Coverage for python/lsst/daf/butler/registry/queries/_query.py: 15%
250 statements
« prev ^ index » next coverage.py v7.3.2, created at 2023-12-05 11:07 +0000
« prev ^ index » next coverage.py v7.3.2, created at 2023-12-05 11:07 +0000
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 software is dual licensed under the GNU General Public License and also
10# under a 3-clause BSD license. Recipients may choose which of these licenses
11# to use; please see the files gpl-3.0.txt and/or bsd_license.txt,
12# respectively. If you choose the GPL option then the following text applies
13# (but note that there is still no warranty even if you opt for BSD instead):
14#
15# This program is free software: you can redistribute it and/or modify
16# it under the terms of the GNU General Public License as published by
17# the Free Software Foundation, either version 3 of the License, or
18# (at your option) any later version.
19#
20# This program is distributed in the hope that it will be useful,
21# but WITHOUT ANY WARRANTY; without even the implied warranty of
22# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23# GNU General Public License for more details.
24#
25# You should have received a copy of the GNU General Public License
26# along with this program. If not, see <http://www.gnu.org/licenses/>.
27from __future__ import annotations
29__all__ = ()
31import itertools
32from collections.abc import Iterable, Iterator, Mapping, Sequence, Set
33from contextlib import contextmanager
34from typing import Any, cast, final
36from lsst.daf.relation import ColumnError, ColumnTag, Diagnostics, Relation, Sort, SortTerm
38from ..._column_tags import DatasetColumnTag, DimensionKeyColumnTag, DimensionRecordColumnTag
39from ..._dataset_ref import DatasetRef
40from ..._dataset_type import DatasetType
41from ...dimensions import DataCoordinate, DimensionElement, DimensionGroup, DimensionRecord
42from .._collection_type import CollectionType
43from ..wildcards import CollectionWildcard
44from ._query_backend import QueryBackend
45from ._query_context import QueryContext
46from ._readers import DataCoordinateReader, DatasetRefReader, DimensionRecordReader
49@final
50class Query:
51 """A general-purpose representation of a registry query.
53 Parameters
54 ----------
55 dimensions : `DimensionGroup`
56 The dimensions that span the query and are used to join its relations
57 together.
58 backend : `QueryBackend`
59 Backend object used to create the query and new ones derived from it.
60 context : `QueryContext`
61 Context manager that holds relation engines and database connections
62 for the query.
63 relation : `Relation`
64 The relation tree representation of the query as a series of operations
65 on tables.
66 governor_constraints : `~collections.abc.Mapping` [ `str`, \
67 `~collections.abc.Set` [ `str` ] ]
68 Constraints on governor dimensions encoded in this query's relation.
69 This is a mapping from governor dimension name to sets of values that
70 dimension may take.
71 is_deferred : `bool`
72 If `True`, modifier methods that return a related `Query` object should
73 not immediately execute the new query.
74 has_record_columns : `bool` or `DimensionElement`
75 Whether this query's relation already includes columns for all or some
76 dimension element records: `True` means all elements in ``dimensions``
77 either have records present in ``record_caches`` or all columns present
78 in ``relation``, while a specific `DimensionElement` means that element
79 does.
80 record_caches : `~collections.abc.Mapping` [ `DimensionElement`, \
81 `~collections.abc.Mapping`
82 [ `DataCoordinate`, `DimensionRecord` ] ], optional
83 Cached dimension record values, organized first by dimension element
84 and then by data ID.
86 Notes
87 -----
88 Iterating over a `Query` yields mappings from `ColumnTag` to the associated
89 value for each row. The `iter_data_ids`, `iter_dataset_refs`, and
90 `iter_dimension_records` methods can be used to instead iterate over
91 various butler primitives derived from these rows.
93 Iterating over a `Query` may or may not execute database queries again each
94 time, depending on the state of its relation tree - see `Query.run` for
95 details.
97 Query is immutable; all methods that might appear to modify it in place
98 actually return a new object (though many attributes will be shared).
100 Query is currently (still) an internal-to-Registry object, with only the
101 "QueryResults" classes that are backed by it directly exposed to users. It
102 has been designed with the intent that it will eventually play a larger
103 role, either as the main query result object in a redesigned query
104 interface, or a "power user" result option that accompanies simpler
105 replacements for the current "QueryResults" objects.
106 """
108 def __init__(
109 self,
110 dimensions: DimensionGroup,
111 backend: QueryBackend[QueryContext],
112 context: QueryContext,
113 relation: Relation,
114 governor_constraints: Mapping[str, Set[str]],
115 is_deferred: bool,
116 has_record_columns: bool | DimensionElement,
117 record_caches: Mapping[DimensionElement, Mapping[DataCoordinate, DimensionRecord]] | None = None,
118 ):
119 self._dimensions = dimensions
120 self._backend = backend
121 self._context = context
122 self._relation = relation
123 self._governor_constraints = governor_constraints
124 self._is_deferred = is_deferred
125 self._has_record_columns = has_record_columns
126 self._record_caches = record_caches if record_caches is not None else {}
128 @property
129 def dimensions(self) -> DimensionGroup:
130 """The dimensions that span the query and are used to join its
131 relations together (`DimensionGroup`).
