '{parent}' has type {record.type.name}, not CHAINED.")
429 assert isinstance(record, ChainedCollectionRecord)
430 return record.children
432 @transactional
433 def setCollectionChain(self, parent: str, children: Any) -> None:
434 """Define or redefine a `~CollectionType.CHAINED` collection.
436 Parameters
437 ----------
438 parent : `str`
439 Name of the chained collection. Must have already been added via
440 a call to `Registry.registerCollection`.
441 children : `Any`
442 An expression defining an ordered search of child collections,
443 generally an iterable of `str`. Restrictions on the dataset types
444 to be searched can also be included, by passing mapping or an
445 iterable containing tuples; see
446 :ref:`daf_butler_collection_expressions` for more information.
448 Raises
449 ------
450 MissingCollectionError
451 Raised when any of the given collections do not exist in the
452 `Registry`.
453 TypeError
454 Raised if ``parent`` does not correspond to a
455 `~CollectionType.CHAINED` collection.
456 ValueError
457 Raised if the given collections contains a cycle.
458 """
459 record = self._collections.find(parent)
460 if record.type is not CollectionType.CHAINED:
461 raise TypeError(f"Collection '{parent}' has type {record.type.name}, not CHAINED.")
462 assert isinstance(record, ChainedCollectionRecord)
463 children = CollectionSearch.fromExpression(children)
464 if children != record.children:
465 record.update(self._collections, children)
467 def registerDatasetType(self, datasetType: DatasetType) -> bool:
468 """
469 Add a new `DatasetType` to the Registry.
471 It is not an error to register the same `DatasetType` twice.
473 Parameters
474 ----------
475 datasetType : `DatasetType`
476 The `DatasetType` to be added.
478 Returns
479 -------
480 inserted : `bool`
481 `True` if ``datasetType`` was inserted, `False` if an identical
482 existing `DatsetType` was found. Note that in either case the
483 DatasetType is guaranteed to be defined in the Registry
484 consistently with the given definition.
486 Raises
487 ------
488 ValueError
489 Raised if the dimensions or storage class are invalid.
490 ConflictingDefinitionError
491 Raised if this DatasetType is already registered with a different
492 definition.
494 Notes
495 -----
496 This method cannot be called within transactions, as it needs to be
497 able to perform its own transaction to be concurrent.
498 """
499 _, inserted = self._datasets.register(datasetType)
500 return inserted
502 def removeDatasetType(self, name: str) -> None:
503 """Remove the named `DatasetType` from the registry.
505 .. warning::
507 Registry caches the dataset type definitions. This means that
508 deleting the dataset type definition may result in unexpected
509 behavior from other butler processes that are active that have
510 not seen the deletion.
512 Parameters
513 ----------
514 name : `str`
515 Name of the type to be removed.
517 Raises
518 ------
519 lsst.daf.butler.registry.OrphanedRecordError
520 Raised if an attempt is made to remove the dataset type definition
521 when there are already datasets associated with it.
523 Notes
524 -----
525 If the dataset type is not registered the method will return without
526 action.
527 """
528 self._datasets.remove(name, universe=self._dimensions.universe)
530 def getDatasetType(self, name: str) -> DatasetType:
531 """Get the `DatasetType`.
533 Parameters
534 ----------
535 name : `str`
536 Name of the type.
538 Returns
539 -------
540 type : `DatasetType`
541 The `DatasetType` associated with the given name.
543 Raises
544 ------
545 KeyError
546 Requested named DatasetType could not be found in registry.
547 """
548 return self._datasets[name].datasetType
550 def findDataset(self, datasetType: Union[DatasetType, str], dataId: Optional[DataId] = None, *,
551 collections: Any, timespan: Optional[Timespan] = None,
552 **kwargs: Any) -> Optional[DatasetRef]:
553 """Find a dataset given its `DatasetType` and data ID.
555 This can be used to obtain a `DatasetRef` that permits the dataset to
556 be read from a `Datastore`. If the dataset is a component and can not
557 be found using the provided dataset type, a dataset ref for the parent
558 will be returned instead but with the correct dataset type.
560 Parameters
561 ----------
562 datasetType : `DatasetType` or `str`
563 A `DatasetType` or the name of one.
564 dataId : `dict` or `DataCoordinate`, optional
565 A `dict`-like object containing the `Dimension` links that identify
566 the dataset within a collection.
567 collections
568 An expression that fully or partially identifies the collections
569 to search for the dataset, such as a `str`, `DatasetType`, or
570 iterable thereof. See :ref:`daf_butler_collection_expressions`
571 for more information.
572 timespan : `Timespan`, optional
573 A timespan that the validity range of the dataset must overlap.
574 If not provided, any `~CollectionType.CALIBRATION` collections
575 matched by the ``collections`` argument will not be searched.
576 **kwargs
577 Additional keyword arguments passed to
578 `DataCoordinate.standardize` to convert ``dataId`` to a true
579 `DataCoordinate` or augment an existing one.
581 Returns
582 -------
583 ref : `DatasetRef`
584 A reference to the dataset, or `None` if no matching Dataset
585 was found.
587 Raises
588 ------
589 LookupError
590 Raised if one or more data ID keys are missing.
591 KeyError
592 Raised if the dataset type does not exist.
593 MissingCollectionError
594 Raised if any of ``collections`` does not exist in the registry.
596 Notes
597 -----
598 This method simply returns `None` and does not raise an exception even
599 when the set of collections searched is intrinsically incompatible with
600 the dataset type, e.g. if ``datasetType.isCalibration() is False``, but
601 only `~CollectionType.CALIBRATION` collections are being searched.
602 This may make it harder to debug some lookup failures, but the behavior
603 is intentional; we consider it more important that failed searches are
604 reported consistently, regardless of the reason, and that adding
605 additional collections that do not contain a match to the search path
606 never changes the behavior.
