Coverage for python/lsst/daf/butler/registry/_registry.py : 14%

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_CHECKING,
41 Union,
42)
44import sqlalchemy
46from ..core import (
47 ButlerURI,
48 Config,
49 DataCoordinate,
50 DataCoordinateIterable,
51 DataId,
52 DatasetAssociation,
53 DatasetRef,
54 DatasetType,
55 ddl,
56 Dimension,
57 DimensionConfig,
58 DimensionElement,
59 DimensionGraph,
60 DimensionRecord,
61 DimensionUniverse,
62 NamedKeyMapping,
63 NameLookupMapping,
64 Progress,
65 StorageClassFactory,
66 Timespan,
67)
68from . import queries
69from ..core.utils import iterable, transactional
70from ._config import RegistryConfig
71from ._collectionType import CollectionType
72from ._defaults import RegistryDefaults
73from ._exceptions import ConflictingDefinitionError, InconsistentDataIdError, OrphanedRecordError
74from .managers import RegistryManagerTypes, RegistryManagerInstances
75from .wildcards import CategorizedWildcard, CollectionQuery, CollectionSearch, Ellipsis
76from .summaries import CollectionSummary
77from .interfaces import ChainedCollectionRecord, RunRecord
79if TYPE_CHECKING: 79 ↛ 80line 79 didn't jump to line 80, because the condition on line 79 was never true
80 from .._butlerConfig import ButlerConfig
81 from .interfaces import (
82 Database,
83 DatastoreRegistryBridgeManager,
84 )
87_LOG = logging.getLogger(__name__)
89# key for dimensions configuration in attributes table
90_DIMENSIONS_ATTR = "config:dimensions.json"
93class Registry:
94 """Registry interface.
96 Parameters
97 ----------
98 database : `Database`
99 Database instance to store Registry.
100 defaults : `RegistryDefaults`, optional
101 Default collection search path and/or output `~CollectionType.RUN`
102 collection.
103 attributes : `type`
104 Manager class implementing `ButlerAttributeManager`.
105 opaque : `type`
106 Manager class implementing `OpaqueTableStorageManager`.
107 dimensions : `type`
108 Manager class implementing `DimensionRecordStorageManager`.
109 collections : `type`
110 Manager class implementing `CollectionManager`.
111 datasets : `type`
112 Manager class implementing `DatasetRecordStorageManager`.
113 datastoreBridges : `type`
114 Manager class implementing `DatastoreRegistryBridgeManager`.
115 dimensionConfig : `DimensionConfig`, optional
116 Dimension universe configuration, only used when ``create`` is True.
117 writeable : `bool`, optional
118 If True then Registry will support write operations.
119 create : `bool`, optional
120 If True then database schema will be initialized, it must be empty
121 before instantiating Registry.
122 """
124 defaultConfigFile: Optional[str] = None
125 """Path to configuration defaults. Accessed within the ``configs`` resource
126 or relative to a search path. Can be None if no defaults specified.
127 """
129 @classmethod
130 def createFromConfig(cls, config: Optional[Union[RegistryConfig, str]] = None,
131 dimensionConfig: Optional[Union[DimensionConfig, str]] = None,
132 butlerRoot: Optional[str] = None) -> Registry:
133 """Create registry database and return `Registry` instance.
135 This method initializes database contents, database must be empty
136 prior to calling this method.
138 Parameters
139 ----------
140 config : `RegistryConfig` or `str`, optional
141 Registry configuration, if missing then default configuration will
142 be loaded from registry.yaml.
143 dimensionConfig : `DimensionConfig` or `str`, optional
144 Dimensions configuration, if missing then default configuration
145 will be loaded from dimensions.yaml.
146 butlerRoot : `str`, optional
147 Path to the repository root this `Registry` will manage.
149 Returns
150 -------
151 registry : `Registry`
152 A new `Registry` instance.
153 """
154 if isinstance(config, str):
155 config = RegistryConfig(config)
156 elif config is None:
157 config = RegistryConfig()
158 elif not isinstance(config, RegistryConfig):
159 raise TypeError(f"Incompatible Registry configuration type: {type(config)}")
160 config.replaceRoot(butlerRoot)
162 if isinstance(dimensionConfig, str):
163 dimensionConfig = DimensionConfig(config)
164 elif dimensionConfig is None:
165 dimensionConfig = DimensionConfig()
166 elif not isinstance(dimensionConfig, DimensionConfig):
167 raise TypeError(f"Incompatible Dimension configuration type: {type(dimensionConfig)}")
169 DatabaseClass = config.getDatabaseClass()
170 database = DatabaseClass.fromUri(str(config.connectionString), origin=config.get("origin", 0),
171 namespace=config.get("namespace"))
172 managerTypes = RegistryManagerTypes.fromConfig(config)
173 managers = managerTypes.makeRepo(database, dimensionConfig)
174 return cls(database, RegistryDefaults(), managers)
176 @classmethod
177 def fromConfig(cls, config: Union[ButlerConfig, RegistryConfig, Config, str],
178 butlerRoot: Optional[Union[str, ButlerURI]] = None, writeable: bool = True,
179 defaults: Optional[RegistryDefaults] = None) -> Registry:
180 """Create `Registry` subclass instance from `config`.
182 Registry database must be inbitialized prior to calling this method.
184 Parameters
185 ----------
186 config : `ButlerConfig`, `RegistryConfig`, `Config` or `str`
187 Registry configuration
188 butlerRoot : `str` or `ButlerURI`, optional
189 Path to the repository root this `Registry` will manage.
190 writeable : `bool`, optional
191 If `True` (default) create a read-write connection to the database.
192 defaults : `RegistryDefaults`, optional
193 Default collection search path and/or output `~CollectionType.RUN`
194 collection.
196 Returns
197 -------
198 registry : `Registry` (subclass)
199 A new `Registry` subclass instance.
200 """
201 if not isinstance(config, RegistryConfig):
202 if isinstance(config, str) or isinstance(config, Config):
203 config = RegistryConfig(config)
204 else:
205 raise ValueError("Incompatible Registry configuration: {}".format(config))
206 config.replaceRoot(butlerRoot)
207 DatabaseClass = config.getDatabaseClass()
208 database = DatabaseClass.fromUri(str(config.connectionString), origin=config.get("origin", 0),
209 namespace=config.get("namespace"), writeable=writeable)
210 managerTypes = RegistryManagerTypes.fromConfig(config)
211 managers = managerTypes.loadRepo(database)
212 if defaults is None:
213 defaults = RegistryDefaults()
214 return cls(database, defaults, managers)
216 def __init__(self, database: Database, defaults: RegistryDefaults, managers: RegistryManagerInstances):
217 self._db = database
218 self._managers = managers
219 self.storageClasses = StorageClassFactory()
220 # Intentionally invoke property setter to initialize defaults. This
221 # can only be done after most of the rest of Registry has already been
222 # initialized, and must be done before the property getter is used.
223 self.defaults = defaults
225 def __str__(self) -> str:
226 return str(self._db)
228 def __repr__(self) -> str:
229 return f"Registry({self._db!r}, {self.dimensions!r})"
231 def isWriteable(self) -> bool:
232 """Return `True` if this registry allows write operations, and `False`
233 otherwise.
234 """
235 return self._db.isWriteable()
237 def copy(self, defaults: Optional[RegistryDefaults] = None) -> Registry:
238 """Create a new `Registry` backed by the same data repository and
239 connection as this one, but independent defaults.
241 Parameters
242 ----------
243 defaults : `RegistryDefaults`, optional
244 Default collections and data ID values for the new registry. If
245 not provided, ``self.defaults`` will be used (but future changes
246 to either registry's defaults will not affect the other).
248 Returns
249 -------
250 copy : `Registry`
251 A new `Registry` instance with its own defaults.
253 Notes
254 -----
255 Because the new registry shares a connection with the original, they
256 also share transaction state (despite the fact that their `transaction`
257 context manager methods do not reflect this), and must be used with
258 care.
259 """
260 if defaults is None:
261 # No need to copy, because `RegistryDefaults` is immutable; we
262 # effectively copy on write.
263 defaults = self.defaults
264 return Registry(self._db, defaults, self._managers)
266 @property
267 def dimensions(self) -> DimensionUniverse:
268 """All dimensions recognized by this `Registry` (`DimensionUniverse`).
269 """
270 return self._managers.dimensions.universe
272 @property
273 def defaults(self) -> RegistryDefaults:
274 """Default collection search path and/or output `~CollectionType.RUN`
275 collection (`RegistryDefaults`).
277 This is an immutable struct whose components may not be set
278 individually, but the entire struct can be set by assigning to this
279 property.
280 """
281 return self._defaults
283 @defaults.setter
284 def defaults(self, value: RegistryDefaults) -> None:
285 if value.run is not None:
286 self.registerRun(value.run)
287 value.finish(self)
288 self._defaults = value
290 def refresh(self) -> None:
291 """Refresh all in-memory state by querying the database.
