Coverage for python/lsst/daf/butler/_quantum_backed.py: 32%

184 statements  

« prev     ^ index     » next       coverage.py v7.2.7, created at 2023-08-05 01:26 +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 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/>. 

21 

22from __future__ import annotations 

23 

24__all__ = ("QuantumBackedButler", "QuantumProvenanceData") 

25 

26import itertools 

27import logging 

28import uuid 

29from collections import defaultdict 

30from collections.abc import Iterable, Mapping 

31from typing import TYPE_CHECKING, Any 

32 

33from deprecated.sphinx import deprecated 

34from lsst.daf.butler._compat import _BaseModelCompat 

35from lsst.resources import ResourcePathExpression 

36 

37from ._butlerConfig import ButlerConfig 

38from ._deferredDatasetHandle import DeferredDatasetHandle 

39from ._limited_butler import LimitedButler 

40from .core import ( 

41 Config, 

42 DatasetId, 

43 DatasetRef, 

44 DatasetType, 

45 Datastore, 

46 DatastoreRecordData, 

47 DimensionUniverse, 

48 Quantum, 

49 SerializedDatastoreRecordData, 

50 StorageClass, 

51 StorageClassFactory, 

52 ddl, 

53) 

54from .registry.bridge.monolithic import MonolithicDatastoreRegistryBridgeManager 

55from .registry.databases.sqlite import SqliteDatabase 

56from .registry.interfaces import DatastoreRegistryBridgeManager, OpaqueTableStorageManager 

57from .registry.opaque import ByNameOpaqueTableStorageManager 

58 

59if TYPE_CHECKING: 

60 from ._butler import Butler 

61 

62_LOG = logging.getLogger(__name__) 

63 

64 

65class _DatasetRecordStorageManagerDatastoreConstructionMimic: 

66 """A partial implementation of `DatasetRecordStorageManager` that exists 

67 only to allow a `DatastoreRegistryBridgeManager` (and hence a `Datastore`) 

68 to be constructed without a full `Registry`. 

69 

70 Notes 

71 ----- 

72 The interface implemented by this class should probably be its own ABC, 

73 and that ABC should probably be used in the definition of 

74 `DatastoreRegistryBridgeManager`, but while prototyping I'm trying to keep 

75 changes minimal. 

76 """ 

77 

78 @classmethod 

79 def getIdColumnType(cls) -> type: 

80 # Docstring inherited. 

81 return ddl.GUID 

82 

83 @classmethod 

84 def addDatasetForeignKey( 

85 cls, 

86 tableSpec: ddl.TableSpec, 

87 *, 

88 name: str = "dataset", 

89 constraint: bool = True, 

90 onDelete: str | None = None, 

91 **kwargs: Any, 

92 ) -> ddl.FieldSpec: 

93 # Docstring inherited. 

94 idFieldSpec = ddl.FieldSpec(f"{name}_id", dtype=ddl.GUID, **kwargs) 

95 tableSpec.fields.add(idFieldSpec) 

96 return idFieldSpec 

97 

98 

99class QuantumBackedButler(LimitedButler): 

100 """An implementation of `LimitedButler` intended to back execution of a 

101 single `Quantum`. 

102 

103 Parameters 

104 ---------- 

105 predicted_inputs : `~collections.abc.Iterable` [`DatasetId`] 

106 Dataset IDs for datasets that can can be read from this butler. 

107 predicted_outputs : `~collections.abc.Iterable` [`DatasetId`] 

108 Dataset IDs for datasets that can be stored in this butler. 

109 dimensions : `DimensionUniverse` 

110 Object managing all dimension definitions. 

111 datastore : `Datastore` 

112 Datastore to use for all dataset I/O and existence checks. 

113 storageClasses : `StorageClassFactory` 

114 Object managing all storage class definitions. 

115 

116 Notes 

117 ----- 

118 Most callers should use the `initialize` `classmethod` to construct new 

119 instances instead of calling the constructor directly. 