607 """
608 if isinstance(datasetType, DatasetType):
609 storage = self._datasets[datasetType.name]
610 else:
611 storage = self._datasets[datasetType]
612 dataId = DataCoordinate.standardize(dataId, graph=storage.datasetType.dimensions,
613 universe=self.dimensions, **kwargs)
614 collections = CollectionSearch.fromExpression(collections)
615 for collectionRecord in collections.iter(self._collections, datasetType=storage.datasetType):
616 if (collectionRecord.type is CollectionType.CALIBRATION
617 and (not storage.datasetType.isCalibration() or timespan is None)):
618 continue
619 result = storage.find(collectionRecord, dataId, timespan=timespan)
620 if result is not None:
621 return result
623 return None
625 @transactional
626 def insertDatasets(self, datasetType: Union[DatasetType, str], dataIds: Iterable[DataId],
627 run: str) -> List[DatasetRef]:
628 """Insert one or more datasets into the `Registry`
630 This always adds new datasets; to associate existing datasets with
631 a new collection, use ``associate``.
633 Parameters
634 ----------
635 datasetType : `DatasetType` or `str`
636 A `DatasetType` or the name of one.
637 dataIds : `~collections.abc.Iterable` of `dict` or `DataCoordinate`
638 Dimension-based identifiers for the new datasets.
639 run : `str`
640 The name of the run that produced the datasets.
642 Returns
643 -------
644 refs : `list` of `DatasetRef`
645 Resolved `DatasetRef` instances for all given data IDs (in the same
646 order).
648 Raises
649 ------
650 ConflictingDefinitionError
651 If a dataset with the same dataset type and data ID as one of those
652 given already exists in ``run``.
653 MissingCollectionError
654 Raised if ``run`` does not exist in the registry.
655 """
656 if isinstance(datasetType, DatasetType):
657 storage = self._datasets.find(datasetType.name)
658 if storage is None:
659 raise LookupError(f"DatasetType '{datasetType}' has not been registered.")
660 else:
661 storage = self._datasets.find(datasetType)
662 if storage is None:
663 raise LookupError(f"DatasetType with name '{datasetType}' has not been registered.")
664 runRecord = self._collections.find(run)
665 if runRecord.type is not CollectionType.RUN:
666 raise TypeError("Given collection is of type {runRecord.type.name}; RUN collection required.")
667 assert isinstance(runRecord, RunRecord)
668 expandedDataIds = [self.expandDataId(dataId, graph=storage.datasetType.dimensions)
669 for dataId in dataIds]
670 try:
671 refs = list(storage.insert(runRecord, expandedDataIds))
672 except sqlalchemy.exc.IntegrityError as err:
673 raise ConflictingDefinitionError(f"A database constraint failure was triggered by inserting "
674 f"one or more datasets of type {storage.datasetType} into "
675 f"collection '{run}'. "
676 f"This probably means a dataset with the same data ID "
677 f"and dataset type already exists, but it may also mean a "
678 f"dimension row is missing.") from err
679 return refs
681 def getDataset(self, id: int) -> Optional[DatasetRef]:
682 """Retrieve a Dataset entry.
684 Parameters
685 ----------
686 id : `int`
687 The unique identifier for the dataset.
689 Returns
690 -------
691 ref : `DatasetRef` or `None`
692 A ref to the Dataset, or `None` if no matching Dataset
693 was found.
694 """
695 ref = self._datasets.getDatasetRef(id, universe=self.dimensions)
696 if ref is None:
697 return None
698 return ref
700 @transactional
701 def removeDatasets(self, refs: Iterable[DatasetRef]) -> None:
702 """Remove datasets from the Registry.
704 The datasets will be removed unconditionally from all collections, and
705 any `Quantum` that consumed this dataset will instead be marked with
706 having a NULL input. `Datastore` records will *not* be deleted; the
707 caller is responsible for ensuring that the dataset has already been
708 removed from all Datastores.
710 Parameters
711 ----------
712 refs : `Iterable` of `DatasetRef`
713 References to the datasets to be removed. Must include a valid
714 ``id`` attribute, and should be considered invalidated upon return.
716 Raises
717 ------
718 AmbiguousDatasetError
719 Raised if any ``ref.id`` is `None`.
720 OrphanedRecordError
721 Raised if any dataset is still present in any `Datastore`.
722 """
723 for datasetType, refsForType in DatasetRef.groupByType(refs).items():
724 storage = self._datasets.find(datasetType.name)
725 assert storage is not None
726 try:
727 storage.delete(refsForType)
728 except sqlalchemy.exc.IntegrityError as err:
729 raise OrphanedRecordError("One or more datasets is still "
730 "present in one or more Datastores.") from err
732 @transactional
733 def associate(self, collection: str, refs: Iterable[DatasetRef]) -> None:
734 """Add existing datasets to a `~CollectionType.TAGGED` collection.
736 If a DatasetRef with the same exact integer ID is already in a
737 collection nothing is changed. If a `DatasetRef` with the same
738 `DatasetType` and data ID but with different integer ID
739 exists in the collection, `ConflictingDefinitionError` is raised.
741 Parameters
742 ----------
743 collection : `str`
744 Indicates the collection the datasets should be associated with.
745 refs : `Iterable` [ `DatasetRef` ]
746 An iterable of resolved `DatasetRef` instances that already exist
747 in this `Registry`.
749 Raises
750 ------
751 ConflictingDefinitionError
752 If a Dataset with the given `DatasetRef` already exists in the
753 given collection.
754 AmbiguousDatasetError
755 Raised if ``any(ref.id is None for ref in refs)``.
756 MissingCollectionError
757 Raised if ``collection`` does not exist in the registry.
758 TypeError
759 Raise adding new datasets to the given ``collection`` is not
760 allowed.
761 """
762 collectionRecord = self._collections.find(collection)
763 if collectionRecord.type is not CollectionType.TAGGED:
764 raise TypeError(f"Collection '{collection}' has type {collectionRecord.type.name}, not TAGGED.")