293 This may be necessary to enable querying for entities added by other
294 `Registry` instances after this one was constructed.
295 """
296 self._managers.refresh()
298 @contextlib.contextmanager
299 def transaction(self, *, savepoint: bool = False) -> Iterator[None]:
300 """Return a context manager that represents a transaction.
301 """
302 try:
303 with self._db.transaction(savepoint=savepoint):
304 yield
305 except BaseException:
306 # TODO: this clears the caches sometimes when we wouldn't actually
307 # need to. Can we avoid that?
308 self._managers.dimensions.clearCaches()
309 raise
311 def resetConnectionPool(self) -> None:
312 """Reset SQLAlchemy connection pool for registry database.
314 This operation is useful when using registry with fork-based
315 multiprocessing. To use registry across fork boundary one has to make
316 sure that there are no currently active connections (no session or
317 transaction is in progress) and connection pool is reset using this
318 method. This method should be called by the child process immediately
319 after the fork.
320 """
321 self._db._engine.dispose()
323 def registerOpaqueTable(self, tableName: str, spec: ddl.TableSpec) -> None:
324 """Add an opaque (to the `Registry`) table for use by a `Datastore` or
325 other data repository client.
327 Opaque table records can be added via `insertOpaqueData`, retrieved via
328 `fetchOpaqueData`, and removed via `deleteOpaqueData`.
330 Parameters
331 ----------
332 tableName : `str`
333 Logical name of the opaque table. This may differ from the
334 actual name used in the database by a prefix and/or suffix.
335 spec : `ddl.TableSpec`
336 Specification for the table to be added.
337 """
338 self._managers.opaque.register(tableName, spec)
340 @transactional
341 def insertOpaqueData(self, tableName: str, *data: dict) -> None:
342 """Insert records into an opaque table.
344 Parameters
345 ----------
346 tableName : `str`
347 Logical name of the opaque table. Must match the name used in a
348 previous call to `registerOpaqueTable`.
349 data
350 Each additional positional argument is a dictionary that represents
351 a single row to be added.
352 """
353 self._managers.opaque[tableName].insert(*data)
355 def fetchOpaqueData(self, tableName: str, **where: Any) -> Iterator[dict]:
356 """Retrieve records from an opaque table.
358 Parameters
359 ----------
360 tableName : `str`
361 Logical name of the opaque table. Must match the name used in a
362 previous call to `registerOpaqueTable`.
363 where
364 Additional keyword arguments are interpreted as equality
365 constraints that restrict the returned rows (combined with AND);
366 keyword arguments are column names and values are the values they
367 must have.
369 Yields
370 ------
371 row : `dict`
372 A dictionary representing a single result row.
373 """
374 yield from self._managers.opaque[tableName].fetch(**where)
376 @transactional
377 def deleteOpaqueData(self, tableName: str, **where: Any) -> None:
378 """Remove records from an opaque table.
380 Parameters
381 ----------
382 tableName : `str`
383 Logical name of the opaque table. Must match the name used in a
384 previous call to `registerOpaqueTable`.
385 where
386 Additional keyword arguments are interpreted as equality
387 constraints that restrict the deleted rows (combined with AND);
388 keyword arguments are column names and values are the values they
389 must have.
390 """
391 self._managers.opaque[tableName].delete(where.keys(), where)
393 def registerCollection(self, name: str, type: CollectionType = CollectionType.TAGGED,
394 doc: Optional[str] = None) -> None:
395 """Add a new collection if one with the given name does not exist.
397 Parameters
398 ----------
399 name : `str`
400 The name of the collection to create.
401 type : `CollectionType`
402 Enum value indicating the type of collection to create.
403 doc : `str`, optional
404 Documentation string for the collection.
406 Notes
407 -----
408 This method cannot be called within transactions, as it needs to be
409 able to perform its own transaction to be concurrent.
410 """
411 self._managers.collections.register(name, type, doc=doc)
413 def getCollectionType(self, name: str) -> CollectionType:
414 """Return an enumeration value indicating the type of the given
415 collection.
417 Parameters
418 ----------
419 name : `str`
420 The name of the collection.
422 Returns
423 -------
424 type : `CollectionType`
425 Enum value indicating the type of this collection.
427 Raises
428 ------
429 MissingCollectionError
430 Raised if no collection with the given name exists.
431 """
432 return self._managers.collections.find(name).type
434 def registerRun(self, name: str, doc: Optional[str] = None) -> None:
435 """Add a new run if one with the given name does not exist.
437 Parameters
438 ----------
439 name : `str`
440 The name of the run to create.
441 doc : `str`, optional
442 Documentation string for the collection.
444 Notes
445 -----
446 This method cannot be called within transactions, as it needs to be
447 able to perform its own transaction to be concurrent.
448 """
449 self._managers.collections.register(name, CollectionType.RUN, doc=doc)
451 @transactional
452 def removeCollection(self, name: str) -> None:
453 """Completely remove the given collection.
455 Parameters
456 ----------
457 name : `str`
458 The name of the collection to remove.
460 Raises
461 ------
462 MissingCollectionError
463 Raised if no collection with the given name exists.
465 Notes
466 -----
467 If this is a `~CollectionType.RUN` collection, all datasets and quanta
468 in it are also fully removed. This requires that those datasets be
469 removed (or at least trashed) from any datastores that hold them first.
471 A collection may not be deleted as long as it is referenced by a
472 `~CollectionType.CHAINED` collection; the ``CHAINED`` collection must
473 be deleted or redefined first.
474 """
475 self._managers.collections.remove(name)
477 def getCollectionChain(self, parent: str) -> CollectionSearch:
478 """Return the child collections in a `~CollectionType.CHAINED`
479 collection.
481 Parameters
482 ----------
483 parent : `str`
484 Name of the chained collection. Must have already been added via
485 a call to `Registry.registerCollection`.
487 Returns
488 -------
489 children : `CollectionSearch`
490 An object that defines the search path of the collection.
491 See :ref:`daf_butler_collection_expressions` for more information.
493 Raises
494 ------
495 MissingCollectionError
496 Raised if ``parent`` does not exist in the `Registry`.
497 TypeError
498 Raised if ``parent`` does not correspond to a
499 `~CollectionType.CHAINED` collection.
500 """
501 record = self._managers.collections.find(parent)
502 if record.type is not CollectionType.CHAINED:
503 raise TypeError(f"Collection '{parent}' has type {record.type.name}, not CHAINED.")
504 assert isinstance(record, ChainedCollectionRecord)
505 return record.children
507 @transactional
508 def setCollectionChain(self, parent: str, children: Any, *, flatten: bool = False) -> None:
509 """Define or redefine a `~CollectionType.CHAINED` collection.
511 Parameters
512 ----------
513 parent : `str`
514 Name of the chained collection. Must have already been added via
515 a call to `Registry.registerCollection`.
516 children : `Any`
517 An expression defining an ordered search of child collections,
518 generally an iterable of `str`; see
519 :ref:`daf_butler_collection_expressions` for more information.
520 flatten : `bool`, optional
521 If `True` (`False` is default), recursively flatten out any nested
522 `~CollectionType.CHAINED` collections in ``children`` first.
524 Raises
525 ------
526 MissingCollectionError
527 Raised when any of the given collections do not exist in the
528 `Registry`.
529 TypeError
530 Raised if ``parent`` does not correspond to a
531 `~CollectionType.CHAINED` collection.
532 ValueError
533 Raised if the given collections contains a cycle.
534 """
535 record = self._managers.collections.find(parent)
536 if record.type is not CollectionType.CHAINED:
537 raise TypeError(f"Collection '{parent}' has type {record.type.name}, not CHAINED.")
538 assert isinstance(record, ChainedCollectionRecord)
539 children = CollectionSearch.fromExpression(children)
540 if children != record.children or flatten:
541 record.update(self._managers.collections, children, flatten=flatten)
543 def getCollectionDocumentation(self, collection: str) -> Optional[str]:
544 """Retrieve the documentation string for a collection.
546 Parameters
547 ----------
548 name : `str`
549 Name of the collection.
551 Returns
552 -------
553 docs : `str` or `None`
554 Docstring for the collection with the given name.
555 """
556 return self._managers.collections.getDocumentation(self._managers.collections.find(collection).key)
558 def setCollectionDocumentation(self, collection: str, doc: Optional[str]) -> None:
559 """Set the documentation string for a collection.
561 Parameters
562 ----------
563 name : `str`
564 Name of the collection.
565 docs : `str` or `None`
566 Docstring for the collection with the given name; will replace any
567 existing docstring. Passing `None` will remove any existing
568 docstring.
