Hide keyboard shortcuts

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 pipe_base. 

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/>. 

21from __future__ import annotations 

22 

23"""Module defining GraphBuilder class and related methods. 

24""" 

25 

26__all__ = ['GraphBuilder'] 

27 

28# ------------------------------- 

29# Imports of standard modules -- 

30# ------------------------------- 

31import itertools 

32from collections import ChainMap 

33from contextlib import contextmanager 

34from dataclasses import dataclass 

35from typing import Dict, Iterable, Iterator, List, Set 

36import logging 

37 

38 

39# ----------------------------- 

40# Imports for other modules -- 

41# ----------------------------- 

42from .connections import iterConnections 

43from .pipeline import PipelineDatasetTypes, TaskDatasetTypes, TaskDef, Pipeline 

44from .graph import QuantumGraph 

45from lsst.daf.butler import ( 

46 DataCoordinate, 

47 DatasetRef, 

48 DatasetType, 

49 DimensionGraph, 

50 DimensionUniverse, 

51 NamedKeyDict, 

52 Quantum, 

53) 

54from lsst.daf.butler.registry.queries.exprParser import ParseError, ParserYacc, TreeVisitor 

55from lsst.utils import doImport 

56 

57# ---------------------------------- 

58# Local non-exported definitions -- 

59# ---------------------------------- 

60 

61_LOG = logging.getLogger(__name__.partition(".")[2]) 

62 

63 

64class _DatasetDict(NamedKeyDict[DatasetType, Dict[DataCoordinate, DatasetRef]]): 

65 """A custom dictionary that maps `DatasetType` to a nested dictionary of 

66 the known `DatasetRef` instances of that type. 

67 

68 Parameters 

69 ---------- 

70 args 

71 Positional arguments are forwarded to the `dict` constructor. 

72 universe : `DimensionUniverse` 

73 Universe of all possible dimensions. 

74 """ 

75 def __init__(self, *args, universe: DimensionGraph): 

76 super().__init__(*args) 

77 self.universe = universe 

78 

79 @classmethod 

80 def fromDatasetTypes(cls, datasetTypes: Iterable[DatasetType], *, 

81 universe: DimensionUniverse) -> _DatasetDict: 

82 """Construct a dictionary from a flat iterable of `DatasetType` keys. 

83 

84 Parameters 

85 ---------- 

86 datasetTypes : `iterable` of `DatasetType` 

87 DatasetTypes to use as keys for the dict. Values will be empty 

88 dictionaries. 

89 universe : `DimensionUniverse` 

90 Universe of all possible dimensions. 

91 

92 Returns 

93 ------- 

94 dictionary : `_DatasetDict` 

95 A new `_DatasetDict` instance. 

96 """ 

97 return cls({datasetType: {} for datasetType in datasetTypes}, universe=universe) 

98 

99 @classmethod 

100 def fromSubset(cls, datasetTypes: Iterable[DatasetType], first: _DatasetDict, *rest: _DatasetDict 

101 ) -> _DatasetDict: 

102 """Return a new dictionary by extracting items corresponding to the 

103 given keys from one or more existing dictionaries. 

104 

105 Parameters 

106 ---------- 

107 datasetTypes : `iterable` of `DatasetType` 

108 DatasetTypes to use as keys for the dict. Values will be obtained 

109 by lookups against ``first`` and ``rest``. 

110 first : `_DatasetDict` 

111 Another dictionary from which to extract values. 

112 rest 

113 Additional dictionaries from which to extract values. 

114 

115 Returns 

116 ------- 

117 dictionary : `_DatasetDict` 

118 A new dictionary instance. 

119 """ 

120 combined = ChainMap(first, *rest) 

121 return cls({datasetType: combined[datasetType] for datasetType in datasetTypes}, 

122 universe=first.universe) 

123 

124 @property 

125 def dimensions(self) -> DimensionGraph: 

126 """The union of all dimensions used by all dataset types in this 

127 dictionary, including implied dependencies (`DimensionGraph`). 

128 """ 

129 base = self.universe.empty 

130 if len(self) == 0: 

131 return base 

132 return base.union(*[datasetType.dimensions for datasetType in self.keys()]) 

133 

134 def unpackSingleRefs(self) -> NamedKeyDict[DatasetType, DatasetRef]: 

135 """Unpack nested single-element `DatasetRef` dicts into a new 

136 mapping with `DatasetType` keys and `DatasetRef` values. 

137 

138 This method assumes that each nest contains exactly one item, as is the 

139 case for all "init" datasets. 

140 

141 Returns 

142 ------- 

143 dictionary : `NamedKeyDict` 

144 Dictionary mapping `DatasetType` to `DatasetRef`, with both 

145 `DatasetType` instances and string names usable as keys. 