132 """
133 return self._dimensions
135 @property
136 def relation(self) -> Relation:
137 """The relation tree representation of the query as a series of
138 operations on tables (`Relation`).
139 """
140 return self._relation
142 @property
143 def has_record_columns(self) -> bool | DimensionElement:
144 """Whether this query's relation already includes columns for all or
145 some dimension element records (`bool` or `DimensionElement`).
146 """
147 return self._has_record_columns
149 @property
150 def backend(self) -> QueryBackend[QueryContext]:
151 """Backend object used to create the query and new ones derived from it
152 (`QueryBackend`).
153 """
154 return self._backend
156 @contextmanager
157 def open_context(self) -> Iterator[None]:
158 """Return a context manager that ensures a database connection is
159 established and temporary tables and cursors have a defined lifetime.
161 Returns
162 -------
163 context : `contextlib.AbstractContextManager`
164 Context manager with no return value.
165 """
166 if self._context.is_open:
167 yield
168 else:
169 with self._context:
170 yield
172 def __str__(self) -> str:
173 return str(self._relation)
175 def __iter__(self) -> Iterator[Mapping[ColumnTag, Any]]:
176 return iter(self._context.fetch_iterable(self._relation))
178 def iter_data_ids(self, dimensions: DimensionGroup | None = None) -> Iterator[DataCoordinate]:
179 """Return an iterator that converts result rows to data IDs.
181 Parameters
182 ----------
183 dimensions : `DimensionGroup`, optional
184 Dimensions of the data IDs to return. If not provided,
185 ``self.dimensions`` is used.
187 Returns
188 -------
189 data_ids : `~collections.abc.Iterator` [ `DataCoordinate` ]
190 Iterator that yields data IDs.
191 """
192 if dimensions is None:
193 dimensions = self._dimensions
194 reader = DataCoordinateReader.make(
195 dimensions, records=self._has_record_columns is True, record_caches=self._record_caches
196 )
197 if not (reader.columns_required <= self.relation.columns):
198 raise ColumnError(
199 f"Missing column(s) {set(reader.columns_required - self.relation.columns)} "
200 f"for data IDs with dimensions {dimensions}."
201 )
202 return (reader.read(row) for row in self)
204 def iter_dataset_refs(
205 self, dataset_type: DatasetType, components: Sequence[None | str] = (None,)
206 ) -> Iterator[DatasetRef]:
207 """Return an iterator that converts result rows to dataset references.
209 Parameters
210 ----------
211 dataset_type : `DatasetType`
212 The parent dataset type to yield references for.
213 components : `~collections.abc.Sequence` [ `None` or `str` ]
214 Which component dataset types to construct refs for from each row
215 representing a parent; `None` for the parent itself.
217 Returns
218 -------
219 refs : `~collections.abc.Iterator` [ `DatasetRef` ]
220 Iterator that yields (resolved) dataset references.
221 """
222 reader = DatasetRefReader(
223 dataset_type,
224 translate_collection=self._backend.get_collection_name,
225 records=self._has_record_columns is True,
226 record_caches=self._record_caches,
227 )
228 if not (reader.columns_required <= self.relation.columns):
229 raise ColumnError(
230 f"Missing column(s) {set(reader.columns_required - self.relation.columns)} "
231 f"for datasets with type {dataset_type.name} and dimensions {dataset_type.dimensions}."
232 )
233 for row in self:
234 parent_ref = reader.read(row)
235 for component in components:
236 if component is None:
237 yield parent_ref
238 else:
239 yield parent_ref.makeComponentRef(component)
241 def iter_data_ids_and_dataset_refs(
242 self, dataset_type: DatasetType, dimensions: DimensionGroup | None = None
243 ) -> Iterator[tuple[DataCoordinate, DatasetRef]]:
244 """Iterate over pairs of data IDs and dataset refs.
246 This permits the data ID dimensions to differ from the dataset
247 dimensions.
249 Parameters
250 ----------
251 dataset_type : `DatasetType`
252 The parent dataset type to yield references for.
253 dimensions : `DimensionGroup`, optional
254 Dimensions of the data IDs to return. If not provided,
255 ``self.dimensions`` is used.
257 Returns
258 -------
259 pairs : `~collections.abc.Iterable` [ `tuple` [ `DataCoordinate`,
260 `DatasetRef` ] ]
261 An iterator over (data ID, dataset reference) pairs.
262 """
263 if dimensions is None:
264 dimensions = self._dimensions
265 data_id_reader = DataCoordinateReader.make(
266 dimensions, records=self._has_record_columns is True, record_caches=self._record_caches
267 )
268 dataset_reader = DatasetRefReader(
269 dataset_type,
270 translate_collection=self._backend.get_collection_name,
271 records=self._has_record_columns is True,
272 record_caches=self._record_caches,
273 )
274 if not (data_id_reader.columns_required <= self.relation.columns):
275 raise ColumnError(
276 f"Missing column(s) {set(data_id_reader.columns_required - self.relation.columns)} "
277 f"for data IDs with dimensions {dimensions}."