569 """
570 self._managers.collections.setDocumentation(self._managers.collections.find(collection).key, doc)
572 def getCollectionSummary(self, collection: str) -> CollectionSummary:
573 """Return a summary for the given collection.
575 Parameters
576 ----------
577 collection : `str`
578 Name of the collection for which a summary is to be retrieved.
580 Returns
581 -------
582 summary : `CollectionSummary`
583 Summary of the dataset types and governor dimension values in
584 this collection.
585 """
586 record = self._managers.collections.find(collection)
587 return self._managers.datasets.getCollectionSummary(record)
589 def registerDatasetType(self, datasetType: DatasetType) -> bool:
590 """
591 Add a new `DatasetType` to the Registry.
593 It is not an error to register the same `DatasetType` twice.
595 Parameters
596 ----------
597 datasetType : `DatasetType`
598 The `DatasetType` to be added.
600 Returns
601 -------
602 inserted : `bool`
603 `True` if ``datasetType`` was inserted, `False` if an identical
604 existing `DatsetType` was found. Note that in either case the
605 DatasetType is guaranteed to be defined in the Registry
606 consistently with the given definition.
608 Raises
609 ------
610 ValueError
611 Raised if the dimensions or storage class are invalid.
612 ConflictingDefinitionError
613 Raised if this DatasetType is already registered with a different
614 definition.
616 Notes
617 -----
618 This method cannot be called within transactions, as it needs to be
619 able to perform its own transaction to be concurrent.
620 """
621 _, inserted = self._managers.datasets.register(datasetType)
622 return inserted
624 def removeDatasetType(self, name: str) -> None:
625 """Remove the named `DatasetType` from the registry.
627 .. warning::
629 Registry caches the dataset type definitions. This means that
630 deleting the dataset type definition may result in unexpected
631 behavior from other butler processes that are active that have
632 not seen the deletion.
634 Parameters
635 ----------
636 name : `str`
637 Name of the type to be removed.
639 Raises
640 ------
641 lsst.daf.butler.registry.OrphanedRecordError
642 Raised if an attempt is made to remove the dataset type definition
643 when there are already datasets associated with it.
645 Notes
646 -----
647 If the dataset type is not registered the method will return without
648 action.
649 """
650 self._managers.datasets.remove(name)
652 def getDatasetType(self, name: str) -> DatasetType:
653 """Get the `DatasetType`.
655 Parameters
656 ----------
657 name : `str`
658 Name of the type.
660 Returns
661 -------
662 type : `DatasetType`
663 The `DatasetType` associated with the given name.
665 Raises
666 ------
667 KeyError
668 Requested named DatasetType could not be found in registry.
669 """
670 return self._managers.datasets[name].datasetType
672 def findDataset(self, datasetType: Union[DatasetType, str], dataId: Optional[DataId] = None, *,
673 collections: Any = None, timespan: Optional[Timespan] = None,
674 **kwargs: Any) -> Optional[DatasetRef]:
675 """Find a dataset given its `DatasetType` and data ID.
677 This can be used to obtain a `DatasetRef` that permits the dataset to
678 be read from a `Datastore`. If the dataset is a component and can not
679 be found using the provided dataset type, a dataset ref for the parent
680 will be returned instead but with the correct dataset type.
682 Parameters
683 ----------
684 datasetType : `DatasetType` or `str`
685 A `DatasetType` or the name of one.
686 dataId : `dict` or `DataCoordinate`, optional
687 A `dict`-like object containing the `Dimension` links that identify
688 the dataset within a collection.
689 collections, optional.
690 An expression that fully or partially identifies the collections to
691 search for the dataset; see
692 :ref:`daf_butler_collection_expressions` for more information.
693 Defaults to ``self.defaults.collections``.
694 timespan : `Timespan`, optional
695 A timespan that the validity range of the dataset must overlap.
696 If not provided, any `~CollectionType.CALIBRATION` collections
697 matched by the ``collections`` argument will not be searched.
698 **kwargs
699 Additional keyword arguments passed to
700 `DataCoordinate.standardize` to convert ``dataId`` to a true
701 `DataCoordinate` or augment an existing one.
703 Returns
704 -------
705 ref : `DatasetRef`
706 A reference to the dataset, or `None` if no matching Dataset
707 was found.
709 Raises
710 ------
711 TypeError
712 Raised if ``collections`` is `None` and
713 ``self.defaults.collections`` is `None`.
714 LookupError
715 Raised if one or more data ID keys are missing.
716 KeyError
717 Raised if the dataset type does not exist.
718 MissingCollectionError
719 Raised if any of ``collections`` does not exist in the registry.
721 Notes
722 -----
723 This method simply returns `None` and does not raise an exception even
724 when the set of collections searched is intrinsically incompatible with
725 the dataset type, e.g. if ``datasetType.isCalibration() is False``, but
726 only `~CollectionType.CALIBRATION` collections are being searched.
727 This may make it harder to debug some lookup failures, but the behavior
728 is intentional; we consider it more important that failed searches are
729 reported consistently, regardless of the reason, and that adding
730 additional collections that do not contain a match to the search path
731 never changes the behavior.
732 """
733 if isinstance(datasetType, DatasetType):
734 storage = self._managers.datasets[datasetType.name]
735 else:
736 storage = self._managers.datasets[datasetType]
737 dataId = DataCoordinate.standardize(dataId, graph=storage.datasetType.dimensions,
738 universe=self.dimensions, defaults=self.defaults.dataId,
739 **kwargs)
740 if collections is None:
741 if not self.defaults.collections:
742 raise TypeError("No collections provided to findDataset, "
743 "and no defaults from registry construction.")
744 collections = self.defaults.collections
745 else:
746 collections = CollectionSearch.fromExpression(collections)
747 for collectionRecord in collections.iter(self._managers.collections):
748 if (collectionRecord.type is CollectionType.CALIBRATION
749 and (not storage.datasetType.isCalibration() or timespan is None)):
750 continue
751 result = storage.find(collectionRecord, dataId, timespan=timespan)
752 if result is not None:
753 return result
755 return None
757 @transactional
758 def insertDatasets(self, datasetType: Union[DatasetType, str], dataIds: Iterable[DataId],
759 run: Optional[str] = None, expand: bool = True) -> List[DatasetRef]:
760 """Insert one or more datasets into the `Registry`
762 This always adds new datasets; to associate existing datasets with
763 a new collection, use ``associate``.
765 Parameters
766 ----------
767 datasetType : `DatasetType` or `str`
768 A `DatasetType` or the name of one.
769 dataIds : `~collections.abc.Iterable` of `dict` or `DataCoordinate`
770 Dimension-based identifiers for the new datasets.
771 run : `str`, optional
772 The name of the run that produced the datasets. Defaults to
773 ``self.defaults.run``.
774 expand : `bool`, optional
775 If `True` (default), expand data IDs as they are inserted. This is
776 necessary in general to allow datastore to generate file templates,
777 but it may be disabled if the caller can guarantee this is
778 unnecessary.
780 Returns
781 -------
782 refs : `list` of `DatasetRef`
783 Resolved `DatasetRef` instances for all given data IDs (in the same
784 order).
786 Raises
787 ------
788 TypeError
789 Raised if ``run`` is `None` and ``self.defaults.run`` is `None`.
790 ConflictingDefinitionError
791 If a dataset with the same dataset type and data ID as one of those
792 given already exists in ``run``.
793 MissingCollectionError
794 Raised if ``run`` does not exist in the registry.
795 """
796 if isinstance(datasetType, DatasetType):
797 storage = self._managers.datasets.find(datasetType.name)
798 if storage is None:
799 raise LookupError(f"DatasetType '{datasetType}' has not been registered.")
800 else:
801 storage = self._managers.datasets.find(datasetType)
802 if storage is None:
803 raise LookupError(f"DatasetType with name '{datasetType}' has not been registered.")
804 if run is None:
805 if self.defaults.run is None:
806 raise TypeError("No run provided to insertDatasets, "
807 "and no default from registry construction.")
808 run = self.defaults.run
809 runRecord = self._managers.collections.find(run)
810 if runRecord.type is not CollectionType.RUN:
811 raise TypeError(f"Given collection is of type {runRecord.type.name}; RUN collection required.")
812 assert isinstance(runRecord, RunRecord)
813 progress = Progress("daf.butler.Registry.insertDatasets", level=logging.DEBUG)
814 if expand:
815 expandedDataIds = [self.expandDataId(dataId, graph=storage.datasetType.dimensions)
816 for dataId in progress.wrap(dataIds,
817 f"Expanding {storage.datasetType.name} data IDs")]
818 else:
819 expandedDataIds = [DataCoordinate.standardize(dataId, graph=storage.datasetType.dimensions)
820 for dataId in dataIds]
821 try:
822 refs = list(storage.insert(runRecord, expandedDataIds))
823 except sqlalchemy.exc.IntegrityError as err:
824 raise ConflictingDefinitionError(f"A database constraint failure was triggered by inserting "
825 f"one or more datasets of type {storage.datasetType} into "
826 f"collection '{run}'. "
827 f"This probably means a dataset with the same data ID "
828 f"and dataset type already exists, but it may also mean a "
829 f"dimension row is missing.") from err
830 return refs
832 def getDataset(self, id: int) -> Optional[DatasetRef]:
833 """Retrieve a Dataset entry.