765 for datasetType, refsForType in DatasetRef.groupByType(refs).items():
766 storage = self._datasets.find(datasetType.name)
767 assert storage is not None
768 try:
769 storage.associate(collectionRecord, refsForType)
770 except sqlalchemy.exc.IntegrityError as err:
771 raise ConflictingDefinitionError(
772 f"Constraint violation while associating dataset of type {datasetType.name} with "
773 f"collection {collection}. This probably means that one or more datasets with the same "
774 f"dataset type and data ID already exist in the collection, but it may also indicate "
775 f"that the datasets do not exist."
776 ) from err
778 @transactional
779 def disassociate(self, collection: str, refs: Iterable[DatasetRef]) -> None:
780 """Remove existing datasets from a `~CollectionType.TAGGED` collection.
782 ``collection`` and ``ref`` combinations that are not currently
783 associated are silently ignored.
785 Parameters
786 ----------
787 collection : `str`
788 The collection the datasets should no longer be associated with.
789 refs : `Iterable` [ `DatasetRef` ]
790 An iterable of resolved `DatasetRef` instances that already exist
791 in this `Registry`.
793 Raises
794 ------
795 AmbiguousDatasetError
796 Raised if any of the given dataset references is unresolved.
797 MissingCollectionError
798 Raised if ``collection`` does not exist in the registry.
799 TypeError
800 Raise adding new datasets to the given ``collection`` is not
801 allowed.
802 """
803 collectionRecord = self._collections.find(collection)
804 if collectionRecord.type is not CollectionType.TAGGED:
805 raise TypeError(f"Collection '{collection}' has type {collectionRecord.type.name}; "
806 "expected TAGGED.")
807 for datasetType, refsForType in DatasetRef.groupByType(refs).items():
808 storage = self._datasets.find(datasetType.name)
809 assert storage is not None
810 storage.disassociate(collectionRecord, refsForType)
812 @transactional
813 def certify(self, collection: str, refs: Iterable[DatasetRef], timespan: Timespan) -> None:
814 """Associate one or more datasets with a calibration collection and a
815 validity range within it.
817 Parameters
818 ----------
819 collection : `str`
820 The name of an already-registered `~CollectionType.CALIBRATION`
821 collection.
822 refs : `Iterable` [ `DatasetRef` ]
823 Datasets to be associated.
824 timespan : `Timespan`
825 The validity range for these datasets within the collection.
827 Raises
828 ------
829 AmbiguousDatasetError
830 Raised if any of the given `DatasetRef` instances is unresolved.
831 ConflictingDefinitionError
832 Raised if the collection already contains a different dataset with
833 the same `DatasetType` and data ID and an overlapping validity
834 range.
835 TypeError
836 Raised if ``collection`` is not a `~CollectionType.CALIBRATION`
837 collection or if one or more datasets are of a dataset type for
838 which `DatasetType.isCalibration` returns `False`.
839 """
840 collectionRecord = self._collections.find(collection)
841 for datasetType, refsForType in DatasetRef.groupByType(refs).items():
842 storage = self._datasets[datasetType.name]
843 storage.certify(collectionRecord, refsForType, timespan)
845 @transactional
846 def decertify(self, collection: str, datasetType: Union[str, DatasetType], timespan: Timespan, *,
847 dataIds: Optional[Iterable[DataId]] = None) -> None:
848 """Remove or adjust datasets to clear a validity range within a
849 calibration collection.
851 Parameters
852 ----------
853 collection : `str`
854 The name of an already-registered `~CollectionType.CALIBRATION`
855 collection.
856 datasetType : `str` or `DatasetType`
857 Name or `DatasetType` instance for the datasets to be decertified.
858 timespan : `Timespan`, optional
859 The validity range to remove datasets from within the collection.
860 Datasets that overlap this range but are not contained by it will
861 have their validity ranges adjusted to not overlap it, which may
862 split a single dataset validity range into two.
863 dataIds : `Iterable` [ `DataId` ], optional
864 Data IDs that should be decertified within the given validity range
865 If `None`, all data IDs for ``self.datasetType`` will be
866 decertified.
868 Raises
869 ------
870 TypeError
871 Raised if ``collection`` is not a `~CollectionType.CALIBRATION`
872 collection or if ``datasetType.isCalibration() is False``.
873 """
874 collectionRecord = self._collections.find(collection)
875 if isinstance(datasetType, str):
876 storage = self._datasets[datasetType]
877 else:
878 storage = self._datasets[datasetType.name]
879 standardizedDataIds = None
880 if dataIds is not None:
881 standardizedDataIds = [DataCoordinate.standardize(d, graph=storage.datasetType.dimensions)
882 for d in dataIds]
883 storage.decertify(collectionRecord, timespan, dataIds=standardizedDataIds)
885 def getDatastoreBridgeManager(self) -> DatastoreRegistryBridgeManager:
886 """Return an object that allows a new `Datastore` instance to
887 communicate with this `Registry`.
889 Returns
890 -------
891 manager : `DatastoreRegistryBridgeManager`
892 Object that mediates communication between this `Registry` and its
893 associated datastores.
894 """
895 return self._datastoreBridges
897 def getDatasetLocations(self, ref: DatasetRef) -> Iterable[str]:
898 """Retrieve datastore locations for a given dataset.
900 Parameters
901 ----------
902 ref : `DatasetRef`
903 A reference to the dataset for which to retrieve storage
904 information.
906 Returns
907 -------
908 datastores : `Iterable` [ `str` ]
909 All the matching datastores holding this dataset.
911 Raises
912 ------
913 AmbiguousDatasetError
914 Raised if ``ref.id`` is `None`.
915 """
916 return self._datastoreBridges.findDatastores(ref)
918 def expandDataId(self, dataId: Optional[DataId] = None, *, graph: Optional[DimensionGraph] = None,
919 records: Optional[NameLookupMapping[DimensionElement, Optional[DimensionRecord]]] = None,
920 **kwargs: Any) -> DataCoordinate:
921 """Expand a dimension-based data ID to include additional information.