120 

121 `QuantumBackedButler` uses a SQLite database internally, in order to reuse 

122 existing `DatastoreRegistryBridge` and `OpaqueTableStorage` 

123 implementations that rely SQLAlchemy. If implementations are added in the 

124 future that don't rely on SQLAlchemy, it should be possible to swap them 

125 in by overriding the type arguments to `initialize` (though at present, 

126 `QuantumBackedButler` would still create at least an in-memory SQLite 

127 database that would then go unused).` 

128 

129 We imagine `QuantumBackedButler` being used during (at least) batch 

130 execution to capture `Datastore` records and save them to per-quantum 

131 files, which are also a convenient place to store provenance for eventual 

132 upload to a SQL-backed `Registry` (once `Registry` has tables to store 

133 provenance, that is). 

134 These per-quantum files can be written in two ways: 

135 

136 - The SQLite file used internally by `QuantumBackedButler` can be used 

137 directly but customizing the ``filename`` argument to ``initialize``, and 

138 then transferring that file to the object store after execution completes 

139 (or fails; a ``try/finally`` pattern probably makes sense here). 

140 

141 - A JSON or YAML file can be written by calling `extract_provenance_data`, 

142 and using ``pydantic`` methods to write the returned 

143 `QuantumProvenanceData` to a file. 

144 

145 Note that at present, the SQLite file only contains datastore records, not 

146 provenance, but that should be easy to address (if desired) after we 

147 actually design a `Registry` schema for provenance. I also suspect that 

148 we'll want to explicitly close the SQLite file somehow before trying to 

149 transfer it. But I'm guessing we'd prefer to write the per-quantum files 

150 as JSON anyway. 

151 """ 

152 

153 def __init__( 

154 self, 

155 predicted_inputs: Iterable[DatasetId], 

156 predicted_outputs: Iterable[DatasetId], 

157 dimensions: DimensionUniverse, 

158 datastore: Datastore, 

159 storageClasses: StorageClassFactory, 

160 dataset_types: Mapping[str, DatasetType] | None = None, 

161 ): 

162 self._dimensions = dimensions 

163 self._predicted_inputs = set(predicted_inputs) 

164 self._predicted_outputs = set(predicted_outputs) 

165 self._available_inputs: set[DatasetId] = set() 

166 self._unavailable_inputs: set[DatasetId] = set() 

167 self._actual_inputs: set[DatasetId] = set() 

168 self._actual_output_refs: set[DatasetRef] = set() 

169 self._datastore = datastore 

170 self.storageClasses = storageClasses 

171 self._dataset_types: Mapping[str, DatasetType] = {} 

172 if dataset_types is not None: 

173 self._dataset_types = dataset_types 

174 self._datastore.set_retrieve_dataset_type_method(self._retrieve_dataset_type) 

175 

176 @classmethod 

177 def initialize( 

178 cls, 

179 config: Config | ResourcePathExpression, 

180 quantum: Quantum, 

181 dimensions: DimensionUniverse, 

182 filename: str = ":memory:", 

183 OpaqueManagerClass: type[OpaqueTableStorageManager] = ByNameOpaqueTableStorageManager, 

184 BridgeManagerClass: type[DatastoreRegistryBridgeManager] = MonolithicDatastoreRegistryBridgeManager, 

185 search_paths: list[str] | None = None, 

186 dataset_types: Mapping[str, DatasetType] | None = None, 

187 ) -> QuantumBackedButler: 

188 """Construct a new `QuantumBackedButler` from repository configuration 

189 and helper types. 

190 

191 Parameters 

192 ---------- 

193 config : `Config` or `~lsst.resources.ResourcePathExpression` 

194 A butler repository root, configuration filename, or configuration 

195 instance. 

196 quantum : `Quantum` 

197 Object describing the predicted input and output dataset relevant 

198 to this butler. This must have resolved `DatasetRef` instances for 

199 all inputs and outputs. 

200 dimensions : `DimensionUniverse` 

201 Object managing all dimension definitions. 

202 filename : `str`, optional 

203 Name for the SQLite database that will back this butler; defaults 

204 to an in-memory database. 