835 Parameters
836 ----------
837 id : `int`
838 The unique identifier for the dataset.
840 Returns
841 -------
842 ref : `DatasetRef` or `None`
843 A ref to the Dataset, or `None` if no matching Dataset
844 was found.
845 """
846 ref = self._managers.datasets.getDatasetRef(id)
847 if ref is None:
848 return None
849 return ref
851 @transactional
852 def removeDatasets(self, refs: Iterable[DatasetRef]) -> None:
853 """Remove datasets from the Registry.
855 The datasets will be removed unconditionally from all collections, and
856 any `Quantum` that consumed this dataset will instead be marked with
857 having a NULL input. `Datastore` records will *not* be deleted; the
858 caller is responsible for ensuring that the dataset has already been
859 removed from all Datastores.
861 Parameters
862 ----------
863 refs : `Iterable` of `DatasetRef`
864 References to the datasets to be removed. Must include a valid
865 ``id`` attribute, and should be considered invalidated upon return.
867 Raises
868 ------
869 AmbiguousDatasetError
870 Raised if any ``ref.id`` is `None`.
871 OrphanedRecordError
872 Raised if any dataset is still present in any `Datastore`.
873 """
874 progress = Progress("lsst.daf.butler.Registry.removeDatasets", level=logging.DEBUG)
875 for datasetType, refsForType in progress.iter_item_chunks(DatasetRef.groupByType(refs).items(),
876 desc="Removing datasets by type"):
877 storage = self._managers.datasets.find(datasetType.name)
878 assert storage is not None
879 try:
880 storage.delete(refsForType)
881 except sqlalchemy.exc.IntegrityError as err:
882 raise OrphanedRecordError("One or more datasets is still "
883 "present in one or more Datastores.") from err
885 @transactional
886 def associate(self, collection: str, refs: Iterable[DatasetRef]) -> None:
887 """Add existing datasets to a `~CollectionType.TAGGED` collection.
889 If a DatasetRef with the same exact integer ID is already in a
890 collection nothing is changed. If a `DatasetRef` with the same
891 `DatasetType` and data ID but with different integer ID
892 exists in the collection, `ConflictingDefinitionError` is raised.
894 Parameters
895 ----------
896 collection : `str`
897 Indicates the collection the datasets should be associated with.
898 refs : `Iterable` [ `DatasetRef` ]
899 An iterable of resolved `DatasetRef` instances that already exist
900 in this `Registry`.
902 Raises
903 ------
904 ConflictingDefinitionError
905 If a Dataset with the given `DatasetRef` already exists in the
906 given collection.
907 AmbiguousDatasetError
908 Raised if ``any(ref.id is None for ref in refs)``.
909 MissingCollectionError
910 Raised if ``collection`` does not exist in the registry.
911 TypeError
912 Raise adding new datasets to the given ``collection`` is not
913 allowed.
914 """
915 progress = Progress("lsst.daf.butler.Registry.associate", level=logging.DEBUG)
916 collectionRecord = self._managers.collections.find(collection)
917 if collectionRecord.type is not CollectionType.TAGGED:
918 raise TypeError(f"Collection '{collection}' has type {collectionRecord.type.name}, not TAGGED.")
919 for datasetType, refsForType in progress.iter_item_chunks(DatasetRef.groupByType(refs).items(),
920 desc="Associating datasets by type"):
921 storage = self._managers.datasets.find(datasetType.name)
922 assert storage is not None
923 try:
924 storage.associate(collectionRecord, refsForType)
925 except sqlalchemy.exc.IntegrityError as err:
926 raise ConflictingDefinitionError(
927 f"Constraint violation while associating dataset of type {datasetType.name} with "
928 f"collection {collection}. This probably means that one or more datasets with the same "
929 f"dataset type and data ID already exist in the collection, but it may also indicate "
930 f"that the datasets do not exist."
931 ) from err
933 @transactional
934 def disassociate(self, collection: str, refs: Iterable[DatasetRef]) -> None:
935 """Remove existing datasets from a `~CollectionType.TAGGED` collection.
937 ``collection`` and ``ref`` combinations that are not currently
938 associated are silently ignored.
940 Parameters
941 ----------
942 collection : `str`
943 The collection the datasets should no longer be associated with.
944 refs : `Iterable` [ `DatasetRef` ]
945 An iterable of resolved `DatasetRef` instances that already exist
946 in this `Registry`.
948 Raises
949 ------
950 AmbiguousDatasetError
951 Raised if any of the given dataset references is unresolved.
952 MissingCollectionError
953 Raised if ``collection`` does not exist in the registry.
954 TypeError
955 Raise adding new datasets to the given ``collection`` is not
956 allowed.
957 """
958 progress = Progress("lsst.daf.butler.Registry.disassociate", level=logging.DEBUG)
959 collectionRecord = self._managers.collections.find(collection)
960 if collectionRecord.type is not CollectionType.TAGGED:
961 raise TypeError(f"Collection '{collection}' has type {collectionRecord.type.name}; "
962 "expected TAGGED.")
963 for datasetType, refsForType in progress.iter_item_chunks(DatasetRef.groupByType(refs).items(),
964 desc="Disassociating datasets by type"):
965 storage = self._managers.datasets.find(datasetType.name)
966 assert storage is not None
967 storage.disassociate(collectionRecord, refsForType)
969 @transactional
970 def certify(self, collection: str, refs: Iterable[DatasetRef], timespan: Timespan) -> None:
971 """Associate one or more datasets with a calibration collection and a
972 validity range within it.
974 Parameters
975 ----------
976 collection : `str`
977 The name of an already-registered `~CollectionType.CALIBRATION`
978 collection.
979 refs : `Iterable` [ `DatasetRef` ]
980 Datasets to be associated.
981 timespan : `Timespan`
982 The validity range for these datasets within the collection.
984 Raises
985 ------
986 AmbiguousDatasetError
987 Raised if any of the given `DatasetRef` instances is unresolved.
988 ConflictingDefinitionError
989 Raised if the collection already contains a different dataset with
990 the same `DatasetType` and data ID and an overlapping validity
991 range.
992 TypeError
993 Raised if ``collection`` is not a `~CollectionType.CALIBRATION`
994 collection or if one or more datasets are of a dataset type for
995 which `DatasetType.isCalibration` returns `False`.
996 """
997 progress = Progress("lsst.daf.butler.Registry.certify", level=logging.DEBUG)
998 collectionRecord = self._managers.collections.find(collection)
999 for datasetType, refsForType in progress.iter_item_chunks(DatasetRef.groupByType(refs).items(),
1000 desc="Certifying datasets by type"):
1001 storage = self._managers.datasets[datasetType.name]
1002 storage.certify(collectionRecord, refsForType, timespan)
1004 @transactional
1005 def decertify(self, collection: str, datasetType: Union[str, DatasetType], timespan: Timespan, *,
1006 dataIds: Optional[Iterable[DataId]] = None) -> None:
1007 """Remove or adjust datasets to clear a validity range within a
1008 calibration collection.
1010 Parameters
1011 ----------
1012 collection : `str`
1013 The name of an already-registered `~CollectionType.CALIBRATION`
1014 collection.
1015 datasetType : `str` or `DatasetType`
1016 Name or `DatasetType` instance for the datasets to be decertified.
1017 timespan : `Timespan`, optional
1018 The validity range to remove datasets from within the collection.
1019 Datasets that overlap this range but are not contained by it will
1020 have their validity ranges adjusted to not overlap it, which may
1021 split a single dataset validity range into two.
1022 dataIds : `Iterable` [ `DataId` ], optional
1023 Data IDs that should be decertified within the given validity range
1024 If `None`, all data IDs for ``self.datasetType`` will be
1025 decertified.
1027 Raises
1028 ------
1029 TypeError
1030 Raised if ``collection`` is not a `~CollectionType.CALIBRATION`
1031 collection or if ``datasetType.isCalibration() is False``.
1032 """
1033 collectionRecord = self._managers.collections.find(collection)
1034 if isinstance(datasetType, str):
1035 storage = self._managers.datasets[datasetType]
1036 else:
1037 storage = self._managers.datasets[datasetType.name]
1038 standardizedDataIds = None
1039 if dataIds is not None:
1040 standardizedDataIds = [DataCoordinate.standardize(d, graph=storage.datasetType.dimensions)
1041 for d in dataIds]
1042 storage.decertify(collectionRecord, timespan, dataIds=standardizedDataIds)
1044 def getDatastoreBridgeManager(self) -> DatastoreRegistryBridgeManager:
1045 """Return an object that allows a new `Datastore` instance to
1046 communicate with this `Registry`.