146 """ 

147 def getOne(refs: Dict[DataCoordinate, DatasetRef]) -> DatasetRef: 

148 ref, = refs.values() 

149 return ref 

150 return NamedKeyDict({datasetType: getOne(refs) for datasetType, refs in self.items()}) 

151 

152 def unpackMultiRefs(self) -> NamedKeyDict[DatasetType, DatasetRef]: 

153 """Unpack nested multi-element `DatasetRef` dicts into a new 

154 mapping with `DatasetType` keys and `set` of `DatasetRef` values. 

155 

156 Returns 

157 ------- 

158 dictionary : `NamedKeyDict` 

159 Dictionary mapping `DatasetType` to `DatasetRef`, with both 

160 `DatasetType` instances and string names usable as keys. 

161 """ 

162 return NamedKeyDict({datasetType: list(refs.values()) for datasetType, refs in self.items()}) 

163 

164 def extract(self, datasetType: DatasetType, dataIds: Iterable[DataCoordinate] 

165 ) -> Iterator[DatasetRef]: 

166 """Iterate over the contained `DatasetRef` instances that match the 

167 given `DatasetType` and data IDs. 

168 

169 Parameters 

170 ---------- 

171 datasetType : `DatasetType` 

172 Dataset type to match. 

173 dataIds : `Iterable` [ `DataCoordinate` ] 

174 Data IDs to match. 

175 

176 Returns 

177 ------- 

178 refs : `Iterator` [ `DatasetRef` ] 

179 DatasetRef instances for which ``ref.datasetType == datasetType`` 

180 and ``ref.dataId`` is in ``dataIds``. 

181 """ 

182 refs = self[datasetType] 

183 return (refs[dataId] for dataId in dataIds) 

184 

185 

186class _QuantumScaffolding: 

187 """Helper class aggregating information about a `Quantum`, used when 

188 constructing a `QuantumGraph`. 

189 

190 See `_PipelineScaffolding` for a top-down description of the full 

191 scaffolding data structure. 

192 

193 Parameters 

194 ---------- 

195 task : _TaskScaffolding 

196 Back-reference to the helper object for the `PipelineTask` this quantum 

197 represents an execution of. 

198 dataId : `DataCoordinate` 

199 Data ID for this quantum. 

200 """ 

201 def __init__(self, task: _TaskScaffolding, dataId: DataCoordinate): 

202 self.task = task 

203 self.dataId = dataId 

204 self.inputs = _DatasetDict.fromDatasetTypes(task.inputs.keys(), universe=dataId.universe) 

205 self.outputs = _DatasetDict.fromDatasetTypes(task.outputs.keys(), universe=dataId.universe) 

206 self.prerequisites = _DatasetDict.fromDatasetTypes(task.prerequisites.keys(), 

207 universe=dataId.universe) 

208 

209 __slots__ = ("task", "dataId", "inputs", "outputs", "prerequisites") 

210 

211 def __repr__(self): 

212 return f"_QuantumScaffolding(taskDef={self.task.taskDef}, dataId={self.dataId}, ...)" 

213 

214 task: _TaskScaffolding 

215 """Back-reference to the helper object for the `PipelineTask` this quantum 

216 represents an execution of. 

217 """ 

218 

219 dataId: DataCoordinate 

220 """Data ID for this quantum. 

221 """ 

222 

223 inputs: _DatasetDict 

224 """Nested dictionary containing `DatasetRef` inputs to this quantum. 

225 

226 This is initialized to map each `DatasetType` to an empty dictionary at 

227 construction. Those nested dictionaries are populated (with data IDs as 

228 keys) with unresolved `DatasetRef` instances in 

229 `_PipelineScaffolding.connectDataIds`. 

230 """ 

231 

232 outputs: _DatasetDict 

233 """Nested dictionary containing `DatasetRef` outputs this quantum. 

234 """ 

235 

236 prerequisites: _DatasetDict 

237 """Nested dictionary containing `DatasetRef` prerequisite inputs to this 

238 quantum. 

239 """ 

240 

241 def makeQuantum(self) -> Quantum: 

242 """Transform the scaffolding object into a true `Quantum` instance. 

243 

244 Returns 

245 ------- 

246 quantum : `Quantum` 

247 An actual `Quantum` instance. 

248 """ 

249 allInputs = self.inputs.unpackMultiRefs() 

250 allInputs.update(self.prerequisites.unpackMultiRefs()) 

251 # Give the task's Connections class an opportunity to remove some 

252 # inputs, or complain if they are unacceptable. 

253 # This will raise if one of the check conditions is not met, which is the intended 

254 # behavior 

255 allInputs = self.task.taskDef.connections.adjustQuantum(allInputs) 

256 return Quantum( 

257 taskName=self.task.taskDef.taskName, 

258 taskClass=self.task.taskDef.taskClass, 

259 dataId=self.dataId, 

260 initInputs=self.task.initInputs.unpackSingleRefs(), 

261 inputs=allInputs, 

262 outputs=self.outputs.unpackMultiRefs(), 

263 ) 

264 

265 

266@dataclass 

267class _TaskScaffolding: 

268 """Helper class aggregating information about a `PipelineTask`, used when 

269 constructing a `QuantumGraph`. 