278 )
279 if not (dataset_reader.columns_required <= self.relation.columns):
280 raise ColumnError(
281 f"Missing column(s) {set(dataset_reader.columns_required - self.relation.columns)} "
282 f"for datasets with type {dataset_type.name} and dimensions {dataset_type.dimensions}."
283 )
284 for row in self:
285 yield (data_id_reader.read(row), dataset_reader.read(row))
287 def iter_dimension_records(self, element: DimensionElement | None = None) -> Iterator[DimensionRecord]:
288 """Return an iterator that converts result rows to dimension records.
290 Parameters
291 ----------
292 element : `DimensionElement`, optional
293 Dimension element whose records will be returned. If not provided,
294 `has_record_columns` must be a `DimensionElement` instance.
296 Returns
297 -------
298 records : `~collections.abc.Iterator` [ `DimensionRecord` ]
299 Iterator that yields dimension records.
300 """
301 if element is None:
302 match self._has_record_columns:
303 case True | False:
304 raise ValueError("No default dimension element in query; 'element' must be given.")
305 case only_element_with_records:
306 element = only_element_with_records
307 if (cache := self._record_caches.get(element)) is not None:
308 return (cache[data_id] for data_id in self.iter_data_ids(element.minimal_group))
309 else:
310 reader = DimensionRecordReader(element)
311 if not (reader.columns_required <= self.relation.columns):
312 raise ColumnError(
313 f"Missing column(s) {set(reader.columns_required - self.relation.columns)} "
314 f"for records of element {element.name}."
315 )
316 return (reader.read(row) for row in self)
318 def run(self) -> Query:
319 """Execute the query and hold its results in memory.
321 Returns
322 -------
323 executed : `Query`
324 New query that holds the query results.
326 Notes
327 -----
328 Iterating over the results of a query that has been `run` will always
329 iterate over an existing container, while iterating over a query that
330 has not been run will result in executing at least some of the query
331 each time.
333 Running a query also sets its `is_deferred` flag to `False`, which will
334 cause new queries constructed by its methods to be run immediately,
335 unless ``defer=True`` is passed to the factory method. After a query
336 has been run, factory methods will also tend to prefer to apply new
337 operations (e.g. `with_only_column`, `sliced`, `sorted`) via Python
338 code acting on the existing container rather than going back to SQL,
339 which can be less efficient overall that applying operations to a
340 deferred query and executing them all only at the end.
342 Running a query is represented in terms of relations by adding a
343 `~lsst.daf.relation.Materialization` marker relation in the iteration
344 engine and then processing the relation tree; this attaches the
345 container of rows to that new relation to short-circuit any future
346 processing of the tree and lock changes to the tree upstream of it.
347 This is very different from the SQL-engine
348 `~lsst.daf.relation.Materialization` added to the tree by the
349 `materialize` method from a user perspective, though it has a similar
350 representation in the relation tree.
351 """
352 relation = (
353 # Make a new relation that definitely ends in the iteration engine
354 # (this does nothing if it already does).
355 self.relation.transferred_to(self._context.iteration_engine)
356 # Make the new relation save its rows to an in-memory Python
357 # collection in relation.payload when processed.
358 .materialized(name_prefix="run")
359 )
360 # Actually process the relation, simplifying out trivial relations,
361 # executing any SQL queries, and saving results to relation.payload.
362 # We discard the simplified relation that's returned, because we want
363 # the new query to have any extra diagnostic information contained in
364 # the original.
365 self._context.process(relation)
366 return self._copy(relation, False)
368 def materialized(self, defer_postprocessing: bool = True) -> Query:
369 """Materialize the results of this query in its context's preferred
370 engine.
372 Usually this means inserting the results into a temporary table in a
373 database.
375 Parameters
376 ----------
377 defer_postprocessing : `bool`, optional
378 If `True`, do not execute operations that occur in the context's
379 `QueryContext.iteration_engine` up front; instead insert and
380 execute a materialization upstream of them (e.g. via a a SQL
381 ``INSERT INTO ... SELECT`` statement, with no fetching to the
382 client) and execute the postprocessing operations when iterating
383 over the query results. If `False`, and iteration-engine
384 postprocessing operations exist, run the full query, execute them
385 now, and upload the results.
386 If the relation is already in the preferred engine, this option
387 is ignored and the materialization will not involve fetching rows
388 to the iteration engine at all. If the relation has already been
389 materialized in the iteration engine (i.e. via `run`), then this
390 option is again ignored and an upload of the existing rows will
391 be performed.
393 Returns
394 -------
395 materialized : `Query`
396 Modified query with the same row-and-column content with a
397 materialization in ``self.context.preferred_engine``.
398 """
399 if defer_postprocessing or self.relation.engine == self._context.preferred_engine:
400 relation, stripped = self._context.strip_postprocessing(self._relation)
401 if relation.engine == self._context.preferred_engine:
402 # We got all the way to the engine we want to materialize in.