205 OpaqueManagerClass : `type`, optional 

206 A subclass of `OpaqueTableStorageManager` to use for datastore 

207 opaque records. Default is a SQL-backed implementation. 

208 BridgeManagerClass : `type`, optional 

209 A subclass of `DatastoreRegistryBridgeManager` to use for datastore 

210 location records. Default is a SQL-backed implementation. 

211 search_paths : `list` of `str`, optional 

212 Additional search paths for butler configuration. 

213 dataset_types: `~collections.abc.Mapping` [`str`, `DatasetType`], \ 

214 optional 

215 Mapping of the dataset type name to its registry definition. 

216 """ 

217 predicted_inputs = [ref.id for ref in itertools.chain.from_iterable(quantum.inputs.values())] 

218 predicted_inputs += [ref.id for ref in quantum.initInputs.values()] 

219 predicted_outputs = [ref.id for ref in itertools.chain.from_iterable(quantum.outputs.values())] 

220 return cls._initialize( 

221 config=config, 

222 predicted_inputs=predicted_inputs, 

223 predicted_outputs=predicted_outputs, 

224 dimensions=dimensions, 

225 filename=filename, 

226 datastore_records=quantum.datastore_records, 

227 OpaqueManagerClass=OpaqueManagerClass, 

228 BridgeManagerClass=BridgeManagerClass, 

229 search_paths=search_paths, 

230 dataset_types=dataset_types, 

231 ) 

232 

233 @classmethod 

234 def from_predicted( 

235 cls, 

236 config: Config | ResourcePathExpression, 

237 predicted_inputs: Iterable[DatasetId], 

238 predicted_outputs: Iterable[DatasetId], 

239 dimensions: DimensionUniverse, 

240 datastore_records: Mapping[str, DatastoreRecordData], 

241 filename: str = ":memory:", 

242 OpaqueManagerClass: type[OpaqueTableStorageManager] = ByNameOpaqueTableStorageManager, 

243 BridgeManagerClass: type[DatastoreRegistryBridgeManager] = MonolithicDatastoreRegistryBridgeManager, 

244 search_paths: list[str] | None = None, 

245 dataset_types: Mapping[str, DatasetType] | None = None, 

246 ) -> QuantumBackedButler: 

247 """Construct a new `QuantumBackedButler` from sets of input and output 

248 dataset IDs. 

249 

250 Parameters 

251 ---------- 

252 config : `Config` or `~lsst.resources.ResourcePathExpression` 

253 A butler repository root, configuration filename, or configuration 

254 instance. 

255 predicted_inputs : `~collections.abc.Iterable` [`DatasetId`] 

256 Dataset IDs for datasets that can can be read from this butler. 

257 predicted_outputs : `~collections.abc.Iterable` [`DatasetId`] 

258 Dataset IDs for datasets that can be stored in this butler, must be 

259 fully resolved. 

260 dimensions : `DimensionUniverse` 

261 Object managing all dimension definitions. 

262 filename : `str`, optional 

263 Name for the SQLite database that will back this butler; defaults 

264 to an in-memory database. 

265 datastore_records : `dict` [`str`, `DatastoreRecordData`] or `None` 

266 Datastore records to import into a datastore. 

267 OpaqueManagerClass : `type`, optional 

268 A subclass of `OpaqueTableStorageManager` to use for datastore 

269 opaque records. Default is a SQL-backed implementation. 

270 BridgeManagerClass : `type`, optional 

271 A subclass of `DatastoreRegistryBridgeManager` to use for datastore 

272 location records. Default is a SQL-backed implementation. 