270 

271 See `_PipelineScaffolding` for a top-down description of the full 

272 scaffolding data structure. 

273 

274 Parameters 

275 ---------- 

276 taskDef : `TaskDef` 

277 Data structure that identifies the task class and its config. 

278 parent : `_PipelineScaffolding` 

279 The parent data structure that will hold the instance being 

280 constructed. 

281 datasetTypes : `TaskDatasetTypes` 

282 Data structure that categorizes the dataset types used by this task. 

283 """ 

284 def __init__(self, taskDef: TaskDef, parent: _PipelineScaffolding, datasetTypes: TaskDatasetTypes): 

285 universe = parent.dimensions.universe 

286 self.taskDef = taskDef 

287 self.dimensions = DimensionGraph(universe, names=taskDef.connections.dimensions) 

288 assert self.dimensions.issubset(parent.dimensions) 

289 # Initialize _DatasetDicts as subsets of the one or two 

290 # corresponding dicts in the parent _PipelineScaffolding. 

291 self.initInputs = _DatasetDict.fromSubset(datasetTypes.initInputs, parent.initInputs, 

292 parent.initIntermediates) 

293 self.initOutputs = _DatasetDict.fromSubset(datasetTypes.initOutputs, parent.initIntermediates, 

294 parent.initOutputs) 

295 self.inputs = _DatasetDict.fromSubset(datasetTypes.inputs, parent.inputs, parent.intermediates) 

296 self.outputs = _DatasetDict.fromSubset(datasetTypes.outputs, parent.intermediates, parent.outputs) 

297 self.prerequisites = _DatasetDict.fromSubset(datasetTypes.prerequisites, parent.prerequisites) 

298 self.dataIds = set() 

299 self.quanta = {} 

300 

301 def __repr__(self): 

302 # Default dataclass-injected __repr__ gets caught in an infinite loop 

303 # because of back-references. 

304 return f"_TaskScaffolding(taskDef={self.taskDef}, ...)" 

305 

306 taskDef: TaskDef 

307 """Data structure that identifies the task class and its config 

308 (`TaskDef`). 

309 """ 

310 

311 dimensions: DimensionGraph 

312 """The dimensions of a single `Quantum` of this task (`DimensionGraph`). 

313 """ 

314 

315 initInputs: _DatasetDict 

316 """Dictionary containing information about datasets used to construct this 

317 task (`_DatasetDict`). 

318 """ 

319 

320 initOutputs: _DatasetDict 

321 """Dictionary containing information about datasets produced as a 

322 side-effect of constructing this task (`_DatasetDict`). 

323 """ 

324 

325 inputs: _DatasetDict 

326 """Dictionary containing information about datasets used as regular, 

327 graph-constraining inputs to this task (`_DatasetDict`). 

328 """ 

329 

330 outputs: _DatasetDict 

331 """Dictionary containing information about datasets produced by this task 

332 (`_DatasetDict`). 

333 """ 

334 

335 prerequisites: _DatasetDict 

336 """Dictionary containing information about input datasets that must be 

337 present in the repository before any Pipeline containing this task is run 

338 (`_DatasetDict`). 

339 """ 

340 

341 quanta: Dict[DataCoordinate, _QuantumScaffolding] 

342 """Dictionary mapping data ID to a scaffolding object for the Quantum of 

343 this task with that data ID. 

344 """ 

345 

346 def makeQuantumSet(self) -> Set[Quantum]: 

347 """Create a `set` of `Quantum` from the information in ``self``. 

348 

349 Returns 

350 ------- 

351 nodes : `set` of `Quantum 

352 The `Quantum` elements corresponding to this task. 

353 """ 

354 return set(q.makeQuantum() for q in self.quanta.values()) 

355 

356 

357@dataclass 

358class _PipelineScaffolding: 

359 """A helper data structure that organizes the information involved in 

360 constructing a `QuantumGraph` for a `Pipeline`. 

361 

362 Parameters 

363 ---------- 

364 pipeline : `Pipeline` 

365 Sequence of tasks from which a graph is to be constructed. Must 

366 have nested task classes already imported. 

367 universe : `DimensionUniverse` 

368 Universe of all possible dimensions. 

369 

370 Notes 

371 ----- 

372 The scaffolding data structure contains nested data structures for both 

373 tasks (`_TaskScaffolding`) and datasets (`_DatasetDict`). The dataset 

374 data structures are shared between the pipeline-level structure (which 

375 aggregates all datasets and categorizes them from the perspective of the 

376 complete pipeline) and the individual tasks that use them as inputs and 

377 outputs. 

378 

379 `QuantumGraph` construction proceeds in four steps, with each corresponding 

380 to a different `_PipelineScaffolding` method: 

381 

382 1. When `_PipelineScaffolding` is constructed, we extract and categorize 

383 the DatasetTypes used by the pipeline (delegating to 

384 `PipelineDatasetTypes.fromPipeline`), then use these to construct the 

385 nested `_TaskScaffolding` and `_DatasetDict` objects. 