403 # Apply that operation to the tree, process it (which actually
404 # creates a temporary table and populates it), and then reapply
405 # the stripped operations.
406 relation = relation.materialized()
407 self._context.process(relation)
408 for operation in stripped:
409 relation = operation.apply(
410 relation, transfer=True, preferred_engine=self._context.iteration_engine
411 )
412 return self._copy(relation, True)
413 # Either defer_postprocessing=False, or attempting to strip off unary
414 # operations until we got to the preferred engine didn't work, because
415 # this tree doesn't actually involve the preferred engine. So we just
416 # transfer to the preferred engine first, and then materialize,
417 # process, and return.
418 relation = self._relation.transferred_to(self._context.preferred_engine).materialized()
419 self._context.process(relation)
420 return self._copy(relation, True)
422 def projected(
423 self,
424 dimensions: DimensionGroup | Iterable[str] | None = None,
425 unique: bool = True,
426 columns: Iterable[ColumnTag] | None = None,
427 defer: bool | None = None,
428 drop_postprocessing: bool = False,
429 keep_record_columns: bool = True,
430 ) -> Query:
431 """Return a modified `Query` with a subset of this one's columns.
433 Parameters
434 ----------
435 dimensions : `~collections.abc.Iterable` [ `str` ],
436 optional
437 Dimensions to include in the new query. Will be expanded to
438 include all required and implied dependencies. Must be a subset of
439 ``self.dimensions``. If not provided, ``self.dimensions`` is used.
440 unique : `bool`, optional
441 If `True` (default) deduplicate rows after dropping columns.
442 columns : `~collections.abc.Iterable` [ `ColumnTag` ], optional
443 Additional dataset or dimension record columns to include in the
444 query. Dimension key columns added here are ignored unless they
445 extend beyond the key columns implied by the ``dimensions``
446 argument (which is an error).
447 defer : `bool`, optional
448 If `False`, run the new query immediately. If `True`, do not. If
449 `None` (default), the ``defer`` option passed when making ``self``
450 is used (this option is "sticky").
451 drop_postprocessing : `bool`, optional
452 Drop any iteration-engine operations that depend on columns that
453 are being removed (e.g. region-overlap tests when region columns
454 are being dropped), making it more likely that projection and
455 deduplication could be performed in the preferred engine, where
456 they may be more efficient.
457 keep_record_columns : `bool`, optional
458 If `True` (default) and this query `has_record_columns`, implicitly
459 add any of those to ``columns`` whose dimension element is in the
460 given ``dimensions``.
462 Returns
463 -------
464 query : `Query`
465 New query with the requested columns only, optionally deduplicated.
467 Notes
468 -----
469 Dataset columns are dropped from the new query unless passed via the
470 ``columns`` argument. All other columns are by default preserved.
472 Raises
473 ------
474 lsst.daf.relation.ColumnError
475 Raised if the columns to include in the new query are not all
476 present in the current query.
477 """
478 match dimensions:
479 case None:
480 dimensions = set(self._dimensions.names)
481 case DimensionGroup():
482 dimensions = set(dimensions.names)
483 case iterable:
484 dimensions = set(iterable)
485 if columns is not None:
486 dimensions.update(tag.dimension for tag in DimensionKeyColumnTag.filter_from(columns))
487 dimensions = self._dimensions.universe.conform(dimensions)
488 if columns is None:
489 columns = set()
490 else:
491 columns = set(columns)
492 columns.update(DimensionKeyColumnTag.generate(dimensions.names))
493 if keep_record_columns:
494 if self._has_record_columns is True:
495 for element_name in dimensions.elements:
496 if element_name not in self._record_caches:
497 columns.update(self.dimensions.universe[element_name].RecordClass.fields.columns)
498 elif self._has_record_columns in dimensions.elements:
499 element = cast(DimensionElement, self._has_record_columns)
500 columns.update(element.RecordClass.fields.columns)
501 if drop_postprocessing:
502 relation = self._context.drop_invalidated_postprocessing(self._relation, columns)
503 # Dropping postprocessing Calculations could cause other columns
504 # we had otherwise intended to keep to be dropped as well.
505 columns &= relation.columns
506 else:
507 relation = self._relation
508 relation = relation.with_only_columns(columns, preferred_engine=self._context.preferred_engine)
509 if unique:
510 relation = relation.without_duplicates(preferred_engine=self._context.preferred_engine)
511 return self._chain(relation, defer, dimensions=dimensions)
513 def with_record_columns(self, dimension_element: str | None = None, defer: bool | None = None) -> Query:
514 """Return a modified `Query` with additional dimension record columns
515 and/or caches.
517 Parameters
518 ----------
519 dimension_element : `str`, optional
520 Name of a single dimension element to add record columns for, or
521 `None` default to add them for all elements in `dimensions`.
522 defer : `bool`, optional
523 If `False`, run the new query immediately. If `True`, do not. If
524 `None` (default), the ``defer`` option passed when making ``self``
525 is used (this option is "sticky").
527 Returns
528 -------
529 query : `Query`
530 New query with the requested record columns either in the relation
531 or (when possible) available via record caching.