273 search_paths : `list` of `str`, optional 

274 Additional search paths for butler configuration. 

275 dataset_types: `~collections.abc.Mapping` [`str`, `DatasetType`], \ 

276 optional 

277 Mapping of the dataset type name to its registry definition. 

278 """ 

279 return cls._initialize( 

280 config=config, 

281 predicted_inputs=predicted_inputs, 

282 predicted_outputs=predicted_outputs, 

283 dimensions=dimensions, 

284 filename=filename, 

285 datastore_records=datastore_records, 

286 OpaqueManagerClass=OpaqueManagerClass, 

287 BridgeManagerClass=BridgeManagerClass, 

288 search_paths=search_paths, 

289 dataset_types=dataset_types, 

290 ) 

291 

292 @classmethod 

293 def _initialize( 

294 cls, 

295 *, 

296 config: Config | ResourcePathExpression, 

297 predicted_inputs: Iterable[DatasetId], 

298 predicted_outputs: Iterable[DatasetId], 

299 dimensions: DimensionUniverse, 

300 filename: str = ":memory:", 

301 datastore_records: Mapping[str, DatastoreRecordData] | None = None, 

302 OpaqueManagerClass: type[OpaqueTableStorageManager] = ByNameOpaqueTableStorageManager, 

303 BridgeManagerClass: type[DatastoreRegistryBridgeManager] = MonolithicDatastoreRegistryBridgeManager, 

304 search_paths: list[str] | None = None, 

305 dataset_types: Mapping[str, DatasetType] | None = None, 

306 ) -> QuantumBackedButler: 

307 """Initialize quantum-backed butler. 

308 

309 Internal method with common implementation used by `initialize` and 

310 `for_output`. 

311 

312 Parameters 

313 ---------- 

314 config : `Config` or `~lsst.resources.ResourcePathExpression` 

315 A butler repository root, configuration filename, or configuration 

316 instance. 

317 predicted_inputs : `~collections.abc.Iterable` [`DatasetId`] 

318 Dataset IDs for datasets that can can be read from this butler. 

319 predicted_outputs : `~collections.abc.Iterable` [`DatasetId`] 

320 Dataset IDs for datasets that can be stored in this butler. 

321 dimensions : `DimensionUniverse` 

322 Object managing all dimension definitions. 

323 filename : `str`, optional 

324 Name for the SQLite database that will back this butler; defaults 

325 to an in-memory database. 

326 datastore_records : `dict` [`str`, `DatastoreRecordData`] or `None` 

327 Datastore records to import into a datastore. 

328 OpaqueManagerClass : `type`, optional 

329 A subclass of `OpaqueTableStorageManager` to use for datastore 

330 opaque records. Default is a SQL-backed implementation. 

331 BridgeManagerClass : `type`, optional 

332 A subclass of `DatastoreRegistryBridgeManager` to use for datastore 

333 location records. Default is a SQL-backed implementation. 

334 search_paths : `list` of `str`, optional 

335 Additional search paths for butler configuration. 

336 dataset_types: `~collections.abc.Mapping` [`str`, `DatasetType`] 

337 Mapping of the dataset type name to its registry definition. 

338 """ 

339 butler_config = ButlerConfig(config, searchPaths=search_paths) 

340 butler_root = butler_config.get("root", butler_config.configDir) 

341 db = SqliteDatabase.fromUri(f"sqlite:///{filename}", origin=0) 

342 with db.declareStaticTables(create=True) as context: 

343 opaque_manager = OpaqueManagerClass.initialize(db, context) 

344 bridge_manager = BridgeManagerClass.initialize( 

345 db, 

346 context, 

347 opaque=opaque_manager, 

348 # MyPy can tell it's a fake, but we know it shouldn't care. 

349 datasets=_DatasetRecordStorageManagerDatastoreConstructionMimic, # type: ignore 

350 universe=dimensions, 

351 ) 

352 # TODO: We need to inform `Datastore` here that it needs to support 

353 # predictive reads; right now that's a configuration option, but after 

354 # execution butler is retired it could just be a kwarg we pass here. 

355 # For now just force this option as we cannot work without it. 