386 

387 2. In `connectDataIds`, we construct and run the "Big Join Query", which 

388 returns related tuples of all dimensions used to identify any regular 

389 input, output, and intermediate datasets (not prerequisites). We then 

390 iterate over these tuples of related dimensions, identifying the subsets 

391 that correspond to distinct data IDs for each task and dataset type, 

392 and then create `_QuantumScaffolding` objects. 

393 

394 3. In `resolveDatasetRefs`, we run follow-up queries against all of the 

395 dataset data IDs previously identified, transforming unresolved 

396 DatasetRefs into resolved DatasetRefs where appropriate. We then look 

397 up prerequisite datasets for all quanta. 

398 

399 4. In `makeQuantumGraph`, we construct a `QuantumGraph` from the lists of 

400 per-task `_QuantumScaffolding` objects. 

401 """ 

402 def __init__(self, pipeline, *, registry): 

403 _LOG.debug("Initializing data structures for QuantumGraph generation.") 

404 self.tasks = [] 

405 # Aggregate and categorize the DatasetTypes in the Pipeline. 

406 datasetTypes = PipelineDatasetTypes.fromPipeline(pipeline, registry=registry) 

407 # Construct dictionaries that map those DatasetTypes to structures 

408 # that will (later) hold addiitonal information about them. 

409 for attr in ("initInputs", "initIntermediates", "initOutputs", 

410 "inputs", "intermediates", "outputs", "prerequisites"): 

411 setattr(self, attr, _DatasetDict.fromDatasetTypes(getattr(datasetTypes, attr), 

412 universe=registry.dimensions)) 

413 # Aggregate all dimensions for all non-init, non-prerequisite 

414 # DatasetTypes. These are the ones we'll include in the big join query. 

415 self.dimensions = self.inputs.dimensions.union(self.intermediates.dimensions, 

416 self.outputs.dimensions) 

417 # Construct scaffolding nodes for each Task, and add backreferences 

418 # to the Task from each DatasetScaffolding node. 

419 # Note that there's only one scaffolding node for each DatasetType, shared by 

420 # _PipelineScaffolding and all _TaskScaffoldings that reference it. 

421 if isinstance(pipeline, Pipeline): 

422 pipeline = pipeline.toExpandedPipeline() 

423 self.tasks = [_TaskScaffolding(taskDef=taskDef, parent=self, datasetTypes=taskDatasetTypes) 

424 for taskDef, taskDatasetTypes in zip(pipeline, 

425 datasetTypes.byTask.values())] 

426 

427 def __repr__(self): 

428 # Default dataclass-injected __repr__ gets caught in an infinite loop 

429 # because of back-references. 

430 return f"_PipelineScaffolding(tasks={self.tasks}, ...)" 

431 

432 tasks: List[_TaskScaffolding] 

433 """Scaffolding data structures for each task in the pipeline 

434 (`list` of `_TaskScaffolding`). 

435 """ 

436 

437 initInputs: _DatasetDict 

438 """Datasets consumed but not produced when constructing the tasks in this 

439 pipeline (`_DatasetDict`). 

440 """ 

441 

442 initIntermediates: _DatasetDict 

443 """Datasets that are both consumed and produced when constructing the tasks 

444 in this pipeline (`_DatasetDict`). 

445 """ 

446 

447 initOutputs: _DatasetDict 

448 """Datasets produced but not consumed when constructing the tasks in this 

449 pipeline (`_DatasetDict`). 

450 """ 

451 

452 inputs: _DatasetDict 

453 """Datasets that are consumed but not produced when running this pipeline 

454 (`_DatasetDict`). 

455 """ 

456 

457 intermediates: _DatasetDict 

458 """Datasets that are both produced and consumed when running this pipeline 

459 (`_DatasetDict`). 

460 """ 

461 

462 outputs: _DatasetDict 

463 """Datasets produced but not consumed when when running this pipeline 

464 (`_DatasetDict`). 

465 """ 

466 

467 prerequisites: _DatasetDict 

468 """Datasets that are consumed when running this pipeline and looked up 

469 per-Quantum when generating the graph (`_DatasetDict`). 

470 """ 

471 

472 dimensions: DimensionGraph 

473 """All dimensions used by any regular input, intermediate, or output 

474 (not prerequisite) dataset; the set of dimension used in the "Big Join 

475 Query" (`DimensionGraph`). 

476 

477 This is required to be a superset of all task quantum dimensions. 

478 """ 

479 

480 @contextmanager 

481 def connectDataIds(self, registry, collections, userQuery): 

482 """Query for the data IDs that connect nodes in the `QuantumGraph`. 

483 

484 This method populates `_TaskScaffolding.dataIds` and 

485 `_DatasetScaffolding.dataIds` (except for those in `prerequisites`). 