533 Notes
534 -----
535 Adding dimension record columns is fundamentally different from adding
536 new dimension key columns or dataset columns, because it is purely an
537 addition of columns, not rows - we can always join in a dimension
538 element table (if it has not already been included) on keys already
539 present in the current relation, confident that there is exactly one
540 row in the dimension element table for each row in the current
541 relation.
542 """
543 if self._has_record_columns is True or self._has_record_columns == dimension_element:
544 return self
545 record_caches = dict(self._record_caches)
546 columns_required: set[ColumnTag] = set()
547 for element_name in self.dimensions.elements if dimension_element is None else [dimension_element]:
548 element = self.dimensions.universe[element_name]
549 if element_name in record_caches:
550 continue
551 if (cache := self._backend.get_dimension_record_cache(element_name, self._context)) is not None:
552 record_caches[element] = cache
553 else:
554 columns_required.update(element.RecordClass.fields.columns.keys())
555 # Modify the relation we have to remove any projections that dropped
556 # columns we now want, as long the relation's behavior is otherwise
557 # unchanged.
558 columns_required -= self._relation.columns
559 relation, columns_found = self._context.restore_columns(self._relation, columns_required)
560 columns_required.difference_update(columns_found)
561 if columns_required:
562 relation = self._backend.make_dimension_relation(
563 self._dimensions,
564 columns_required,
565 self._context,
566 initial_relation=relation,
567 # Don't permit joins to use any columns beyond those in the
568 # original relation, as that would change what this operation
569 # does.
570 initial_join_max_columns=frozenset(self._relation.columns),
571 governor_constraints=self._governor_constraints,
572 )
573 return self._chain(
574 relation,
575 defer=defer,
576 has_record_columns=(
577 True if dimension_element is None else self.dimensions.universe[dimension_element]
578 ),
579 record_caches=record_caches,
580 )
582 def find_datasets(
583 self,
584 dataset_type: DatasetType,
585 collections: Any,
586 *,
587 find_first: bool = True,
588 columns: Set[str] = frozenset(("dataset_id", "run")),
589 defer: bool | None = None,
590 ) -> Query:
591 """Return a modified `Query` that includes a search for datasets of the
592 given type.
594 Parameters
595 ----------
596 dataset_type : `DatasetType`
597 Dataset type to search for. May not be a component.
598 collections
599 Collection search path or pattern. Must be a single collection
600 name or ordered sequence if ``find_first=True``. See
601 :ref:`daf_butler_collection_expressions` for more information.
602 find_first : `bool`, optional
603 If `True` (default) search collections in order until the first
604 match for each data ID is found. If `False`, return all matches in
605 all collections.
606 columns : `~collections.abc.Set` [ `str` ]
607 Dataset columns to include in the new query. Options include
609 - ``dataset_id``: the unique identifier of the dataset. The type
610 is implementation-dependent. Never nullable. Included by
611 default.
613 - ``ingest_date``: the date and time the dataset was added to the
614 data repository.
616 - ``run``: the foreign key column to the `~CollectionType.RUN`
617 collection holding the dataset (not necessarily the collection
618 name). The type is dependent on the collection manager
619 implementation. Included by default.
621 - ``collection``: the foreign key column to the collection type in
622 which the dataset was actually in this search. The type is
623 dependent on the collection manager implementation. This may
624 differ from ``run`` if the dataset is present in a matching
625 `~CollectionType.TAGGED` or `~CollectionType.CALIBRATION`
626 collection, which means the same dataset may also appear multiple
627 times in the query results.
629 - ``timespan``: the validity range for datasets found in a
630 `~CollectionType.CALIBRATION` collection, or ``NULL`` for other
631 collection types.
633 The default columns (``dataset_id`` and ``run``) are sufficient to
634 enable `iter_dataset_refs`, which also takes care of translating
635 the internal ``RUN`` collection key into its public name.
637 Setting this to an empty set while passing ``find_first=False``
638 will return a query that is constrained by dataset existence in
639 some matching collection that does not actually return which
640 datasets existed.
641 defer : `bool`, optional
642 If `False`, run the new query immediately. If `True`, do not. If
643 `None` (default), the ``defer`` option passed when making ``self``
644 is used (this option is "sticky").
646 Returns
647 -------
648 query : `Query`
649 New query with the requested dataset columns, constrained by the
650 existence of datasets of this type in the given collection.
652 Raises
653 ------
654 lsst.daf.relation.ColumnError
655 Raised if a dataset search is already present in this query and
656 this is a find-first search.
657 """
658 if find_first and DatasetColumnTag.filter_from(self._relation.columns):
659 raise ColumnError(
660 "Cannot search for datasets with find_first=True "
661 "on a query that already includes dataset columns."