1048 Returns
1049 -------
1050 manager : `DatastoreRegistryBridgeManager`
1051 Object that mediates communication between this `Registry` and its
1052 associated datastores.
1053 """
1054 return self._managers.datastores
1056 def getDatasetLocations(self, ref: DatasetRef) -> Iterable[str]:
1057 """Retrieve datastore locations for a given dataset.
1059 Parameters
1060 ----------
1061 ref : `DatasetRef`
1062 A reference to the dataset for which to retrieve storage
1063 information.
1065 Returns
1066 -------
1067 datastores : `Iterable` [ `str` ]
1068 All the matching datastores holding this dataset.
1070 Raises
1071 ------
1072 AmbiguousDatasetError
1073 Raised if ``ref.id`` is `None`.
1074 """
1075 return self._managers.datastores.findDatastores(ref)
1077 def expandDataId(self, dataId: Optional[DataId] = None, *, graph: Optional[DimensionGraph] = None,
1078 records: Optional[NameLookupMapping[DimensionElement, Optional[DimensionRecord]]] = None,
1079 withDefaults: bool = True,
1080 **kwargs: Any) -> DataCoordinate:
1081 """Expand a dimension-based data ID to include additional information.
1083 Parameters
1084 ----------
1085 dataId : `DataCoordinate` or `dict`, optional
1086 Data ID to be expanded; augmented and overridden by ``kwds``.
1087 graph : `DimensionGraph`, optional
1088 Set of dimensions for the expanded ID. If `None`, the dimensions
1089 will be inferred from the keys of ``dataId`` and ``kwds``.
1090 Dimensions that are in ``dataId`` or ``kwds`` but not in ``graph``
1091 are silently ignored, providing a way to extract and expand a
1092 subset of a data ID.
1093 records : `Mapping` [`str`, `DimensionRecord`], optional
1094 Dimension record data to use before querying the database for that
1095 data, keyed by element name.
1096 withDefaults : `bool`, optional
1097 Utilize ``self.defaults.dataId`` to fill in missing governor
1098 dimension key-value pairs. Defaults to `True` (i.e. defaults are
1099 used).
1100 **kwargs
1101 Additional keywords are treated like additional key-value pairs for
1102 ``dataId``, extending and overriding
1104 Returns
1105 -------
1106 expanded : `DataCoordinate`
1107 A data ID that includes full metadata for all of the dimensions it
1108 identifieds, i.e. guarantees that ``expanded.hasRecords()`` and
1109 ``expanded.hasFull()`` both return `True`.
1110 """
1111 if not withDefaults:
1112 defaults = None
1113 else:
1114 defaults = self.defaults.dataId
1115 standardized = DataCoordinate.standardize(dataId, graph=graph, universe=self.dimensions,
1116 defaults=defaults, **kwargs)
1117 if standardized.hasRecords():
1118 return standardized
1119 if records is None:
1120 records = {}
1121 elif isinstance(records, NamedKeyMapping):
1122 records = records.byName()
1123 else:
1124 records = dict(records)
1125 if isinstance(dataId, DataCoordinate) and dataId.hasRecords():
1126 records.update(dataId.records.byName())
1127 keys = standardized.byName()
1128 for element in standardized.graph.primaryKeyTraversalOrder:
1129 record = records.get(element.name, ...) # Use ... to mean not found; None might mean NULL
1130 if record is ...:
1131 if isinstance(element, Dimension) and keys.get(element.name) is None:
1132 if element in standardized.graph.required:
1133 raise LookupError(
1134 f"No value or null value for required dimension {element.name}."
1135 )
1136 keys[element.name] = None
1137 record = None
1138 else:
1139 storage = self._managers.dimensions[element]
1140 dataIdSet = DataCoordinateIterable.fromScalar(
1141 DataCoordinate.standardize(keys, graph=element.graph)
1142 )
1143 fetched = tuple(storage.fetch(dataIdSet))
1144 try:
1145 (record,) = fetched
1146 except ValueError:
1147 record = None
1148 records[element.name] = record
1149 if record is not None:
1150 for d in element.implied:
1151 value = getattr(record, d.name)
1152 if keys.setdefault(d.name, value) != value:
1153 raise InconsistentDataIdError(
1154 f"Data ID {standardized} has {d.name}={keys[d.name]!r}, "
1155 f"but {element.name} implies {d.name}={value!r}."
1156 )
1157 else:
1158 if element in standardized.graph.required:
1159 raise LookupError(
1160 f"Could not fetch record for required dimension {element.name} via keys {keys}."
1161 )
1162 if element.alwaysJoin:
1163 raise InconsistentDataIdError(
1164 f"Could not fetch record for element {element.name} via keys {keys}, ",
1165 "but it is marked alwaysJoin=True; this means one or more dimensions are not "
1166 "related."
1167 )
1168 for d in element.implied:
1169 keys.setdefault(d.name, None)
1170 records.setdefault(d.name, None)
1171 return DataCoordinate.standardize(keys, graph=standardized.graph).expanded(records=records)
1173 def insertDimensionData(self, element: Union[DimensionElement, str],
1174 *data: Union[Mapping[str, Any], DimensionRecord],
1175 conform: bool = True) -> None:
1176 """Insert one or more dimension records into the database.
1178 Parameters
1179 ----------
1180 element : `DimensionElement` or `str`
1181 The `DimensionElement` or name thereof that identifies the table
1182 records will be inserted into.
1183 data : `dict` or `DimensionRecord` (variadic)
1184 One or more records to insert.
1185 conform : `bool`, optional
1186 If `False` (`True` is default) perform no checking or conversions,
1187 and assume that ``element`` is a `DimensionElement` instance and
1188 ``data`` is a one or more `DimensionRecord` instances of the
1189 appropriate subclass.
1190 """
1191 if conform:
1192 if isinstance(element, str):
1193 element = self.dimensions[element]
1194 records = [row if isinstance(row, DimensionRecord) else element.RecordClass(**row)
1195 for row in data]
1196 else:
1197 # Ignore typing since caller said to trust them with conform=False.
1198 records = data # type: ignore
1199 storage = self._managers.dimensions[element] # type: ignore
1200 storage.insert(*records)
1202 def syncDimensionData(self, element: Union[DimensionElement, str],
1203 row: Union[Mapping[str, Any], DimensionRecord],
1204 conform: bool = True) -> bool:
1205 """Synchronize the given dimension record with the database, inserting
1206 if it does not already exist and comparing values if it does.
1208 Parameters
1209 ----------
1210 element : `DimensionElement` or `str`
1211 The `DimensionElement` or name thereof that identifies the table
1212 records will be inserted into.
1213 row : `dict` or `DimensionRecord`
1214 The record to insert.
1215 conform : `bool`, optional
1216 If `False` (`True` is default) perform no checking or conversions,
1217 and assume that ``element`` is a `DimensionElement` instance and
1218 ``data`` is a one or more `DimensionRecord` instances of the
1219 appropriate subclass.
1221 Returns
1222 -------
1223 inserted : `bool`
1224 `True` if a new row was inserted, `False` otherwise.
1226 Raises
1227 ------
1228 ConflictingDefinitionError
1229 Raised if the record exists in the database (according to primary
1230 key lookup) but is inconsistent with the given one.
1231 """
1232 if conform:
1233 if isinstance(element, str):
1234 element = self.dimensions[element]
1235 record = row if isinstance(row, DimensionRecord) else element.RecordClass(**row)
1236 else:
1237 # Ignore typing since caller said to trust them with conform=False.
1238 record = row # type: ignore
1239 storage = self._managers.dimensions[element] # type: ignore
1240 return storage.sync(record)
1242 def queryDatasetTypes(self, expression: Any = ..., *, components: Optional[bool] = None
1243 ) -> Iterator[DatasetType]:
1244 """Iterate over the dataset types whose names match an expression.
1246 Parameters
1247 ----------
1248 expression : `Any`, optional
1249 An expression that fully or partially identifies the dataset types
1250 to return, such as a `str`, `re.Pattern`, or iterable thereof.
1251 `...` can be used to return all dataset types, and is the default.
1252 See :ref:`daf_butler_dataset_type_expressions` for more
1253 information.
1254 components : `bool`, optional
1255 If `True`, apply all expression patterns to component dataset type
1256 names as well. If `False`, never apply patterns to components.
1257 If `None` (default), apply patterns to components only if their
1258 parent datasets were not matched by the expression.
1259 Fully-specified component datasets (`str` or `DatasetType`
1260 instances) are always included.