486 

487 Parameters 

488 ---------- 

489 registry : `lsst.daf.butler.Registry` 

490 Registry for the data repository; used for all data ID queries. 

491 collections : `lsst.daf.butler.CollectionSearch` 

492 Object representing the collections to search for input datasets. 

493 userQuery : `str`, optional 

494 User-provided expression to limit the data IDs processed. 

495 

496 Returns 

497 ------- 

498 commonDataIds : \ 

499 `lsst.daf.butler.registry.queries.DataCoordinateQueryResults` 

500 An interface to a database temporary table containing all data IDs 

501 that will appear in this `QuantumGraph`. Returned inside a 

502 context manager, which will drop the temporary table at the end of 

503 the `with` block in which this method is called. 

504 """ 

505 _LOG.debug("Building query for data IDs.") 

506 # Initialization datasets always have empty data IDs. 

507 emptyDataId = DataCoordinate.makeEmpty(registry.dimensions) 

508 for datasetType, refs in itertools.chain(self.initInputs.items(), 

509 self.initIntermediates.items(), 

510 self.initOutputs.items()): 

511 refs[emptyDataId] = DatasetRef(datasetType, emptyDataId) 

512 # Run one big query for the data IDs for task dimensions and regular 

513 # inputs and outputs. We limit the query to only dimensions that are 

514 # associated with the input dataset types, but don't (yet) try to 

515 # obtain the dataset_ids for those inputs. 

516 _LOG.debug("Submitting data ID query and materializing results.") 

517 with registry.queryDataIds(self.dimensions, 

518 datasets=list(self.inputs), 

519 collections=collections, 

520 where=userQuery, 

521 ).materialize() as commonDataIds: 

522 _LOG.debug("Expanding data IDs.") 

523 commonDataIds = commonDataIds.expanded() 

524 _LOG.debug("Iterating over query results to associate quanta with datasets.") 

525 # Iterate over query results, populating data IDs for datasets and 

526 # quanta and then connecting them to each other. 

527 n = 0 

528 for n, commonDataId in enumerate(commonDataIds): 

529 # Create DatasetRefs for all DatasetTypes from this result row, 

530 # noting that we might have created some already. 

531 # We remember both those that already existed and those that we 

532 # create now. 

533 refsForRow = {} 

534 for datasetType, refs in itertools.chain(self.inputs.items(), self.intermediates.items(), 

535 self.outputs.items()): 

536 datasetDataId = commonDataId.subset(datasetType.dimensions) 

537 ref = refs.get(datasetDataId) 

538 if ref is None: 

539 ref = DatasetRef(datasetType, datasetDataId) 

540 refs[datasetDataId] = ref 

541 refsForRow[datasetType.name] = ref 

542 # Create _QuantumScaffolding objects for all tasks from this result 

543 # row, noting that we might have created some already. 

544 for task in self.tasks: 

545 quantumDataId = commonDataId.subset(task.dimensions) 

546 quantum = task.quanta.get(quantumDataId) 

547 if quantum is None: 

548 quantum = _QuantumScaffolding(task=task, dataId=quantumDataId) 

549 task.quanta[quantumDataId] = quantum 

550 # Whether this is a new quantum or an existing one, we can now 

551 # associate the DatasetRefs for this row with it. The fact 

552 # the fact that a Quantum data ID and a dataset data ID both 

553 # came from the same result row is what tells us they should 

554 # be associated. 

555 # Many of these associates will be duplicates (because another 

556 # query row that differed from this one only in irrelevant 

557 # dimensions already added them), and we use sets to skip. 

558 for datasetType in task.inputs: 

559 ref = refsForRow[datasetType.name] 

560 quantum.inputs[datasetType.name][ref.dataId] = ref 

561 for datasetType in task.outputs: 

562 ref = refsForRow[datasetType.name] 

563 quantum.outputs[datasetType.name][ref.dataId] = ref 

564 _LOG.debug("Finished processing %d rows from data ID query.", n) 

565 yield commonDataIds 

566 

567 def resolveDatasetRefs(self, registry, collections, run, commonDataIds, *, skipExisting=True): 

568 """Perform follow up queries for each dataset data ID produced in 

569 `fillDataIds`. 

570 

571 This method populates `_DatasetScaffolding.refs` (except for those in 

572 `prerequisites`). 

573 

574 Parameters 

575 ---------- 

576 registry : `lsst.daf.butler.Registry` 

577 Registry for the data repository; used for all data ID queries. 

578 collections : `lsst.daf.butler.CollectionSearch` 

579 Object representing the collections to search for input datasets. 

580 run : `str`, optional 

581 Name of the `~lsst.daf.butler.CollectionType.RUN` collection for 

582 output datasets, if it already exists. 

583 commonDataIds : \ 

584 `lsst.daf.butler.registry.queries.DataCoordinateQueryResults` 

585 Result of a previous call to `connectDataIds`. 

586 skipExisting : `bool`, optional 

587 If `True` (default), a Quantum is not created if all its outputs 

588 already exist in ``run``. Ignored if ``run`` is `None`. 