356 butler_config["datastore", "trust_get_request"] = True 

357 datastore = Datastore.fromConfig(butler_config, bridge_manager, butler_root) 

358 if datastore_records is not None: 

359 datastore.import_records(datastore_records) 

360 storageClasses = StorageClassFactory() 

361 storageClasses.addFromConfig(butler_config) 

362 return cls( 

363 predicted_inputs, 

364 predicted_outputs, 

365 dimensions, 

366 datastore, 

367 storageClasses=storageClasses, 

368 dataset_types=dataset_types, 

369 ) 

370 

371 def _retrieve_dataset_type(self, name: str) -> DatasetType | None: 

372 """Return DatasetType defined in registry given dataset type name.""" 

373 return self._dataset_types.get(name) 

374 

375 def isWriteable(self) -> bool: 

376 # Docstring inherited. 

377 return True 

378 

379 # TODO: remove on DM-40067. 

380 @deprecated( 

381 reason="Butler.get() now behaves like Butler.getDirect() when given a DatasetRef." 

382 " Please use Butler.get(). Will be removed after v26.0.", 

383 version="v26.0", 

384 category=FutureWarning, 

385 ) 

386 def getDirect( 

387 self, 

388 ref: DatasetRef, 

389 *, 

390 parameters: dict[str, Any] | None = None, 

391 storageClass: str | StorageClass | None = None, 

392 ) -> Any: 

393 # Docstring inherited. 

394 return self.get(ref, parameters=parameters, storageClass=storageClass) 

395 

396 def get( 

397 self, 

398 ref: DatasetRef, 

399 /, 

400 *, 

401 parameters: dict[str, Any] | None = None, 

402 storageClass: StorageClass | str | None = None, 

403 ) -> Any: 

404 try: 

405 obj = super().get( 

406 ref, 

407 parameters=parameters, 

408 storageClass=storageClass, 

409 ) 

410 except (LookupError, FileNotFoundError, OSError): 

411 self._unavailable_inputs.add(ref.id) 

412 raise 

413 if ref.id in self._predicted_inputs: 

414 # do this after delegating to super in case that raises. 

415 self._actual_inputs.add(ref.id) 

416 self._available_inputs.add(ref.id) 

417 return obj 

418 

419 # TODO: remove on DM-40067. 

420 @deprecated( 

421 reason="Butler.getDeferred() now behaves like getDirectDeferred() when given a DatasetRef. " 

422 "Please use Butler.getDeferred(). Will be removed after v26.0.", 

423 version="v26.0", 

424 category=FutureWarning, 

425 ) 

426 def getDirectDeferred( 

427 self, 

428 ref: DatasetRef, 

429 *, 

430 parameters: dict[str, Any] | None = None, 

431 storageClass: str | StorageClass | None = None, 

432 ) -> DeferredDatasetHandle: 

433 # Docstring inherited. 

434 return self.getDeferred(ref, parameters=parameters, storageClass=storageClass) 

435 

436 def getDeferred( 

437 self, 

438 ref: DatasetRef, 

439 /, 

440 *, 

441 parameters: dict[str, Any] | None = None, 

442 storageClass: str | StorageClass | None = None, 

443 ) -> DeferredDatasetHandle: 

444 if ref.id in self._predicted_inputs: 

445 # Unfortunately, we can't do this after the handle succeeds in 

446 # loading, so it's conceivable here that we're marking an input 

447 # as "actual" even when it's not even available. 

448 self._actual_inputs.add(ref.id) 

449 return super().getDeferred(ref, parameters=parameters, storageClass=storageClass) 

450 

451 def stored(self, ref: DatasetRef) -> bool: 

452 # Docstring inherited. 

453 stored = super().stored(ref) 

454 if ref.id in self._predicted_inputs: 

455 if stored: 

456 self._available_inputs.add(ref.id) 

457 else: 

458 self._unavailable_inputs.add(ref.id) 

459 return stored 

460 

461 def stored_many( 

462 self, 

463 refs: Iterable[DatasetRef], 

464 ) -> dict[DatasetRef, bool]: 

465 # Docstring inherited. 

466 existence = super().stored_many(refs) 

467 

468 for ref, stored in existence.items(): 

469 if ref.id in self._predicted_inputs: 

470 if stored: 

471 self._available_inputs.add(ref.id) 

472 else: 

473 self._unavailable_inputs.add(ref.id) 

474 return existence 

475 

476 def markInputUnused(self, ref: DatasetRef) -> None: 

477 # Docstring inherited. 