662 )
663 #
664 # TODO: it'd be nice to do a QueryContext.restore_columns call here or
665 # similar, to look for dataset-constraint joins already present in the
666 # relation and expand them to include dataset-result columns as well,
667 # instead of doing a possibly-redundant join here. But that would
668 # require pushing relation usage down further into
669 # DatasetStorageManager.make_relation, so that it doesn't need to be
670 # given the columns, and then giving the relation system the ability to
671 # simplify-away redundant joins when they only provide columns that
672 # aren't ultimately used. The right time to look into that is probably
673 # when investigating whether the base QueryBackend should be
674 # responsible for producing an "abstract" relation tree of some sort,
675 # with the subclasses only responsible for filling it in with payloads
676 # (and possibly replacing some leaves with new sub-trees) during when
677 # "processed" (or in some other "prepare" step).
678 #
679 # This is a low priority for three reasons:
680 # - there's some chance the database's query optimizer will simplify
681 # away these redundant joins;
682 # - at present, the main use of this code path is in QG generation,
683 # where we materialize the initial data ID query into a temp table
684 # and hence can't go back and "recover" those dataset columns anyway;
685 #
686 collections = CollectionWildcard.from_expression(collections)
687 if find_first:
688 collections.require_ordered()
689 rejections: list[str] = []
690 collection_records = self._backend.resolve_dataset_collections(
691 dataset_type,
692 collections,
693 governor_constraints=self._governor_constraints,
694 allow_calibration_collections=True,
695 rejections=rejections,
696 )
697 # If the dataset type has dimensions not in the current query, or we
698 # need a temporal join for a calibration collection, either restore
699 # those columns or join them in.
700 full_dimensions = dataset_type.dimensions.as_group().union(self._dimensions)
701 relation = self._relation
702 record_caches = self._record_caches
703 base_columns_required: set[ColumnTag] = {
704 DimensionKeyColumnTag(name) for name in full_dimensions.names
705 }
706 spatial_joins: list[tuple[str, str]] = []
707 if not (dataset_type.dimensions <= self._dimensions):
708 if self._has_record_columns is True:
709 # This query is for expanded data IDs, so if we add new
710 # dimensions to the query we need to be able to get records for
711 # the new dimensions.
712 record_caches = dict(self._record_caches)
713 for element_name in full_dimensions.elements:
714 element = full_dimensions.universe[element_name]
715 if element in record_caches:
716 continue
717 if (
718 cache := self._backend.get_dimension_record_cache(element_name, self._context)
719 ) is not None:
720 record_caches[element] = cache
721 else:
722 base_columns_required.update(element.RecordClass.fields.columns.keys())
723 # See if we need spatial joins between the current query and the
724 # dataset type's dimensions. The logic here is for multiple
725 # spatial joins in general, but in practice it'll be exceedingly
726 # rare for there to be more than one. We start by figuring out
727 # which spatial "families" (observations vs. skymaps, skypix
728 # systems) are present on only one side and not the other.
729 lhs_spatial_families = self._dimensions.spatial - dataset_type.dimensions.spatial
730 rhs_spatial_families = dataset_type.dimensions.spatial - self._dimensions.spatial
731 # Now we iterate over the Cartesian product of those, so e.g.
732 # if the query has {tract, patch, visit} and the dataset type
733 # has {htm7} dimensions, the iterations of this loop
734 # correspond to: (skymap, htm), (observations, htm).
735 for lhs_spatial_family, rhs_spatial_family in itertools.product(
736 lhs_spatial_families, rhs_spatial_families
737 ):
738 # For each pair we add a join between the most-precise element
739 # present in each family (e.g. patch beats tract).
740 spatial_joins.append(
741 (
742 lhs_spatial_family.choose(
743 full_dimensions.elements.names, self.dimensions.universe
744 ).name,
745 rhs_spatial_family.choose(
746 full_dimensions.elements.names, self.dimensions.universe
747 ).name,
748 )
749 )
750 # Set up any temporal join between the query dimensions and CALIBRATION
751 # collection's validity ranges.
752 temporal_join_on: set[ColumnTag] = set()
753 if any(r.type is CollectionType.CALIBRATION for r in collection_records):
754 for family in self._dimensions.temporal:
755 endpoint = family.choose(self._dimensions.elements.names, self.dimensions.universe)
756 temporal_join_on.add(DimensionRecordColumnTag(endpoint.name, "timespan"))
757 base_columns_required.update(temporal_join_on)
758 # Note which of the many kinds of potentially-missing columns we have
759 # and add the rest.
760 base_columns_required.difference_update(relation.columns)
761 if base_columns_required:
762 relation = self._backend.make_dimension_relation(
763 full_dimensions,
764 base_columns_required,
765 self._context,
766 initial_relation=relation,
767 # Don't permit joins to use any columns beyond those in the
768 # original relation, as that would change what this
769 # operation does.
770 initial_join_max_columns=frozenset(self._relation.columns),
771 governor_constraints=self._governor_constraints,
772 spatial_joins=spatial_joins,
773 )
774 # Finally we can join in the search for the dataset query.