589 

590 Raises 

591 ------ 

592 OutputExistsError 

593 Raised if an output dataset already exists in the output run 

594 and ``skipExisting`` is `False`. The case where some but not all 

595 of a quantum's outputs are present and ``skipExisting`` is `True` 

596 cannot be identified at this stage, and is handled by `fillQuanta` 

597 instead. 

598 """ 

599 # Look up [init] intermediate and output datasets in the output 

600 # collection, if there is an output collection. 

601 if run is not None: 

602 for datasetType, refs in itertools.chain(self.initIntermediates.items(), 

603 self.initOutputs.items(), 

604 self.intermediates.items(), 

605 self.outputs.items()): 

606 _LOG.debug("Resolving %d datasets for intermediate and/or output dataset %s.", 

607 len(refs), datasetType.name) 

608 isInit = datasetType in self.initIntermediates or datasetType in self.initOutputs 

609 resolvedRefQueryResults = commonDataIds.subset( 

610 datasetType.dimensions, 

611 unique=True 

612 ).findDatasets( 

613 datasetType, 

614 collections=run, 

615 deduplicate=True 

616 ) 

617 for resolvedRef in resolvedRefQueryResults: 

618 # TODO: we could easily support per-DatasetType 

619 # skipExisting and I could imagine that being useful - it's 

620 # probably required in order to support writing initOutputs 

621 # before QuantumGraph generation. 

622 assert resolvedRef.dataId in refs 

623 if skipExisting or isInit: 

624 refs[resolvedRef.dataId] = resolvedRef 

625 else: 

626 raise OutputExistsError(f"Output dataset {datasetType.name} already exists in " 

627 f"output RUN collection '{run}' with data ID" 

628 f" {resolvedRef.dataId}.") 

629 # Look up input and initInput datasets in the input collection(s). 

630 for datasetType, refs in itertools.chain(self.initInputs.items(), self.inputs.items()): 

631 _LOG.debug("Resolving %d datasets for input dataset %s.", len(refs), datasetType.name) 

632 resolvedRefQueryResults = commonDataIds.subset( 

633 datasetType.dimensions, 

634 unique=True 

635 ).findDatasets( 

636 datasetType, 

637 collections=collections, 

638 deduplicate=True 

639 ) 

640 dataIdsNotFoundYet = set(refs.keys()) 

641 for resolvedRef in resolvedRefQueryResults: 

642 dataIdsNotFoundYet.discard(resolvedRef.dataId) 

643 refs[resolvedRef.dataId] = resolvedRef 

644 if dataIdsNotFoundYet: 

645 raise RuntimeError( 

646 f"{len(dataIdsNotFoundYet)} dataset(s) of type " 

647 f"'{datasetType.name}' was/were present in a previous " 

648 f"query, but could not be found now." 

649 f"This is either a logic bug in QuantumGraph generation " 

650 f"or the input collections have been modified since " 

651 f"QuantumGraph generation began." 

652 ) 

653 # Copy the resolved DatasetRefs to the _QuantumScaffolding objects, 

654 # replacing the unresolved refs there, and then look up prerequisites. 

655 for task in self.tasks: 

656 _LOG.debug( 

657 "Applying resolutions and finding prerequisites for %d quanta of task with label '%s'.", 

658 len(task.quanta), 

659 task.taskDef.label 

660 ) 

661 lookupFunctions = { 

662 c.name: c.lookupFunction 

663 for c in iterConnections(task.taskDef.connections, "prerequisiteInputs") 

664 if c.lookupFunction is not None 

665 } 

666 dataIdsToSkip = [] 

667 for quantum in task.quanta.values(): 

668 # Process outputs datasets only if there is a run to look for 

669 # outputs in and skipExisting is True. Note that if 

670 # skipExisting is False, any output datasets that already exist 

671 # would have already caused an exception to be raised. 

672 # We never update the DatasetRefs in the quantum because those 

673 # should never be resolved. 

674 if run is not None and skipExisting: 

675 resolvedRefs = [] 

676 unresolvedRefs = [] 

677 for datasetType, originalRefs in quantum.outputs.items(): 

678 for ref in task.outputs.extract(datasetType, originalRefs.keys()): 

679 if ref.id is not None: 

680 resolvedRefs.append(ref) 

681 else: 

682 unresolvedRefs.append(ref) 

683 if resolvedRefs: 

684 if unresolvedRefs: 

685 raise OutputExistsError( 

686 f"Quantum {quantum.dataId} of task with label " 

687 f"'{quantum.task.taskDef.label}' has some outputs that exist " 

688 f"({resolvedRefs}) " 

689 f"and others that don't ({unresolvedRefs})." 

690 ) 

691 else: 

692 # All outputs are already present; skip this 

693 # quantum and continue to the next. 

694 dataIdsToSkip.append(quantum.dataId) 

695 continue 

696 # Update the input DatasetRefs to the resolved ones we already 

697 # searched for. 