1262 Yields
1263 ------
1264 datasetType : `DatasetType`
1265 A `DatasetType` instance whose name matches ``expression``.
1266 """
1267 wildcard = CategorizedWildcard.fromExpression(expression, coerceUnrecognized=lambda d: d.name)
1268 if wildcard is Ellipsis:
1269 for datasetType in self._managers.datasets:
1270 # The dataset type can no longer be a component
1271 yield datasetType
1272 if components:
1273 # Automatically create the component dataset types
1274 try:
1275 componentsForDatasetType = datasetType.makeAllComponentDatasetTypes()
1276 except KeyError as err:
1277 _LOG.warning(f"Could not load storage class {err} for {datasetType.name}; "
1278 "if it has components they will not be included in query results.")
1279 else:
1280 yield from componentsForDatasetType
1281 return
1282 done: Set[str] = set()
1283 for name in wildcard.strings:
1284 storage = self._managers.datasets.find(name)
1285 if storage is not None:
1286 done.add(storage.datasetType.name)
1287 yield storage.datasetType
1288 if wildcard.patterns:
1289 # If components (the argument) is None, we'll save component
1290 # dataset that we might want to match, but only if their parents
1291 # didn't get included.
1292 componentsForLater = []
1293 for registeredDatasetType in self._managers.datasets:
1294 # Components are not stored in registry so expand them here
1295 allDatasetTypes = [registeredDatasetType]
1296 try:
1297 allDatasetTypes.extend(registeredDatasetType.makeAllComponentDatasetTypes())
1298 except KeyError as err:
1299 _LOG.warning(f"Could not load storage class {err} for {registeredDatasetType.name}; "
1300 "if it has components they will not be included in query results.")
1301 for datasetType in allDatasetTypes:
1302 if datasetType.name in done:
1303 continue
1304 parentName, componentName = datasetType.nameAndComponent()
1305 if componentName is not None and not components:
1306 if components is None and parentName not in done:
1307 componentsForLater.append(datasetType)
1308 continue
1309 if any(p.fullmatch(datasetType.name) for p in wildcard.patterns):
1310 done.add(datasetType.name)
1311 yield datasetType
1312 # Go back and try to match saved components.
1313 for datasetType in componentsForLater:
1314 parentName, _ = datasetType.nameAndComponent()
1315 if parentName not in done and any(p.fullmatch(datasetType.name) for p in wildcard.patterns):
1316 yield datasetType
1318 def queryCollections(self, expression: Any = ...,
1319 datasetType: Optional[DatasetType] = None,
1320 collectionTypes: Iterable[CollectionType] = CollectionType.all(),
1321 flattenChains: bool = False,
1322 includeChains: Optional[bool] = None) -> Iterator[str]:
1323 """Iterate over the collections whose names match an expression.
1325 Parameters
1326 ----------
1327 expression : `Any`, optional
1328 An expression that identifies the collections to return, such as a
1329 `str` (for full matches), `re.Pattern` (for partial matches), or
1330 iterable thereof. `...` can be used to return all collections,
1331 and is the default. See :ref:`daf_butler_collection_expressions`
1332 for more information.
1333 datasetType : `DatasetType`, optional
1334 If provided, only yield collections that may contain datasets of
1335 this type. This is a conservative approximation in general; it may
1336 yield collections that do not have any such datasets.
1337 collectionTypes : `AbstractSet` [ `CollectionType` ], optional
1338 If provided, only yield collections of these types.
1339 flattenChains : `bool`, optional
1340 If `True` (`False` is default), recursively yield the child
1341 collections of matching `~CollectionType.CHAINED` collections.
1342 includeChains : `bool`, optional
1343 If `True`, yield records for matching `~CollectionType.CHAINED`
1344 collections. Default is the opposite of ``flattenChains``: include
1345 either CHAINED collections or their children, but not both.
1347 Yields
1348 ------
1349 collection : `str`
1350 The name of a collection that matches ``expression``.
1351 """
1352 # Right now the datasetTypes argument is completely ignored, but that
1353 # is consistent with its [lack of] guarantees. DM-24939 or a follow-up
1354 # ticket will take care of that.
1355 query = CollectionQuery.fromExpression(expression)
1356 for record in query.iter(self._managers.collections, collectionTypes=frozenset(collectionTypes),
1357 flattenChains=flattenChains, includeChains=includeChains):
1358 yield record.name
1360 def makeQueryBuilder(self, summary: queries.QuerySummary) -> queries.QueryBuilder:
1361 """Return a `QueryBuilder` instance capable of constructing and
1362 managing more complex queries than those obtainable via `Registry`
1363 interfaces.
1365 This is an advanced interface; downstream code should prefer
1366 `Registry.queryDataIds` and `Registry.queryDatasets` whenever those
1367 are sufficient.
1369 Parameters
1370 ----------
1371 summary : `queries.QuerySummary`
1372 Object describing and categorizing the full set of dimensions that
1373 will be included in the query.
1375 Returns
1376 -------
1377 builder : `queries.QueryBuilder`
1378 Object that can be used to construct and perform advanced queries.
1379 """
1380 return queries.QueryBuilder(
1381 summary,
1382 queries.RegistryManagers(
1383 collections=self._managers.collections,
1384 dimensions=self._managers.dimensions,
1385 datasets=self._managers.datasets,
1386 TimespanReprClass=self._db.getTimespanRepresentation(),
1387 ),
1388 )
1390 def queryDatasets(self, datasetType: Any, *,
1391 collections: Any = None,
1392 dimensions: Optional[Iterable[Union[Dimension, str]]] = None,
1393 dataId: Optional[DataId] = None,
1394 where: Optional[str] = None,
1395 findFirst: bool = False,
1396 components: Optional[bool] = None,
1397 bind: Optional[Mapping[str, Any]] = None,
1398 check: bool = True,
1399 **kwargs: Any) -> queries.DatasetQueryResults:
1400 """Query for and iterate over dataset references matching user-provided
1401 criteria.
1403 Parameters
1404 ----------
1405 datasetType
1406 An expression that fully or partially identifies the dataset types
1407 to be queried. Allowed types include `DatasetType`, `str`,
1408 `re.Pattern`, and iterables thereof. The special value `...` can
1409 be used to query all dataset types. See
1410 :ref:`daf_butler_dataset_type_expressions` for more information.
1411 collections: optional
1412 An expression that identifies the collections to search, such as a
1413 `str` (for full matches), `re.Pattern` (for partial matches), or
1414 iterable thereof. `...` can be used to search all collections
1415 (actually just all `~CollectionType.RUN` collections, because this
1416 will still find all datasets). If not provided,
1417 ``self.default.collections`` is used. See
1418 :ref:`daf_butler_collection_expressions` for more information.
1419 dimensions : `~collections.abc.Iterable` of `Dimension` or `str`
1420 Dimensions to include in the query (in addition to those used
1421 to identify the queried dataset type(s)), either to constrain
1422 the resulting datasets to those for which a matching dimension
1423 exists, or to relate the dataset type's dimensions to dimensions
1424 referenced by the ``dataId`` or ``where`` arguments.
1425 dataId : `dict` or `DataCoordinate`, optional
1426 A data ID whose key-value pairs are used as equality constraints
1427 in the query.
1428 where : `str`, optional
1429 A string expression similar to a SQL WHERE clause. May involve
1430 any column of a dimension table or (as a shortcut for the primary
1431 key column of a dimension table) dimension name. See
1432 :ref:`daf_butler_dimension_expressions` for more information.
1433 findFirst : `bool`, optional
1434 If `True` (`False` is default), for each result data ID, only
1435 yield one `DatasetRef` of each `DatasetType`, from the first
1436 collection in which a dataset of that dataset type appears
1437 (according to the order of ``collections`` passed in). If `True`,
1438 ``collections`` must not contain regular expressions and may not
1439 be `...`.
1440 components : `bool`, optional
1441 If `True`, apply all dataset expression patterns to component
1442 dataset type names as well. If `False`, never apply patterns to
1443 components. If `None` (default), apply patterns to components only
1444 if their parent datasets were not matched by the expression.
1445 Fully-specified component datasets (`str` or `DatasetType`
1446 instances) are always included.
1447 bind : `Mapping`, optional
1448 Mapping containing literal values that should be injected into the
1449 ``where`` expression, keyed by the identifiers they replace.
1450 check : `bool`, optional
1451 If `True` (default) check the query for consistency before
1452 executing it. This may reject some valid queries that resemble
1453 common mistakes (e.g. queries for visits without specifying an
1454 instrument).
1455 **kwargs
1456 Additional keyword arguments are forwarded to
1457 `DataCoordinate.standardize` when processing the ``dataId``
1458 argument (and may be used to provide a constraining data ID even
1459 when the ``dataId`` argument is `None`).