923 Parameters
924 ----------
925 dataId : `DataCoordinate` or `dict`, optional
926 Data ID to be expanded; augmented and overridden by ``kwds``.
927 graph : `DimensionGraph`, optional
928 Set of dimensions for the expanded ID. If `None`, the dimensions
929 will be inferred from the keys of ``dataId`` and ``kwds``.
930 Dimensions that are in ``dataId`` or ``kwds`` but not in ``graph``
931 are silently ignored, providing a way to extract and expand a
932 subset of a data ID.
933 records : `Mapping` [`str`, `DimensionRecord`], optional
934 Dimension record data to use before querying the database for that
935 data, keyed by element name.
936 **kwargs
937 Additional keywords are treated like additional key-value pairs for
938 ``dataId``, extending and overriding
940 Returns
941 -------
942 expanded : `DataCoordinate`
943 A data ID that includes full metadata for all of the dimensions it
944 identifieds, i.e. guarantees that ``expanded.hasRecords()`` and
945 ``expanded.hasFull()`` both return `True`.
946 """
947 standardized = DataCoordinate.standardize(dataId, graph=graph, universe=self.dimensions, **kwargs)
948 if standardized.hasRecords():
949 return standardized
950 if records is None:
951 records = {}
952 elif isinstance(records, NamedKeyMapping):
953 records = records.byName()
954 else:
955 records = dict(records)
956 if isinstance(dataId, DataCoordinate) and dataId.hasRecords():
957 records.update(dataId.records.byName())
958 keys = standardized.byName()
959 for element in standardized.graph.primaryKeyTraversalOrder:
960 record = records.get(element.name, ...) # Use ... to mean not found; None might mean NULL
961 if record is ...:
962 if isinstance(element, Dimension) and keys.get(element.name) is None:
963 if element in standardized.graph.required:
964 raise LookupError(
965 f"No value or null value for required dimension {element.name}."
966 )
967 keys[element.name] = None
968 record = None
969 else:
970 storage = self._dimensions[element]
971 dataIdSet = DataCoordinateIterable.fromScalar(
972 DataCoordinate.standardize(keys, graph=element.graph)
973 )
974 fetched = tuple(storage.fetch(dataIdSet))
975 try:
976 (record,) = fetched
977 except ValueError:
978 record = None
979 records[element.name] = record
980 if record is not None:
981 for d in element.implied:
982 value = getattr(record, d.name)
983 if keys.setdefault(d.name, value) != value:
984 raise InconsistentDataIdError(
985 f"Data ID {standardized} has {d.name}={keys[d.name]!r}, "
986 f"but {element.name} implies {d.name}={value!r}."
987 )
988 else:
989 if element in standardized.graph.required:
990 raise LookupError(
991 f"Could not fetch record for required dimension {element.name} via keys {keys}."
992 )
993 if element.alwaysJoin:
994 raise InconsistentDataIdError(
995 f"Could not fetch record for element {element.name} via keys {keys}, ",
996 "but it is marked alwaysJoin=True; this means one or more dimensions are not "
997 "related."
998 )
999 for d in element.implied:
1000 keys.setdefault(d.name, None)
1001 records.setdefault(d.name, None)
1002 return DataCoordinate.standardize(keys, graph=standardized.graph).expanded(records=records)
1004 def insertDimensionData(self, element: Union[DimensionElement, str],
1005 *data: Union[Mapping[str, Any], DimensionRecord],
1006 conform: bool = True) -> None:
1007 """Insert one or more dimension records into the database.
1009 Parameters
1010 ----------
1011 element : `DimensionElement` or `str`
1012 The `DimensionElement` or name thereof that identifies the table
1013 records will be inserted into.
1014 data : `dict` or `DimensionRecord` (variadic)
1015 One or more records to insert.
1016 conform : `bool`, optional
1017 If `False` (`True` is default) perform no checking or conversions,
1018 and assume that ``element`` is a `DimensionElement` instance and
1019 ``data`` is a one or more `DimensionRecord` instances of the
1020 appropriate subclass.
1021 """
1022 if conform:
1023 if isinstance(element, str):
1024 element = self.dimensions[element]
1025 records = [row if isinstance(row, DimensionRecord) else element.RecordClass(**row)
1026 for row in data]
1027 else:
1028 # Ignore typing since caller said to trust them with conform=False.
1029 records = data # type: ignore
1030 storage = self._dimensions[element] # type: ignore
1031 storage.insert(*records)
1033 def syncDimensionData(self, element: Union[DimensionElement, str],
1034 row: Union[Mapping[str, Any], DimensionRecord],
1035 conform: bool = True) -> bool:
1036 """Synchronize the given dimension record with the database, inserting
1037 if it does not already exist and comparing values if it does.
1039 Parameters
1040 ----------
1041 element : `DimensionElement` or `str`
1042 The `DimensionElement` or name thereof that identifies the table
1043 records will be inserted into.
1044 row : `dict` or `DimensionRecord`
1045 The record to insert.
1046 conform : `bool`, optional
1047 If `False` (`True` is default) perform no checking or conversions,
1048 and assume that ``element`` is a `DimensionElement` instance and
1049 ``data`` is a one or more `DimensionRecord` instances of the
1050 appropriate subclass.
1052 Returns
1053 -------
1054 inserted : `bool`
1055 `True` if a new row was inserted, `False` otherwise.
1057 Raises
1058 ------
1059 ConflictingDefinitionError
1060 Raised if the record exists in the database (according to primary
1061 key lookup) but is inconsistent with the given one.
1063 Notes
1064 -----
1065 This method cannot be called within transactions, as it needs to be
1066 able to perform its own transaction to be concurrent.