698 for datasetType, refs in quantum.inputs.items(): 

699 for ref in task.inputs.extract(datasetType, refs.keys()): 

700 refs[ref.dataId] = ref 

701 # Look up prerequisite datasets in the input collection(s). 

702 # These may have dimensions that extend beyond those we queried 

703 # for originally, because we want to permit those data ID 

704 # values to differ across quanta and dataset types. 

705 for datasetType in task.prerequisites: 

706 lookupFunction = lookupFunctions.get(datasetType.name) 

707 if lookupFunction is not None: 

708 # PipelineTask has provided its own function to do the 

709 # lookup. This always takes precedence. 

710 refs = list( 

711 lookupFunction(datasetType, registry, quantum.dataId, collections) 

712 ) 

713 elif (datasetType.isCalibration() 

714 and datasetType.dimensions <= quantum.dataId.graph 

715 and quantum.dataId.graph.temporal): 

716 # This is a master calibration lookup, which we have to 

717 # handle specially because the query system can't do a 

718 # temporal join on a non-dimension-based timespan yet. 

719 timespan = quantum.dataId.timespan 

720 try: 

721 refs = [registry.findDataset(datasetType, quantum.dataId, 

722 collections=collections, 

723 timespan=timespan)] 

724 except KeyError: 

725 # This dataset type is not present in the registry, 

726 # which just means there are no datasets here. 

727 refs = [] 

728 else: 

729 # Most general case. 

730 refs = list(registry.queryDatasets(datasetType, 

731 collections=collections, 

732 dataId=quantum.dataId, 

733 deduplicate=True).expanded()) 

734 quantum.prerequisites[datasetType].update({ref.dataId: ref for ref in refs 

735 if ref is not None}) 

736 # Actually remove any quanta that we decided to skip above. 

737 if dataIdsToSkip: 

738 _LOG.debug("Pruning %d quanta for task with label '%s' because all of their outputs exist.", 

739 len(dataIdsToSkip), task.taskDef.label) 

740 for dataId in dataIdsToSkip: 

741 del task.quanta[dataId] 

742 

743 def makeQuantumGraph(self): 

744 """Create a `QuantumGraph` from the quanta already present in 

745 the scaffolding data structure. 

746 

747 Returns 

748 ------- 

749 graph : `QuantumGraph` 

750 The full `QuantumGraph`. 

751 """ 

752 graph = QuantumGraph({task.taskDef: task.makeQuantumSet() for task in self.tasks}) 

753 return graph 

754 

755 

756class _InstrumentFinder(TreeVisitor): 

757 """Implementation of TreeVisitor which looks for instrument name 

758 

759 Instrument should be specified as a boolean expression 

760 

761 instrument = 'string' 

762 'string' = instrument 

763 

764 so we only need to find a binary operator where operator is "=", 

765 one side is a string literal and other side is an identifier. 

766 All visit methods return tuple of (type, value), non-useful nodes 

767 return None for both type and value. 

768 """ 

769 def __init__(self): 

770 self.instruments = [] 

771 

772 def visitNumericLiteral(self, value, node): 

773 # do not care about numbers 

774 return (None, None) 

775 

776 def visitStringLiteral(self, value, node): 

777 # return type and value 

778 return ("str", value) 

779 

780 def visitTimeLiteral(self, value, node): 

781 # do not care about these 

782 return (None, None) 

783 

784 def visitRangeLiteral(self, start, stop, stride, node): 

785 # do not care about these 

786 return (None, None) 

787 

788 def visitIdentifier(self, name, node): 

789 if name.lower() == "instrument": 

790 return ("id", "instrument") 

791 return (None, None) 

792 

793 def visitUnaryOp(self, operator, operand, node): 

794 # do not care about these 

795 return (None, None) 

796 

797 def visitBinaryOp(self, operator, lhs, rhs, node): 

798 if operator == "=": 

799 if lhs == ("id", "instrument") and rhs[0] == "str": 

800 self.instruments.append(rhs[1]) 

801 elif rhs == ("id", "instrument") and lhs[0] == "str": 

802 self.instruments.append(lhs[1]) 

803 return (None, None) 

804 

805 def visitIsIn(self, lhs, values, not_in, node): 

806 # do not care about these 

807 return (None, None) 

808 

809 def visitParens(self, expression, node): 

810 # do not care about these 

811 return (None, None) 

812 

813 

814def _findInstruments(queryStr): 

815 """Get the names of any instrument named in the query string by searching 

816 for "instrument = <value>" and similar patterns. 