775 columns = set(columns)
776 columns.add("dataset_id")
777 if not collection_records:
778 relation = relation.join(
779 self._backend.make_doomed_dataset_relation(dataset_type, columns, rejections, self._context)
780 )
781 elif find_first:
782 relation = self._backend.make_dataset_search_relation(
783 dataset_type,
784 collection_records,
785 columns,
786 self._context,
787 join_to=relation,
788 temporal_join_on=temporal_join_on,
789 )
790 else:
791 relation = self._backend.make_dataset_query_relation(
792 dataset_type,
793 collection_records,
794 columns,
795 self._context,
796 join_to=relation,
797 temporal_join_on=temporal_join_on,
798 )
799 return self._chain(relation, dimensions=full_dimensions, record_caches=record_caches, defer=defer)
801 def sliced(
802 self,
803 start: int = 0,
804 stop: int | None = None,
805 defer: bool | None = None,
806 ) -> Query:
807 """Return a modified `Query` with that takes a slice of this one's
808 rows.
810 Parameters
811 ----------
812 start : `int`, optional
813 First index to include, inclusive.
814 stop : `int` or `None`, optional
815 One past the last index to include (i.e. exclusive).
816 defer : `bool`, optional
817 If `False`, run the new query immediately. If `True`, do not. If
818 `None` (default), the ``defer`` option passed when making ``self``
819 is used (this option is "sticky").
821 Returns
822 -------
823 query : `Query`
824 New query with the requested slice.
826 Notes
827 -----
828 This operation must be implemented in the iteration engine if there are
829 postprocessing operations, which may be much less efficient than
830 performing it in the preferred engine (e.g. via ``LIMIT .. OFFSET ..``
831 in SQL).
833 Since query row order is usually arbitrary, it usually makes sense to
834 call `sorted` before calling `sliced` to make the results
835 deterministic. This is not checked because there are some contexts
836 where getting an arbitrary subset of the results of a given size
837 still makes sense.
838 """
839 return self._chain(self._relation[start:stop], defer)
841 def sorted(
842 self,
843 order_by: Iterable[SortTerm],
844 defer: bool | None = None,
845 ) -> Query:
846 """Return a modified `Query` that sorts this one's rows.
848 Parameters
849 ----------
850 order_by : `~collections.abc.Iterable` [ `SortTerm` ]
851 Expressions to sort by.
852 defer : `bool`, optional
853 If `False`, run the new query immediately. If `True`, do not. If
854 `None` (default), the ``defer`` option passed when making ``self``
855 is used (this option is "sticky").
857 Returns
858 -------
859 query : `Query`
860 New query with the requested sorting.
862 Notes
863 -----
864 The ``order_by`` expression can include references to dimension record
865 columns that were not present in the original relation; this is
866 similar to calling `with_record_columns` for those columns first (but
867 in this case column requests cannot be satisfied by record caches).
868 All other columns referenced must be present in the query already.
869 """
870 op = Sort(tuple(order_by))
871 columns_required = set(op.columns_required)
872 columns_required.difference_update(self._relation.columns)
873 if columns_required:
874 relation, columns_found = self._context.restore_columns(self._relation, columns_required)
875 columns_required.difference_update(columns_found)
876 if columns_required:
877 try:
878 relation = self._backend.make_dimension_relation(
879 self._dimensions,
880 columns_required,
881 self._context,
882 initial_relation=relation,
883 # Don't permit joins to use any columns beyond those in
884 # the original relation, as that would change what this
885 # operation does.
886 initial_join_max_columns=frozenset(self._relation.columns),
887 governor_constraints=self._governor_constraints,
888 )
889 except ColumnError as err:
890 raise ColumnError(
891 "Cannot sort by columns that were not included in the original query or "
892 "fully resolved by its dimensions."
893 ) from err
894 else:
895 relation = self._relation
896 relation = op.apply(relation, preferred_engine=self._context.preferred_engine)
897 return self._chain(relation, defer)
899 def count(self, *, exact: bool = True, discard: bool = False) -> int:
900 """Count the number of rows in this query.
902 Parameters
903 ----------
904 exact : `bool`, optional
905 If `True` (default), return the exact number of rows. If `False`,
906 returning an upper bound is permitted if it can be done much more
907 efficiently, e.g. by running a SQL ``SELECT COUNT(*)`` query but
908 ignoring client-side filtering that would otherwise take place.
909 discard : `bool`, optional
910 If `True`, compute the exact count even if it would require running
911 the full query and then throwing away the result rows after
912 counting them. If `False`, this is an error, as the user would
913 usually be better off executing the query first to fetch its rows
914 into a new query (or passing ``exact=False``). Ignored if
915 ``exact=False``.
917 Returns
918 -------
919 n_rows : `int`
920 Number of rows in the query, or an upper bound. This includes
921 duplicates, if there are any.
923 Raises
924 ------
925 RuntimeError
926 Raised if an exact count was requested and could not be obtained
927 without fetching and discarding rows.
928 """
929 if self._relation.min_rows == self._relation.max_rows:
930 return self._relation.max_rows
931 return self._context.count(self._relation, exact=exact, discard=discard)
933 def any(self, *, execute: bool = True, exact: bool = True) -> bool:
934 """Check whether this query has any result rows at all.
936 Parameters
937 ----------
938 execute : `bool`, optional
939 If `True`, execute at least a ``LIMIT 1`` query if it cannot be
940 determined prior to execution that the query would return no rows.