1067 """
1068 if conform:
1069 if isinstance(element, str):
1070 element = self.dimensions[element]
1071 record = row if isinstance(row, DimensionRecord) else element.RecordClass(**row)
1072 else:
1073 # Ignore typing since caller said to trust them with conform=False.
1074 record = row # type: ignore
1075 storage = self._dimensions[element] # type: ignore
1076 return storage.sync(record)
1078 def queryDatasetTypes(self, expression: Any = ..., *, components: Optional[bool] = None
1079 ) -> Iterator[DatasetType]:
1080 """Iterate over the dataset types whose names match an expression.
1082 Parameters
1083 ----------
1084 expression : `Any`, optional
1085 An expression that fully or partially identifies the dataset types
1086 to return, such as a `str`, `re.Pattern`, or iterable thereof.
1087 `...` can be used to return all dataset types, and is the default.
1088 See :ref:`daf_butler_dataset_type_expressions` for more
1089 information.
1090 components : `bool`, optional
1091 If `True`, apply all expression patterns to component dataset type
1092 names as well. If `False`, never apply patterns to components.
1093 If `None` (default), apply patterns to components only if their
1094 parent datasets were not matched by the expression.
1095 Fully-specified component datasets (`str` or `DatasetType`
1096 instances) are always included.
1098 Yields
1099 ------
1100 datasetType : `DatasetType`
1101 A `DatasetType` instance whose name matches ``expression``.
1102 """
1103 wildcard = CategorizedWildcard.fromExpression(expression, coerceUnrecognized=lambda d: d.name)
1104 if wildcard is Ellipsis:
1105 for datasetType in self._datasets:
1106 # The dataset type can no longer be a component
1107 yield datasetType
1108 if components and datasetType.isComposite():
1109 # Automatically create the component dataset types
1110 for component in datasetType.makeAllComponentDatasetTypes():
1111 yield component
1112 return
1113 done: Set[str] = set()
1114 for name in wildcard.strings:
1115 storage = self._datasets.find(name)
1116 if storage is not None:
1117 done.add(storage.datasetType.name)
1118 yield storage.datasetType
1119 if wildcard.patterns:
1120 # If components (the argument) is None, we'll save component
1121 # dataset that we might want to match, but only if their parents
1122 # didn't get included.
1123 componentsForLater = []
1124 for registeredDatasetType in self._datasets:
1125 # Components are not stored in registry so expand them here
1126 allDatasetTypes = [registeredDatasetType] \
1127 + registeredDatasetType.makeAllComponentDatasetTypes()
1128 for datasetType in allDatasetTypes:
1129 if datasetType.name in done:
1130 continue
1131 parentName, componentName = datasetType.nameAndComponent()
1132 if componentName is not None and not components:
1133 if components is None and parentName not in done:
1134 componentsForLater.append(datasetType)
1135 continue
1136 if any(p.fullmatch(datasetType.name) for p in wildcard.patterns):
1137 done.add(datasetType.name)
1138 yield datasetType
1139 # Go back and try to match saved components.
1140 for datasetType in componentsForLater:
1141 parentName, _ = datasetType.nameAndComponent()
1142 if parentName not in done and any(p.fullmatch(datasetType.name) for p in wildcard.patterns):
1143 yield datasetType
1145 def queryCollections(self, expression: Any = ...,
1146 datasetType: Optional[DatasetType] = None,
1147 collectionTypes: Iterable[CollectionType] = CollectionType.all(),
1148 flattenChains: bool = False,
1149 includeChains: Optional[bool] = None) -> Iterator[str]:
1150 """Iterate over the collections whose names match an expression.
1152 Parameters
1153 ----------
1154 expression : `Any`, optional
1155 An expression that fully or partially identifies the collections
1156 to return, such as a `str`, `re.Pattern`, or iterable thereof.
1157 `...` can be used to return all collections, and is the default.
1158 See :ref:`daf_butler_collection_expressions` for more
1159 information.
1160 datasetType : `DatasetType`, optional
1161 If provided, only yield collections that should be searched for
1162 this dataset type according to ``expression``. If this is
1163 not provided, any dataset type restrictions in ``expression`` are
1164 ignored.
1165 collectionTypes : `AbstractSet` [ `CollectionType` ], optional
1166 If provided, only yield collections of these types.
1167 flattenChains : `bool`, optional
1168 If `True` (`False` is default), recursively yield the child
1169 collections of matching `~CollectionType.CHAINED` collections.
1170 includeChains : `bool`, optional
1171 If `True`, yield records for matching `~CollectionType.CHAINED`
1172 collections. Default is the opposite of ``flattenChains``: include
1173 either CHAINED collections or their children, but not both.
1175 Yields
1176 ------
1177 collection : `str`
1178 The name of a collection that matches ``expression``.
1179 """
1180 query = CollectionQuery.fromExpression(expression)
1181 for record in query.iter(self._collections, datasetType=datasetType,
1182 collectionTypes=frozenset(collectionTypes),
1183 flattenChains=flattenChains, includeChains=includeChains):
1184 yield record.name
1186 def makeQueryBuilder(self, summary: queries.QuerySummary) -> queries.QueryBuilder:
1187 """Return a `QueryBuilder` instance capable of constructing and
1188 managing more complex queries than those obtainable via `Registry`
1189 interfaces.
1191 This is an advanced interface; downstream code should prefer
1192 `Registry.queryDataIds` and `Registry.queryDatasets` whenever those
1193 are sufficient.
1195 Parameters
1196 ----------
1197 summary : `queries.QuerySummary`
1198 Object describing and categorizing the full set of dimensions that
1199 will be included in the query.