817 

818 Parameters 

819 ---------- 

820 queryStr : `str` or None 

821 The query string to search, or None if there is no query. 

822 

823 Returns 

824 ------- 

825 instruments : `list` [`str`] 

826 The list of instrument names found in the query. 

827 

828 Raises 

829 ------ 

830 ValueError 

831 If the query expression can not be parsed. 

832 """ 

833 if not queryStr: 

834 return [] 

835 parser = ParserYacc() 

836 finder = _InstrumentFinder() 

837 try: 

838 tree = parser.parse(queryStr) 

839 except ParseError as exc: 

840 raise ValueError(f"failed to parse query expression: {queryStr}") from exc 

841 tree.visit(finder) 

842 return finder.instruments 

843 

844 

845# ------------------------ 

846# Exported definitions -- 

847# ------------------------ 

848 

849 

850class GraphBuilderError(Exception): 

851 """Base class for exceptions generated by graph builder. 

852 """ 

853 pass 

854 

855 

856class OutputExistsError(GraphBuilderError): 

857 """Exception generated when output datasets already exist. 

858 """ 

859 pass 

860 

861 

862class PrerequisiteMissingError(GraphBuilderError): 

863 """Exception generated when a prerequisite dataset does not exist. 

864 """ 

865 pass 

866 

867 

868class GraphBuilder(object): 

869 """GraphBuilder class is responsible for building task execution graph from 

870 a Pipeline. 

871 

872 Parameters 

873 ---------- 

874 registry : `~lsst.daf.butler.Registry` 

875 Data butler instance. 

876 skipExisting : `bool`, optional 

877 If `True` (default), a Quantum is not created if all its outputs 

878 already exist. 

879 """ 

880 

881 def __init__(self, registry, skipExisting=True): 

882 self.registry = registry 

883 self.dimensions = registry.dimensions 

884 self.skipExisting = skipExisting 

885 

886 def makeGraph(self, pipeline, collections, run, userQuery): 

887 """Create execution graph for a pipeline. 

888 

889 Parameters 

890 ---------- 

891 pipeline : `Pipeline` 

892 Pipeline definition, task names/classes and their configs. 

893 collections : `lsst.daf.butler.CollectionSearch` 

894 Object representing the collections to search for input datasets. 

895 run : `str`, optional 

896 Name of the `~lsst.daf.butler.CollectionType.RUN` collection for 

897 output datasets, if it already exists. 

898 userQuery : `str` 

899 String which defines user-defined selection for registry, should be 

900 empty or `None` if there is no restrictions on data selection. 

901 

902 Returns 

903 ------- 

904 graph : `QuantumGraph` 

905 

906 Raises 

907 ------ 

908 UserExpressionError 

909 Raised when user expression cannot be parsed. 

910 OutputExistsError 

911 Raised when output datasets already exist. 

912 Exception 

913 Other exceptions types may be raised by underlying registry 

914 classes. 

915 """ 

916 scaffolding = _PipelineScaffolding(pipeline, registry=self.registry) 

917 

918 instrument = pipeline.getInstrument() 

919 if isinstance(instrument, str): 

920 instrument = doImport(instrument) 

921 instrumentName = instrument.getName() if instrument else None 

922 userQuery = self._verifyInstrumentRestriction(instrumentName, userQuery) 

923 

924 with scaffolding.connectDataIds(self.registry, collections, userQuery) as commonDataIds: 

925 scaffolding.resolveDatasetRefs(self.registry, collections, run, commonDataIds, 

926 skipExisting=self.skipExisting) 

927 return scaffolding.makeQuantumGraph() 

928 

929 @staticmethod 

930 def _verifyInstrumentRestriction(instrumentName, query): 

931 """Add an instrument restriction to the query if it does not have one, 

932 and verify that if given an instrument name that there are no other 

933 instrument restrictions in the query. 

934 

935 Parameters 

936 ---------- 

937 instrumentName : `str` 

938 The name of the instrument that should appear in the query. 

939 query : `str` 

940 The query string. 

941 

942 Returns 

943 ------- 

944 query : `str` 

945 The query string with the instrument added to it if needed. 

946 

947 Raises 

948 ------ 

949 RuntimeError 

950 If the pipeline names an instrument and the query contains more 

951 than one instrument or the name of the instrument in the query does 

952 not match the instrument named by the pipeline. 

953 """ 

954 if not instrumentName: 

955 return query 

956 queryInstruments = _findInstruments(query) 

957 if len(queryInstruments) > 1: 

958 raise RuntimeError(f"When the pipeline has an instrument (\"{instrumentName}\") the query must " 

959 "have zero instruments or one instrument that matches the pipeline. " 

960 f"Found these instruments in the query: {queryInstruments}.") 

961 if not queryInstruments: 

962 # There is not an instrument in the query, add it: 

963 restriction = f"instrument = '{instrumentName}'" 

964 _LOG.debug(f"Adding restriction \"{restriction}\" to query.") 

965 query = f"{restriction} AND ({query})" if query else restriction # (there may not be a query) 

966 elif queryInstruments[0] != instrumentName: 

967 # Since there is an instrument in the query, it should match 

968 # the instrument in the pipeline. 

969 raise RuntimeError(f"The instrument named in the query (\"{queryInstruments[0]}\") does not " 

970 f"match the instrument named by the pipeline (\"{instrumentName}\")") 

971 return query