1461 Returns
1462 -------
1463 refs : `queries.DatasetQueryResults`
1464 Dataset references matching the given query criteria. Nested data
1465 IDs are guaranteed to include values for all implied dimensions
1466 (i.e. `DataCoordinate.hasFull` will return `True`), but will not
1467 include dimension records (`DataCoordinate.hasRecords` will be
1468 `False`) unless `~queries.DatasetQueryResults.expanded` is called
1469 on the result object (which returns a new one).
1471 Raises
1472 ------
1473 TypeError
1474 Raised when the arguments are incompatible, such as when a
1475 collection wildcard is passed when ``findFirst`` is `True`, or
1476 when ``collections`` is `None` and``self.defaults.collections`` is
1477 also `None`.
1479 Notes
1480 -----
1481 When multiple dataset types are queried in a single call, the
1482 results of this operation are equivalent to querying for each dataset
1483 type separately in turn, and no information about the relationships
1484 between datasets of different types is included. In contexts where
1485 that kind of information is important, the recommended pattern is to
1486 use `queryDataIds` to first obtain data IDs (possibly with the
1487 desired dataset types and collections passed as constraints to the
1488 query), and then use multiple (generally much simpler) calls to
1489 `queryDatasets` with the returned data IDs passed as constraints.
1490 """
1491 # Standardize the collections expression.
1492 if collections is None:
1493 if not self.defaults.collections:
1494 raise TypeError("No collections provided to findDataset, "
1495 "and no defaults from registry construction.")
1496 collections = self.defaults.collections
1497 elif findFirst:
1498 collections = CollectionSearch.fromExpression(collections)
1499 else:
1500 collections = CollectionQuery.fromExpression(collections)
1501 # Standardize and expand the data ID provided as a constraint.
1502 standardizedDataId = self.expandDataId(dataId, **kwargs)
1504 # We can only query directly if given a non-component DatasetType
1505 # instance. If we were given an expression or str or a component
1506 # DatasetType instance, we'll populate this dict, recurse, and return.
1507 # If we already have a non-component DatasetType, it will remain None
1508 # and we'll run the query directly.
1509 composition: Optional[
1510 Dict[
1511 DatasetType, # parent dataset type
1512 List[Optional[str]] # component name, or None for parent
1513 ]
1514 ] = None
1515 if not isinstance(datasetType, DatasetType):
1516 # We were given a dataset type expression (which may be as simple
1517 # as a str). Loop over all matching datasets, delegating handling
1518 # of the `components` argument to queryDatasetTypes, as we populate
1519 # the composition dict.
1520 composition = defaultdict(list)
1521 for trueDatasetType in self.queryDatasetTypes(datasetType, components=components):
1522 parentName, componentName = trueDatasetType.nameAndComponent()
1523 if componentName is not None:
1524 parentDatasetType = self.getDatasetType(parentName)
1525 composition.setdefault(parentDatasetType, []).append(componentName)
1526 else:
1527 composition.setdefault(trueDatasetType, []).append(None)
1528 elif datasetType.isComponent():
1529 # We were given a true DatasetType instance, but it's a component.
1530 # the composition dict will have exactly one item.
1531 parentName, componentName = datasetType.nameAndComponent()
1532 parentDatasetType = self.getDatasetType(parentName)
1533 composition = {parentDatasetType: [componentName]}
1534 if composition is not None:
1535 # We need to recurse. Do that once for each parent dataset type.
1536 chain = []
1537 for parentDatasetType, componentNames in composition.items():
1538 parentResults = self.queryDatasets(
1539 parentDatasetType,
1540 collections=collections,
1541 dimensions=dimensions,
1542 dataId=standardizedDataId,
1543 where=where,
1544 findFirst=findFirst,
1545 check=check,
1546 )
1547 if isinstance(parentResults, queries.ParentDatasetQueryResults):
1548 chain.append(
1549 parentResults.withComponents(componentNames)
1550 )
1551 else:
1552 # Should only happen if we know there would be no results.
1553 assert isinstance(parentResults, queries.ChainedDatasetQueryResults) \
1554 and not parentResults._chain
1555 return queries.ChainedDatasetQueryResults(chain)
1556 # If we get here, there's no need to recurse (or we are already
1557 # recursing; there can only ever be one level of recursion).
1559 # The full set of dimensions in the query is the combination of those
1560 # needed for the DatasetType and those explicitly requested, if any.
1561 requestedDimensionNames = set(datasetType.dimensions.names)
1562 if dimensions is not None:
1563 requestedDimensionNames.update(self.dimensions.extract(dimensions).names)
1564 # Construct the summary structure needed to construct a QueryBuilder.
1565 summary = queries.QuerySummary(
1566 requested=DimensionGraph(self.dimensions, names=requestedDimensionNames),
1567 dataId=standardizedDataId,
1568 expression=where,
1569 bind=bind,
1570 defaults=self.defaults.dataId,
1571 check=check,
1572 )
1573 builder = self.makeQueryBuilder(summary)
1574 # Add the dataset subquery to the query, telling the QueryBuilder to
1575 # include the rank of the selected collection in the results only if we
1576 # need to findFirst. Note that if any of the collections are
1577 # actually wildcard expressions, and we've asked for deduplication,
1578 # this will raise TypeError for us.
1579 if not builder.joinDataset(datasetType, collections, isResult=True, findFirst=findFirst):
1580 return queries.ChainedDatasetQueryResults(())
1581 query = builder.finish()
1582 return queries.ParentDatasetQueryResults(self._db, query, components=[None])
1584 def queryDataIds(self, dimensions: Union[Iterable[Union[Dimension, str]], Dimension, str], *,
1585 dataId: Optional[DataId] = None,
1586 datasets: Any = None,
1587 collections: Any = None,
1588 where: Optional[str] = None,
1589 components: Optional[bool] = None,
1590 bind: Optional[Mapping[str, Any]] = None,
1591 check: bool = True,
1592 **kwargs: Any) -> queries.DataCoordinateQueryResults:
1593 """Query for data IDs matching user-provided criteria.
1595 Parameters
1596 ----------
1597 dimensions : `Dimension` or `str`, or iterable thereof
1598 The dimensions of the data IDs to yield, as either `Dimension`
1599 instances or `str`. Will be automatically expanded to a complete
1600 `DimensionGraph`.
1601 dataId : `dict` or `DataCoordinate`, optional
1602 A data ID whose key-value pairs are used as equality constraints
1603 in the query.
1604 datasets : `Any`, optional
1605 An expression that fully or partially identifies dataset types
1606 that should constrain the yielded data IDs. For example, including
1607 "raw" here would constrain the yielded ``instrument``,
1608 ``exposure``, ``detector``, and ``physical_filter`` values to only
1609 those for which at least one "raw" dataset exists in
1610 ``collections``. Allowed types include `DatasetType`, `str`,
1611 `re.Pattern`, and iterables thereof. Unlike other dataset type
1612 expressions, ``...`` is not permitted - it doesn't make sense to
1613 constrain data IDs on the existence of *all* datasets.
1614 See :ref:`daf_butler_dataset_type_expressions` for more
1615 information.
1616 collections: `Any`, optional
1617 An expression that identifies the collections to search for
1618 datasets, such as a `str` (for full matches), `re.Pattern` (for
1619 partial matches), or iterable thereof. `...` can be used to search
1620 all collections (actually just all `~CollectionType.RUN`
1621 collections, because this will still find all datasets). If not
1622 provided, ``self.default.collections`` is used. Ignored unless
1623 ``datasets`` is also passed. See
1624 :ref:`daf_butler_collection_expressions` for more information.
1625 where : `str`, optional
1626 A string expression similar to a SQL WHERE clause. May involve
1627 any column of a dimension table or (as a shortcut for the primary
1628 key column of a dimension table) dimension name. See
1629 :ref:`daf_butler_dimension_expressions` for more information.
1630 components : `bool`, optional
1631 If `True`, apply all dataset expression patterns to component
1632 dataset type names as well. If `False`, never apply patterns to
1633 components. If `None` (default), apply patterns to components only
1634 if their parent datasets were not matched by the expression.
1635 Fully-specified component datasets (`str` or `DatasetType`
1636 instances) are always included.
1637 bind : `Mapping`, optional
1638 Mapping containing literal values that should be injected into the
1639 ``where`` expression, keyed by the identifiers they replace.
1640 check : `bool`, optional
1641 If `True` (default) check the query for consistency before
1642 executing it. This may reject some valid queries that resemble
1643 common mistakes (e.g. queries for visits without specifying an
1644 instrument).
1645 **kwargs
1646 Additional keyword arguments are forwarded to
1647 `DataCoordinate.standardize` when processing the ``dataId``
1648 argument (and may be used to provide a constraining data ID even
1649 when the ``dataId`` argument is `None`).