1201 Returns
1202 -------
1203 builder : `queries.QueryBuilder`
1204 Object that can be used to construct and perform advanced queries.
1205 """
1206 return queries.QueryBuilder(
1207 summary,
1208 queries.RegistryManagers(
1209 collections=self._collections,
1210 dimensions=self._dimensions,
1211 datasets=self._datasets
1212 )
1213 )
1215 def queryDatasets(self, datasetType: Any, *,
1216 collections: Any,
1217 dimensions: Optional[Iterable[Union[Dimension, str]]] = None,
1218 dataId: Optional[DataId] = None,
1219 where: Optional[str] = None,
1220 deduplicate: bool = False,
1221 components: Optional[bool] = None,
1222 **kwargs: Any) -> queries.DatasetQueryResults:
1223 """Query for and iterate over dataset references matching user-provided
1224 criteria.
1226 Parameters
1227 ----------
1228 datasetType
1229 An expression that fully or partially identifies the dataset types
1230 to be queried. Allowed types include `DatasetType`, `str`,
1231 `re.Pattern`, and iterables thereof. The special value `...` can
1232 be used to query all dataset types. See
1233 :ref:`daf_butler_dataset_type_expressions` for more information.
1234 collections
1235 An expression that fully or partially identifies the collections
1236 to search for datasets, such as a `str`, `re.Pattern`, or iterable
1237 thereof. `...` can be used to datasets from all
1238 `~CollectionType.RUN` collections (no other collections are
1239 necessary, because all datasets are in a ``RUN`` collection). See
1240 :ref:`daf_butler_collection_expressions` for more information.
1241 dimensions : `~collections.abc.Iterable` of `Dimension` or `str`
1242 Dimensions to include in the query (in addition to those used
1243 to identify the queried dataset type(s)), either to constrain
1244 the resulting datasets to those for which a matching dimension
1245 exists, or to relate the dataset type's dimensions to dimensions
1246 referenced by the ``dataId`` or ``where`` arguments.
1247 dataId : `dict` or `DataCoordinate`, optional
1248 A data ID whose key-value pairs are used as equality constraints
1249 in the query.
1250 where : `str`, optional
1251 A string expression similar to a SQL WHERE clause. May involve
1252 any column of a dimension table or (as a shortcut for the primary
1253 key column of a dimension table) dimension name. See
1254 :ref:`daf_butler_dimension_expressions` for more information.
1255 deduplicate : `bool`, optional
1256 If `True` (`False` is default), for each result data ID, only
1257 yield one `DatasetRef` of each `DatasetType`, from the first
1258 collection in which a dataset of that dataset type appears
1259 (according to the order of ``collections`` passed in). If `True`,
1260 ``collections`` must not contain regular expressions and may not
1261 be `...`.
1262 components : `bool`, optional
1263 If `True`, apply all dataset expression patterns to component
1264 dataset type names as well. If `False`, never apply patterns to
1265 components. If `None` (default), apply patterns to components only
1266 if their parent datasets were not matched by the expression.
1267 Fully-specified component datasets (`str` or `DatasetType`
1268 instances) are always included.
1269 **kwargs
1270 Additional keyword arguments are forwarded to
1271 `DataCoordinate.standardize` when processing the ``dataId``
1272 argument (and may be used to provide a constraining data ID even
1273 when the ``dataId`` argument is `None`).
1275 Returns
1276 -------
1277 refs : `queries.DatasetQueryResults`
1278 Dataset references matching the given query criteria.
1280 Raises
1281 ------
1282 TypeError
1283 Raised when the arguments are incompatible, such as when a
1284 collection wildcard is passed when ``deduplicate`` is `True`.
1286 Notes
1287 -----
1288 When multiple dataset types are queried in a single call, the
1289 results of this operation are equivalent to querying for each dataset
1290 type separately in turn, and no information about the relationships
1291 between datasets of different types is included. In contexts where
1292 that kind of information is important, the recommended pattern is to
1293 use `queryDataIds` to first obtain data IDs (possibly with the
1294 desired dataset types and collections passed as constraints to the
1295 query), and then use multiple (generally much simpler) calls to
1296 `queryDatasets` with the returned data IDs passed as constraints.
1297 """
1298 # Standardize the collections expression.
1299 if deduplicate:
1300 collections = CollectionSearch.fromExpression(collections)
1301 else:
1302 collections = CollectionQuery.fromExpression(collections)
1303 # Standardize and expand the data ID provided as a constraint.
1304 standardizedDataId = self.expandDataId(dataId, **kwargs)
1306 # We can only query directly if given a non-component DatasetType
1307 # instance. If we were given an expression or str or a component
1308 # DatasetType instance, we'll populate this dict, recurse, and return.
1309 # If we already have a non-component DatasetType, it will remain None
1310 # and we'll run the query directly.
1311 composition: Optional[
1312 Dict[
1313 DatasetType, # parent dataset type
1314 List[Optional[str]] # component name, or None for parent
1315 ]
1316 ] = None
1317 if not isinstance(datasetType, DatasetType):
1318 # We were given a dataset type expression (which may be as simple
1319 # as a str). Loop over all matching datasets, delegating handling
1320 # of the `components` argument to queryDatasetTypes, as we populate
1321 # the composition dict.
1322 composition = defaultdict(list)
1323 for trueDatasetType in self.queryDatasetTypes(datasetType, components=components):
1324 parentName, componentName = trueDatasetType.nameAndComponent()
1325 if componentName is not None:
1326 parentDatasetType = self.getDatasetType(parentName)
1327 composition.setdefault(parentDatasetType, []).append(componentName)
1328 else:
1329 composition.setdefault(trueDatasetType, []).append(None)
1330 elif datasetType.isComponent():
1331 # We were given a true DatasetType instance, but it's a component.
1332 # the composition dict will have exactly one item.
1333 parentName, componentName = datasetType.nameAndComponent()
1334 parentDatasetType = self.getDatasetType(parentName)
1335 composition = {parentDatasetType: [componentName]}
1336 if composition is not None:
1337 # We need to recurse. Do that once for each parent dataset type.