478 self._actual_inputs.discard(ref.id) 

479 

480 @property 

481 def dimensions(self) -> DimensionUniverse: 

482 # Docstring inherited. 

483 return self._dimensions 

484 

485 def put(self, obj: Any, ref: DatasetRef, /) -> DatasetRef: 

486 # Docstring inherited. 

487 if ref.id not in self._predicted_outputs: 

488 raise RuntimeError("Cannot `put` dataset that was not predicted as an output.") 

489 self._datastore.put(obj, ref) 

490 self._actual_output_refs.add(ref) 

491 return ref 

492 

493 def pruneDatasets( 

494 self, 

495 refs: Iterable[DatasetRef], 

496 *, 

497 disassociate: bool = True, 

498 unstore: bool = False, 

499 tags: Iterable[str] = (), 

500 purge: bool = False, 

501 ) -> None: 

502 # docstring inherited from LimitedButler 

503 

504 if purge: 

505 if not disassociate: 

506 raise TypeError("Cannot pass purge=True without disassociate=True.") 

507 if not unstore: 

508 raise TypeError("Cannot pass purge=True without unstore=True.") 

509 elif disassociate: 

510 # No tagged collections for this butler. 

511 raise TypeError("Cannot pass disassociate=True without purge=True.") 

512 

513 refs = list(refs) 

514 

515 # Pruning a component of a DatasetRef makes no sense. 

516 for ref in refs: 

517 if ref.datasetType.component(): 

518 raise ValueError(f"Can not prune a component of a dataset (ref={ref})") 

519 

520 if unstore: 

521 self._datastore.trash(refs) 

522 if purge: 

523 for ref in refs: 

524 # We only care about removing them from actual output refs, 

525 self._actual_output_refs.discard(ref) 

526 

527 if unstore: 

528 # Point of no return for removing artifacts 

529 self._datastore.emptyTrash() 

530 

531 def extract_provenance_data(self) -> QuantumProvenanceData: 

532 """Extract provenance information and datastore records from this 

533 butler. 

534 

535 Returns 

536 ------- 

537 provenance : `QuantumProvenanceData` 

538 A serializable struct containing input/output dataset IDs and 

539 datastore records. This assumes all dataset IDs are UUIDs (just to 

540 make it easier for `pydantic` to reason about the struct's types); 

541 the rest of this class makes no such assumption, but the approach 

542 to processing in which it's useful effectively requires UUIDs 

543 anyway. 

544 

545 Notes 

546 ----- 

547 `QuantumBackedButler` records this provenance information when its 

548 methods are used, which mostly saves `~lsst.pipe.base.PipelineTask` 

549 authors from having to worry about while still recording very 

550 detailed information. But it has two small weaknesses: 

551 

552 - Calling `getDirectDeferred` or `getDirect` is enough to mark a 

553 dataset as an "actual input", which may mark some datasets that 

554 aren't actually used. We rely on task authors to use 

555 `markInputUnused` to address this. 

556 

557 - We assume that the execution system will call ``datasetExistsDirect`` 

558 on all predicted inputs prior to execution, in order to populate the 

559 "available inputs" set. This is what I envision 

560 '`~lsst.ctrl.mpexec.SingleQuantumExecutor` doing after we update it 

561 to use this class, but it feels fragile for this class to make such 

562 a strong assumption about how it will be used, even if I can't think 

563 of any other executor behavior that would make sense. 