941 exact : `bool`, optional
942 If `True`, run the full query and perform post-query filtering if
943 needed, until at least one result row is found. If `False`, the
944 returned result does not account for post-query filtering, and
945 hence may be `True` even when all result rows would be filtered
946 out.
948 Returns
949 -------
950 any_rows : `bool`
951 Whether the query has any rows, or if it may have any rows if
952 ``exact=False``.
954 Raises
955 ------
956 RuntimeError
957 Raised if an exact check was requested and could not be obtained
958 without executing the query.
959 """
960 if self._relation.min_rows > 0:
961 return True
962 if self._relation.max_rows == 0:
963 return False
964 if execute:
965 return self._context.any(self._relation, execute=execute, exact=exact)
966 elif not exact:
967 return True
968 raise TypeError("Cannot obtain exact results without executing the query.")
970 def explain_no_results(self, execute: bool = True) -> list[str]:
971 """Return human-readable messages that may help explain why the query
972 yields no results.
974 Parameters
975 ----------
976 execute : `bool`, optional
977 If `True` (default) execute simplified versions (e.g. ``LIMIT 1``)
978 of aspects of the query to more precisely determine where rows were
979 filtered out.
981 Returns
982 -------
983 messages : `~collections.abc.Iterable` [ `str` ]
984 String messages that describe reasons the query might not yield any
985 results.
986 """
987 # First try without actually executing any queries.
988 diagnostics = Diagnostics.run(self._relation)
989 if diagnostics.is_doomed:
990 return diagnostics.messages
991 if execute:
992 # Try again, running LIMIT 1 queries as we walk back down the tree
993 # to look for relations with no rows:
994 diagnostics = Diagnostics.run(self._relation, executor=self._context.any)
995 if diagnostics.is_doomed:
996 return diagnostics.messages
997 return []
999 def _copy(
1000 self,
1001 relation: Relation,
1002 is_deferred: bool,
1003 dimensions: DimensionGroup | None = None,
1004 governor_constraints: Mapping[str, Set[str]] | None = None,
1005 has_record_columns: bool | DimensionElement | None = None,
1006 record_caches: Mapping[DimensionElement, Mapping[DataCoordinate, DimensionRecord]] | None = None,
1007 ) -> Query:
1008 """Return a modified copy of this query with some attributes replaced.
1010 See class docs for parameter documentation; the only difference here
1011 is that the defaults are the values ``self`` was constructed with.
1012 """
1013 return Query(
1014 dimensions=self._dimensions if dimensions is None else dimensions,
1015 backend=self._backend,
1016 context=self._context,
1017 relation=relation,
1018 governor_constraints=(
1019 governor_constraints if governor_constraints is not None else self._governor_constraints
1020 ),
1021 is_deferred=is_deferred,
1022 has_record_columns=self._has_record_columns if has_record_columns is None else has_record_columns,
1023 record_caches=self._record_caches if record_caches is None else record_caches,
1024 )
1026 def _chain(
1027 self,
1028 relation: Relation,
1029 defer: bool | None,
1030 dimensions: DimensionGroup | None = None,
1031 governor_constraints: Mapping[str, Set[str]] | None = None,
1032 has_record_columns: bool | DimensionElement | None = None,
1033 record_caches: Mapping[DimensionElement, Mapping[DataCoordinate, DimensionRecord]] | None = None,
1034 ) -> Query:
1035 """Return a modified query with a new relation while handling the
1036 ubiquitous ``defer`` parameter's logic.
1038 Parameters
1039 ----------
1040 relation : `Relation`
1041 Relation for the new query.
1042 defer : `bool`
1043 If `False`, run the new query immediately. If `True`, do not. If
1044 `None` , the ``defer`` option passed when making ``self`` is used
1045 (this option is "sticky").
1046 dimensions : `DimensionGroup`, optional
1047 See class docs.
1048 governor_constraints : `~collections.abc.Mapping` [ `str`, \
1049 `~collections.abc.Set` [ `str` ] ], optional
1050 See class docs.
1051 has_record_columns : `bool` or `DimensionElement`, optional
1052 See class docs.
1053 record_caches : `~collections.abc.Mapping` [ `DimensionElement`, \
1054 `~collections.abc.Mapping` \
1055 [ `DataCoordinate`, `DimensionRecord` ] ], optional
1056 See class docs.
1058 Returns
1059 -------
1060 chained : `Query`
1061 Modified query, or ``self`` if no modifications were actually
1062 requested.
1063 """
1064 if defer is None:
1065 defer = self._is_deferred
1066 if (
1067 relation is self._relation
1068 and dimensions is None
1069 and defer == self._is_deferred
1070 and record_caches is None
1071 and has_record_columns is None
1072 and governor_constraints is None
1073 ):
1074 return self
1075 result = self._copy(
1076 relation,
1077 is_deferred=True,
1078 governor_constraints=governor_constraints,
1079 dimensions=dimensions,
1080 has_record_columns=has_record_columns,
1081 record_caches=record_caches,
1082 )
1083 if not defer:
1084 result = result.run()
1085 return result