1338 chain = []
1339 for parentDatasetType, componentNames in composition.items():
1340 parentResults = self.queryDatasets(
1341 parentDatasetType,
1342 collections=collections,
1343 dimensions=dimensions,
1344 dataId=standardizedDataId,
1345 where=where,
1346 deduplicate=deduplicate
1347 )
1348 if isinstance(parentResults, queries.ParentDatasetQueryResults):
1349 chain.append(
1350 parentResults.withComponents(componentNames)
1351 )
1352 else:
1353 # Should only happen if we know there would be no results.
1354 assert isinstance(parentResults, queries.ChainedDatasetQueryResults) \
1355 and not parentResults._chain
1356 return queries.ChainedDatasetQueryResults(chain)
1357 # If we get here, there's no need to recurse (or we are already
1358 # recursing; there can only ever be one level of recursion).
1360 # The full set of dimensions in the query is the combination of those
1361 # needed for the DatasetType and those explicitly requested, if any.
1362 requestedDimensionNames = set(datasetType.dimensions.names)
1363 if dimensions is not None:
1364 requestedDimensionNames.update(self.dimensions.extract(dimensions).names)
1365 # Construct the summary structure needed to construct a QueryBuilder.
1366 summary = queries.QuerySummary(
1367 requested=DimensionGraph(self.dimensions, names=requestedDimensionNames),
1368 dataId=standardizedDataId,
1369 expression=where,
1370 )
1371 builder = self.makeQueryBuilder(summary)
1372 # Add the dataset subquery to the query, telling the QueryBuilder to
1373 # include the rank of the selected collection in the results only if we
1374 # need to deduplicate. Note that if any of the collections are
1375 # actually wildcard expressions, and we've asked for deduplication,
1376 # this will raise TypeError for us.
1377 if not builder.joinDataset(datasetType, collections, isResult=True, deduplicate=deduplicate):
1378 return queries.ChainedDatasetQueryResults(())
1379 query = builder.finish()
1380 return queries.ParentDatasetQueryResults(self._db, query, components=[None])
1382 def queryDataIds(self, dimensions: Union[Iterable[Union[Dimension, str]], Dimension, str], *,
1383 dataId: Optional[DataId] = None,
1384 datasets: Any = None,
1385 collections: Any = None,
1386 where: Optional[str] = None,
1387 components: Optional[bool] = None,
1388 **kwargs: Any) -> queries.DataCoordinateQueryResults:
1389 """Query for data IDs matching user-provided criteria.
1391 Parameters
1392 ----------
1393 dimensions : `Dimension` or `str`, or iterable thereof
1394 The dimensions of the data IDs to yield, as either `Dimension`
1395 instances or `str`. Will be automatically expanded to a complete
1396 `DimensionGraph`.
1397 dataId : `dict` or `DataCoordinate`, optional
1398 A data ID whose key-value pairs are used as equality constraints
1399 in the query.
1400 datasets : `Any`, optional
1401 An expression that fully or partially identifies dataset types
1402 that should constrain the yielded data IDs. For example, including
1403 "raw" here would constrain the yielded ``instrument``,
1404 ``exposure``, ``detector``, and ``physical_filter`` values to only
1405 those for which at least one "raw" dataset exists in
1406 ``collections``. Allowed types include `DatasetType`, `str`,
1407 `re.Pattern`, and iterables thereof. Unlike other dataset type
1408 expressions, ``...`` is not permitted - it doesn't make sense to
1409 constrain data IDs on the existence of *all* datasets.
1410 See :ref:`daf_butler_dataset_type_expressions` for more
1411 information.
1412 collections: `Any`, optional
1413 An expression that fully or partially identifies the collections
1414 to search for datasets, such as a `str`, `re.Pattern`, or iterable
1415 thereof. `...` can be used to return all collections. Must be
1416 provided if ``datasets`` is, and is ignored if it is not. See
1417 :ref:`daf_butler_collection_expressions` for more information.
1418 where : `str`, optional
1419 A string expression similar to a SQL WHERE clause. May involve
1420 any column of a dimension table or (as a shortcut for the primary
1421 key column of a dimension table) dimension name. See
1422 :ref:`daf_butler_dimension_expressions` for more information.
1423 components : `bool`, optional
1424 If `True`, apply all dataset expression patterns to component
1425 dataset type names as well. If `False`, never apply patterns to
1426 components. If `None` (default), apply patterns to components only
1427 if their parent datasets were not matched by the expression.
1428 Fully-specified component datasets (`str` or `DatasetType`
1429 instances) are always included.
1430 **kwargs
1431 Additional keyword arguments are forwarded to
1432 `DataCoordinate.standardize` when processing the ``dataId``
1433 argument (and may be used to provide a constraining data ID even
1434 when the ``dataId`` argument is `None`).
1436 Returns
1437 -------
1438 dataIds : `DataCoordinateQueryResults`
1439 Data IDs matching the given query parameters. These are guaranteed
1440 to identify all dimensions (`DataCoordinate.hasFull` returns
1441 `True`), but will not contain `DimensionRecord` objects
1442 (`DataCoordinate.hasRecords` returns `False`). Call
1443 `DataCoordinateQueryResults.expanded` on the returned object to
1444 fetch those (and consider using
1445 `DataCoordinateQueryResults.materialize` on the returned object
1446 first if the expected number of rows is very large). See
1447 documentation for those methods for additional information.
1448 """
1449 dimensions = iterable(dimensions)
1450 standardizedDataId = self.expandDataId(dataId, **kwargs)
1451 standardizedDatasetTypes = set()
1452 requestedDimensions = self.dimensions.extract(dimensions)
1453 queryDimensionNames = set(requestedDimensions.names)
1454 if datasets is not None:
1455 if collections is None:
1456 raise TypeError("Cannot pass 'datasets' without 'collections'.")
1457 for datasetType in self.queryDatasetTypes(datasets, components=components):
1458 queryDimensionNames.update(datasetType.dimensions.names)
1459 # If any matched dataset type is a component, just operate on
1460 # its parent instead, because Registry doesn't know anything
1461 # about what components exist, and here (unlike queryDatasets)
1462 # we don't care about returning them.