564 """ 

565 if not self._actual_inputs.isdisjoint(self._unavailable_inputs): 

566 _LOG.warning( 

567 "Inputs %s were marked as actually used (probably because a DeferredDatasetHandle) " 

568 "was obtained, but did not actually exist. This task should be be using markInputUnused " 

569 "directly to clarify its provenance.", 

570 self._actual_inputs & self._unavailable_inputs, 

571 ) 

572 self._actual_inputs -= self._unavailable_inputs 

573 checked_inputs = self._available_inputs | self._unavailable_inputs 

574 if self._predicted_inputs != checked_inputs: 

575 _LOG.warning( 

576 "Execution harness did not check predicted inputs %s for existence; available inputs " 

577 "recorded in provenance may be incomplete.", 

578 self._predicted_inputs - checked_inputs, 

579 ) 

580 datastore_records = self._datastore.export_records(self._actual_output_refs) 

581 provenance_records = { 

582 datastore_name: records.to_simple() for datastore_name, records in datastore_records.items() 

583 } 

584 

585 return QuantumProvenanceData( 

586 predicted_inputs=self._predicted_inputs, 

587 available_inputs=self._available_inputs, 

588 actual_inputs=self._actual_inputs, 

589 predicted_outputs=self._predicted_outputs, 

590 actual_outputs={ref.id for ref in self._actual_output_refs}, 

591 datastore_records=provenance_records, 

592 ) 

593 

594 

595class QuantumProvenanceData(_BaseModelCompat): 

596 """A serializable struct for per-quantum provenance information and 

597 datastore records. 

598 

599 Notes 

600 ----- 

601 This class slightly duplicates information from the `Quantum` class itself 

602 (the ``predicted_inputs`` and ``predicted_outputs`` sets should have the 

603 same IDs present in `Quantum.inputs` and `Quantum.outputs`), but overall it 

604 assumes the original `Quantum` is also available to reconstruct the 

605 complete provenance (e.g. by associating dataset IDs with data IDs, 

606 dataset types, and `~CollectionType.RUN` names. 

607 

608 Note that ``pydantic`` method ``parse_raw()`` is not going to work 

609 correctly for this class, use `direct` method instead. 

610 """ 

611 

612 # This class probably should have information about its execution 

613 # environment (anything not controlled and recorded at the 

614 # `~CollectionType.RUN` level, such as the compute node ID). but adding it 

615 # now is out of scope for this prototype. 

616 

617 predicted_inputs: set[uuid.UUID] 

618 """Unique IDs of datasets that were predicted as inputs to this quantum 

619 when the QuantumGraph was built. 

620 """ 

621 

622 available_inputs: set[uuid.UUID] 

623 """Unique IDs of input datasets that were actually present in the datastore 

624 when this quantum was executed. 

625 

626 This is a subset of ``predicted_inputs``, with the difference generally 

627 being datasets were ``predicted_outputs`` but not ``actual_outputs`` of 

628 some upstream task. 

629 """ 

630 

631 actual_inputs: set[uuid.UUID] 

632 """Unique IDs of datasets that were actually used as inputs by this task. 

633 

634 This is a subset of ``available_inputs``. 

635 

636 Notes 

637 ----- 

638 The criteria for marking an input as used is that rerunning the quantum 

639 with only these ``actual_inputs`` available must yield identical outputs. 

640 This means that (for example) even just using an input to help determine 

641 an output rejection criteria and then rejecting it as an outlier qualifies 

642 that input as actually used. 

643 """ 

644 

645 predicted_outputs: set[uuid.UUID] 

646 """Unique IDs of datasets that were predicted as outputs of this quantum 

647 when the QuantumGraph was built. 

648 """ 

649 

650 actual_outputs: set[uuid.UUID] 

651 """Unique IDs of datasets that were actually written when this quantum 

652 was executed. 

653 """ 

654 

655 datastore_records: dict[str, SerializedDatastoreRecordData] 

656 """Datastore records indexed by datastore name.""" 

657 

658 @staticmethod 

659 def collect_and_transfer( 

660 butler: Butler, quanta: Iterable[Quantum], provenance: Iterable[QuantumProvenanceData] 

661 ) -> None: 

662 """Transfer output datasets from multiple quanta to a more permantent 

663 `Butler` repository. 

664 

665 Parameters 

666 ---------- 

667 butler : `Butler` 

668 Full butler representing the data repository to transfer datasets 

669 to. 