1651 Returns
1652 -------
1653 dataIds : `DataCoordinateQueryResults`
1654 Data IDs matching the given query parameters. These are guaranteed
1655 to identify all dimensions (`DataCoordinate.hasFull` returns
1656 `True`), but will not contain `DimensionRecord` objects
1657 (`DataCoordinate.hasRecords` returns `False`). Call
1658 `DataCoordinateQueryResults.expanded` on the returned object to
1659 fetch those (and consider using
1660 `DataCoordinateQueryResults.materialize` on the returned object
1661 first if the expected number of rows is very large). See
1662 documentation for those methods for additional information.
1664 Raises
1665 ------
1666 TypeError
1667 Raised if ``collections`` is `None`, ``self.defaults.collections``
1668 is `None`, and ``datasets`` is not `None`.
1669 """
1670 dimensions = iterable(dimensions)
1671 standardizedDataId = self.expandDataId(dataId, **kwargs)
1672 standardizedDatasetTypes = set()
1673 requestedDimensions = self.dimensions.extract(dimensions)
1674 queryDimensionNames = set(requestedDimensions.names)
1675 if datasets is not None:
1676 if collections is None:
1677 if not self.defaults.collections:
1678 raise TypeError("Cannot pass 'datasets' without 'collections'.")
1679 collections = self.defaults.collections
1680 else:
1681 # Preprocess collections expression in case the original
1682 # included single-pass iterators (we'll want to use it multiple
1683 # times below).
1684 collections = CollectionQuery.fromExpression(collections)
1685 for datasetType in self.queryDatasetTypes(datasets, components=components):
1686 queryDimensionNames.update(datasetType.dimensions.names)
1687 # If any matched dataset type is a component, just operate on
1688 # its parent instead, because Registry doesn't know anything
1689 # about what components exist, and here (unlike queryDatasets)
1690 # we don't care about returning them.
1691 parentDatasetTypeName, componentName = datasetType.nameAndComponent()
1692 if componentName is not None:
1693 datasetType = self.getDatasetType(parentDatasetTypeName)
1694 standardizedDatasetTypes.add(datasetType)
1696 summary = queries.QuerySummary(
1697 requested=DimensionGraph(self.dimensions, names=queryDimensionNames),
1698 dataId=standardizedDataId,
1699 expression=where,
1700 bind=bind,
1701 defaults=self.defaults.dataId,
1702 check=check,
1703 )
1704 builder = self.makeQueryBuilder(summary)
1705 for datasetType in standardizedDatasetTypes:
1706 builder.joinDataset(datasetType, collections, isResult=False)
1707 query = builder.finish()
1708 return queries.DataCoordinateQueryResults(self._db, query)
1710 def queryDimensionRecords(self, element: Union[DimensionElement, str], *,
1711 dataId: Optional[DataId] = None,
1712 datasets: Any = None,
1713 collections: Any = None,
1714 where: Optional[str] = None,
1715 components: Optional[bool] = None,
1716 bind: Optional[Mapping[str, Any]] = None,
1717 check: bool = True,
1718 **kwargs: Any) -> Iterator[DimensionRecord]:
1719 """Query for dimension information matching user-provided criteria.
1721 Parameters
1722 ----------
1723 element : `DimensionElement` or `str`
1724 The dimension element to obtain records for.
1725 dataId : `dict` or `DataCoordinate`, optional
1726 A data ID whose key-value pairs are used as equality constraints
1727 in the query.
1728 datasets : `Any`, optional
1729 An expression that fully or partially identifies dataset types
1730 that should constrain the yielded records. See `queryDataIds` and
1731 :ref:`daf_butler_dataset_type_expressions` for more information.
1732 collections: `Any`, optional
1733 An expression that identifies the collections to search for
1734 datasets, such as a `str` (for full matches), `re.Pattern` (for
1735 partial matches), or iterable thereof. `...` can be used to search
1736 all collections (actually just all `~CollectionType.RUN`
1737 collections, because this will still find all datasets). If not
1738 provided, ``self.default.collections`` is used. Ignored unless
1739 ``datasets`` is also passed. See
1740 :ref:`daf_butler_collection_expressions` for more information.
1741 where : `str`, optional
1742 A string expression similar to a SQL WHERE clause. See
1743 `queryDataIds` and :ref:`daf_butler_dimension_expressions` for more
1744 information.
1745 components : `bool`, optional
1746 Whether to apply dataset expressions to components as well.
1747 See `queryDataIds` for more information.
1748 bind : `Mapping`, optional
1749 Mapping containing literal values that should be injected into the
1750 ``where`` expression, keyed by the identifiers they replace.
1751 check : `bool`, optional
1752 If `True` (default) check the query for consistency before
1753 executing it. This may reject some valid queries that resemble
1754 common mistakes (e.g. queries for visits without specifying an
1755 instrument).
1756 **kwargs
1757 Additional keyword arguments are forwarded to
1758 `DataCoordinate.standardize` when processing the ``dataId``
1759 argument (and may be used to provide a constraining data ID even
1760 when the ``dataId`` argument is `None`).
1762 Returns
1763 -------
1764 dataIds : `DataCoordinateQueryResults`
1765 Data IDs matching the given query parameters.
1766 """
1767 if not isinstance(element, DimensionElement):
1768 try:
1769 element = self.dimensions[element]
1770 except KeyError as e:
1771 raise KeyError(f"No such dimension '{element}', available dimensions: "
1772 + str(self.dimensions.getStaticElements())) from e
1773 dataIds = self.queryDataIds(element.graph, dataId=dataId, datasets=datasets, collections=collections,
1774 where=where, components=components, bind=bind, check=check, **kwargs)
1775 return iter(self._managers.dimensions[element].fetch(dataIds))
1777 def queryDatasetAssociations(
1778 self,
1779 datasetType: Union[str, DatasetType],
1780 collections: Any = ...,
1781 *,
1782 collectionTypes: Iterable[CollectionType] = CollectionType.all(),
1783 flattenChains: bool = False,
1784 ) -> Iterator[DatasetAssociation]:
1785 """Iterate over dataset-collection combinations where the dataset is in
1786 the collection.
1788 This method is a temporary placeholder for better support for
1789 assocation results in `queryDatasets`. It will probably be
1790 removed in the future, and should be avoided in production code
1791 whenever possible.
1793 Parameters
1794 ----------
1795 datasetType : `DatasetType` or `str`
1796 A dataset type object or the name of one.
1797 collections: `Any`, optional
1798 An expression that identifies the collections to search for
1799 datasets, such as a `str` (for full matches), `re.Pattern` (for
1800 partial matches), or iterable thereof. `...` can be used to search
1801 all collections (actually just all `~CollectionType.RUN`
1802 collections, because this will still find all datasets). If not
1803 provided, ``self.default.collections`` is used. See
1804 :ref:`daf_butler_collection_expressions` for more information.
1805 collectionTypes : `AbstractSet` [ `CollectionType` ], optional
1806 If provided, only yield associations from collections of these
1807 types.
1808 flattenChains : `bool`, optional
1809 If `True` (default) search in the children of
1810 `~CollectionType.CHAINED` collections. If `False`, ``CHAINED``
1811 collections are ignored.
1813 Yields
1814 ------
1815 association : `DatasetAssociation`
1816 Object representing the relationship beween a single dataset and
1817 a single collection.
1819 Raises
1820 ------
1821 TypeError
1822 Raised if ``collections`` is `None` and
1823 ``self.defaults.collections`` is `None`.
1824 """
1825 if collections is None:
1826 if not self.defaults.collections:
1827 raise TypeError("No collections provided to findDataset, "
1828 "and no defaults from registry construction.")
1829 collections = self.defaults.collections
1830 else:
1831 collections = CollectionQuery.fromExpression(collections)
1832 TimespanReprClass = self._db.getTimespanRepresentation()
1833 if isinstance(datasetType, str):
1834 storage = self._managers.datasets[datasetType]
1835 else:
1836 storage = self._managers.datasets[datasetType.name]
1837 for collectionRecord in collections.iter(self._managers.collections,
1838 collectionTypes=frozenset(collectionTypes),
1839 flattenChains=flattenChains):
1840 query = storage.select(collectionRecord)
1841 if query is None:
1842 continue
1843 for row in self._db.query(query.combine()):
1844 dataId = DataCoordinate.fromRequiredValues(
1845 storage.datasetType.dimensions,
1846 tuple(row[name] for name in storage.datasetType.dimensions.required.names)
1847 )
1848 runRecord = self._managers.collections[row[self._managers.collections.getRunForeignKeyName()]]
1849 ref = DatasetRef(storage.datasetType, dataId, id=row["id"], run=runRecord.name,
1850 conform=False)
1851 if collectionRecord.type is CollectionType.CALIBRATION:
1852 timespan = TimespanReprClass.extract(row)
1853 else:
1854 timespan = None
1855 yield DatasetAssociation(ref=ref, collection=collectionRecord.name, timespan=timespan)
1857 storageClasses: StorageClassFactory
1858 """All storage classes known to the registry (`StorageClassFactory`).
1859 """