1463 parentDatasetTypeName, componentName = datasetType.nameAndComponent()
1464 if componentName is not None:
1465 datasetType = self.getDatasetType(parentDatasetTypeName)
1466 standardizedDatasetTypes.add(datasetType)
1467 # Preprocess collections expression in case the original included
1468 # single-pass iterators (we'll want to use it multiple times
1469 # below).
1470 collections = CollectionQuery.fromExpression(collections)
1472 summary = queries.QuerySummary(
1473 requested=DimensionGraph(self.dimensions, names=queryDimensionNames),
1474 dataId=standardizedDataId,
1475 expression=where,
1476 )
1477 builder = self.makeQueryBuilder(summary)
1478 for datasetType in standardizedDatasetTypes:
1479 builder.joinDataset(datasetType, collections, isResult=False)
1480 query = builder.finish()
1481 return queries.DataCoordinateQueryResults(self._db, query)
1483 def queryDimensionRecords(self, element: Union[DimensionElement, str], *,
1484 dataId: Optional[DataId] = None,
1485 datasets: Any = None,
1486 collections: Any = None,
1487 where: Optional[str] = None,
1488 components: Optional[bool] = None,
1489 **kwargs: Any) -> Iterator[DimensionRecord]:
1490 """Query for dimension information matching user-provided criteria.
1492 Parameters
1493 ----------
1494 element : `DimensionElement` or `str`
1495 The dimension element to obtain r
1496 dataId : `dict` or `DataCoordinate`, optional
1497 A data ID whose key-value pairs are used as equality constraints
1498 in the query.
1499 datasets : `Any`, optional
1500 An expression that fully or partially identifies dataset types
1501 that should constrain the yielded records. See `queryDataIds` and
1502 :ref:`daf_butler_dataset_type_expressions` for more information.
1503 collections: `Any`, optional
1504 An expression that fully or partially identifies the collections
1505 to search for datasets. See `queryDataIds` and
1506 :ref:`daf_butler_collection_expressions` for more information.
1507 where : `str`, optional
1508 A string expression similar to a SQL WHERE clause. See
1509 `queryDataIds` and :ref:`daf_butler_dimension_expressions` for more
1510 information.
1511 components : `bool`, optional
1512 Whether to apply dataset expressions to components as well.
1513 See `queryDataIds` for more information.
1514 **kwargs
1515 Additional keyword arguments are forwarded to
1516 `DataCoordinate.standardize` when processing the ``dataId``
1517 argument (and may be used to provide a constraining data ID even
1518 when the ``dataId`` argument is `None`).
1520 Returns
1521 -------
1522 dataIds : `DataCoordinateQueryResults`
1523 Data IDs matching the given query parameters.
1524 """
1525 if not isinstance(element, DimensionElement):
1526 element = self.dimensions[element]
1527 dataIds = self.queryDataIds(element.graph, dataId=dataId, datasets=datasets, collections=collections,
1528 where=where, components=components, **kwargs)
1529 return iter(self._dimensions[element].fetch(dataIds))
1531 def queryDatasetAssociations(
1532 self,
1533 datasetType: Union[str, DatasetType],
1534 collections: Any = ...,
1535 *,
1536 collectionTypes: Iterable[CollectionType] = CollectionType.all(),
1537 flattenChains: bool = False,
1538 ) -> Iterator[DatasetAssociation]:
1539 """Iterate over dataset-collection combinations where the dataset is in
1540 the collection.
1542 This method is a temporary placeholder for better support for
1543 assocation results in `queryDatasets`. It will probably be
1544 removed in the future, and should be avoided in production code
1545 whenever possible.
1547 Parameters
1548 ----------
1549 datasetType : `DatasetType` or `str`
1550 A dataset type object or the name of one.
1551 collections: `Any`, optional
1552 An expression that fully or partially identifies the collections
1553 to search for datasets. See `queryCollections` and
1554 :ref:`daf_butler_collection_expressions` for more information.
1555 collectionTypes : `AbstractSet` [ `CollectionType` ], optional
1556 If provided, only yield associations from collections of these
1557 types.
1558 flattenChains : `bool`, optional
1559 If `True` (default) search in the children of
1560 `~CollectionType.CHAINED` collections. If `False`, ``CHAINED``
1561 collections are ignored.
1563 Yields
1564 ------
1565 association : `DatasetAssociation`
1566 Object representing the relationship beween a single dataset and
1567 a single collection.
1568 """
1569 collections = CollectionQuery.fromExpression(collections)
1570 tsRepr = self._db.getTimespanRepresentation()
1571 if isinstance(datasetType, str):
1572 storage = self._datasets[datasetType]
1573 else:
1574 storage = self._datasets[datasetType.name]
1575 for collectionRecord in collections.iter(self._collections, datasetType=datasetType,
1576 collectionTypes=frozenset(collectionTypes),
1577 flattenChains=flattenChains):
1578 query = storage.select(collectionRecord)
1579 if query is None:
1580 continue
1581 for row in self._db.query(query.combine()):
1582 dataId = DataCoordinate.fromRequiredValues(
1583 storage.datasetType.dimensions,
1584 tuple(row[name] for name in storage.datasetType.dimensions.required.names)
1585 )
1586 runRecord = self._collections[row[self._collections.getRunForeignKeyName()]]
1587 ref = DatasetRef(storage.datasetType, dataId, id=row["id"], run=runRecord.name,
1588 conform=False)
1589 if collectionRecord.type is CollectionType.CALIBRATION:
1590 timespan = tsRepr.extract(row)
1591 else:
1592 timespan = None
1593 yield DatasetAssociation(ref=ref, collection=collectionRecord.name, timespan=timespan)
1595 storageClasses: StorageClassFactory
1596 """All storage classes known to the registry (`StorageClassFactory`).
1597 """