670 quanta : `~collections.abc.Iterable` [ `Quantum` ] 

671 Iterable of `Quantum` objects that carry information about 

672 predicted outputs. May be a single-pass iterator. 

673 provenance : `~collections.abc.Iterable` [ `QuantumProvenanceData` ] 

674 Provenance and datastore data for each of the given quanta, in the 

675 same order. May be a single-pass iterator. 

676 

677 Notes 

678 ----- 

679 Input-output provenance data is not actually transferred yet, because 

680 `Registry` has no place to store it. 

681 

682 This method probably works most efficiently if run on all quanta for a 

683 single task label at once, because this will gather all datasets of 

684 a particular type together into a single vectorized `Registry` import. 

685 It should still behave correctly if run on smaller groups of quanta 

686 or even quanta from multiple tasks. 

687 

688 Currently this method transfers datastore record data unchanged, with 

689 no possibility of actually moving (e.g.) files. Datastores that are 

690 present only in execution or only in the more permanent butler are 

691 ignored. 

692 """ 

693 grouped_refs = defaultdict(list) 

694 summary_records: dict[str, DatastoreRecordData] = {} 

695 for quantum, provenance_for_quantum in zip(quanta, provenance, strict=True): 

696 quantum_refs_by_id = { 

697 ref.id: ref 

698 for ref in itertools.chain.from_iterable(quantum.outputs.values()) 

699 if ref.id in provenance_for_quantum.actual_outputs 

700 } 

701 for ref in quantum_refs_by_id.values(): 

702 grouped_refs[ref.datasetType, ref.run].append(ref) 

703 

704 # merge datastore records into a summary structure 

705 for datastore_name, serialized_records in provenance_for_quantum.datastore_records.items(): 

706 quantum_records = DatastoreRecordData.from_simple(serialized_records) 

707 if (records := summary_records.get(datastore_name)) is not None: 

708 records.update(quantum_records) 

709 else: 

710 summary_records[datastore_name] = quantum_records 

711 

712 for refs in grouped_refs.values(): 

713 butler.registry._importDatasets(refs) 

714 butler._datastore.import_records(summary_records) 

715 

716 @classmethod 

717 def parse_raw(cls, *args: Any, **kwargs: Any) -> QuantumProvenanceData: 

718 raise NotImplementedError("parse_raw() is not usable for this class, use direct() instead.") 

719 

720 @classmethod 

721 def direct( 

722 cls, 

723 *, 

724 predicted_inputs: Iterable[str | uuid.UUID], 

725 available_inputs: Iterable[str | uuid.UUID], 

726 actual_inputs: Iterable[str | uuid.UUID], 

727 predicted_outputs: Iterable[str | uuid.UUID], 

728 actual_outputs: Iterable[str | uuid.UUID], 

729 datastore_records: Mapping[str, Mapping], 

730 ) -> QuantumProvenanceData: 

731 """Construct an instance directly without validators. 

732 

733 This differs from the pydantic "construct" method in that the 

734 arguments are explicitly what the model requires, and it will recurse 

735 through members, constructing them from their corresponding `direct` 

736 methods. 

737 

738 This method should only be called when the inputs are trusted. 

739 """ 

740 

741 def _to_uuid_set(uuids: Iterable[str | uuid.UUID]) -> set[uuid.UUID]: 

742 """Convert input UUIDs, which could be in string representation to 

743 a set of `UUID` instances. 

744 """ 

745 return {uuid.UUID(id) if isinstance(id, str) else id for id in uuids} 

746 

747 data = cls.model_construct( 

748 predicted_inputs=_to_uuid_set(predicted_inputs), 

749 available_inputs=_to_uuid_set(available_inputs), 

750 actual_inputs=_to_uuid_set(actual_inputs), 

751 predicted_outputs=_to_uuid_set(predicted_outputs), 

752 actual_outputs=_to_uuid_set(actual_outputs), 

753 datastore_records={ 

754 key: SerializedDatastoreRecordData.direct(**records) 

755 for key, records in datastore_records.items() 

756 }, 

757 ) 

758 

759 return data