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 obs_base. 

2# 

3# Developed for the LSST Data Management System. 

4# This product includes software developed by the LSST Project 

5# (https://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 

22 

23__all__ = ("RawIngestTask", "RawIngestConfig", "makeTransferChoiceField") 

24 

25import os.path 

26from dataclasses import dataclass, InitVar 

27from typing import List, Iterator, Iterable, Type, Optional, Any 

28from collections import defaultdict 

29from multiprocessing import Pool 

30 

31from astro_metadata_translator import ObservationInfo, fix_header, merge_headers 

32from lsst.afw.fits import readMetadata 

33from lsst.daf.butler import ( 

34 Butler, 

35 CollectionType, 

36 DataCoordinate, 

37 DatasetRef, 

38 DatasetType, 

39 DimensionRecord, 

40 DimensionUniverse, 

41 FileDataset, 

42 Formatter, 

43) 

44from lsst.pex.config import Config, ChoiceField 

45from lsst.pipe.base import Task 

46 

47from ._instrument import Instrument, makeExposureRecordFromObsInfo 

48from ._fitsRawFormatterBase import FitsRawFormatterBase 

49 

50 

51@dataclass 

52class RawFileDatasetInfo: 

53 """Structure that holds information about a single dataset within a 

54 raw file. 

55 """ 

56 

57 dataId: DataCoordinate 

58 """Data ID for this file (`lsst.daf.butler.DataCoordinate`). 

59 """ 

60 

61 obsInfo: ObservationInfo 

62 """Standardized observation metadata extracted directly from the file 

63 headers (`astro_metadata_translator.ObservationInfo`). 

64 """ 

65 

66 

67@dataclass 

68class RawFileData: 

69 """Structure that holds information about a single raw file, used during 

70 ingest. 

71 """ 

72 

73 datasets: List[RawFileDatasetInfo] 

74 """The information describing each dataset within this raw file. 

75 (`list` of `RawFileDatasetInfo`) 

76 """ 

77 

78 filename: str 

79 """Name of the file this information was extracted from (`str`). 

80 

81 This is the path prior to ingest, not the path after ingest. 

82 """ 

83 

84 FormatterClass: Type[FitsRawFormatterBase] 

85 """Formatter class that should be used to ingest this file (`type`; as 

86 subclass of `FitsRawFormatterBase`). 

87 """ 

88 

89 instrumentClass: Optional[Type[Instrument]] 

90 """The `Instrument` class associated with this file. Can be `None` 

91 if ``datasets`` is an empty list.""" 

92 

93 

94@dataclass 

95class RawExposureData: 

96 """Structure that holds information about a complete raw exposure, used 

97 during ingest. 

98 """ 

99 

100 dataId: DataCoordinate 

101 """Data ID for this exposure (`lsst.daf.butler.DataCoordinate`). 

102 """ 

103 

104 files: List[RawFileData] 

105 """List of structures containing file-level information. 

106 """ 

107 

108 universe: InitVar[DimensionUniverse] 

109 """Set of all known dimensions. 

110 """ 

111 

112 record: Optional[DimensionRecord] = None 

113 """The exposure `DimensionRecord` that must be inserted into the 

114 `~lsst.daf.butler.Registry` prior to file-level ingest (`DimensionRecord`). 

115 """ 

116 

117 def __post_init__(self, universe: DimensionUniverse): 

118 # We don't care which file or dataset we read metadata from, because 

119 # we're assuming they'll all be the same; just use the first ones. 

120 self.record = makeExposureRecordFromObsInfo(self.files[0].datasets[0].obsInfo, universe) 

121 

122 

123def makeTransferChoiceField(doc="How to transfer files (None for no transfer).", default="auto"): 

124 """Create a Config field with options for how to transfer files between 

125 data repositories. 

126 

127 The allowed options for the field are exactly those supported by 

128 `lsst.daf.butler.Datastore.ingest`. 

129 

130 Parameters 

131 ---------- 

132 doc : `str` 

133 Documentation for the configuration field. 

134 

135 Returns 

136 ------- 

137 field : `lsst.pex.config.ChoiceField` 

138 Configuration field. 

139 """ 

140 return ChoiceField( 

141 doc=doc, 

142 dtype=str, 

143 allowed={"move": "move", 

144 "copy": "copy", 

145 "auto": "choice will depend on datastore", 

146 "link": "hard link falling back to symbolic link", 

147 "hardlink": "hard link", 

148 "symlink": "symbolic (soft) link", 

149 "relsymlink": "relative symbolic link", 

150 }, 

151 optional=True, 

152 default=default 

153 ) 

154 

155 

156class RawIngestConfig(Config): 

157 transfer = makeTransferChoiceField() 

158 

159 

160class RawIngestTask(Task): 

161 """Driver Task for ingesting raw data into Gen3 Butler repositories. 

162 

163 Parameters 

164 ---------- 

165 config : `RawIngestConfig` 

166 Configuration for the task. 

167 butler : `~lsst.daf.butler.Butler` 

168 Writeable butler instance, with ``butler.run`` set to the appropriate 

169 `~lsst.daf.butler.CollectionType.RUN` collection for these raw 

170 datasets. 

171 **kwargs 

172 Additional keyword arguments are forwarded to the `lsst.pipe.base.Task` 

173 constructor. 

174 

175 Notes 

176 ----- 

177 Each instance of `RawIngestTask` writes to the same Butler. Each 

178 invocation of `RawIngestTask.run` ingests a list of files. 

179 """ 

180 

181 ConfigClass = RawIngestConfig 

182 

183 _DefaultName = "ingest" 

184 

185 def getDatasetType(self): 

186 """Return the DatasetType of the datasets ingested by this Task. 

187 """ 

188 return DatasetType("raw", ("instrument", "detector", "exposure"), "Exposure", 

189 universe=self.butler.registry.dimensions) 

190 

191 def __init__(self, config: Optional[RawIngestConfig] = None, *, butler: Butler, **kwargs: Any): 

192 config.validate() # Not a CmdlineTask nor PipelineTask, so have to validate the config here. 

193 super().__init__(config, **kwargs) 

194 self.butler = butler 

195 self.universe = self.butler.registry.dimensions 

196 self.datasetType = self.getDatasetType() 

197 

198 # Import all the instrument classes so that we ensure that we 

199 # have all the relevant metadata translators loaded. 

200 Instrument.importAll(self.butler.registry) 

201 

202 def _reduce_kwargs(self): 

203 # Add extra parameters to pickle 

204 return dict(**super()._reduce_kwargs(), butler=self.butler) 

205 

206 def extractMetadata(self, filename: str) -> RawFileData: 

207 """Extract and process metadata from a single raw file. 

208 

209 Parameters 

210 ---------- 

211 filename : `str` 

212 Path to the file. 

213 

214 Returns 

215 ------- 

216 data : `RawFileData` 

217 A structure containing the metadata extracted from the file, 

218 as well as the original filename. All fields will be populated, 

219 but the `RawFileData.dataId` attribute will be a minimal 

220 (unexpanded) `DataCoordinate` instance. 

221 

222 Notes 

223 ----- 

224 Assumes that there is a single dataset associated with the given 

225 file. Instruments using a single file to store multiple datasets 

226 must implement their own version of this method. 

227 """ 

228 

229 # We do not want to stop ingest if we are given a bad file. 

230 # Instead return a RawFileData with no datasets and allow 

231 # the caller to report the failure. 

232 

233 try: 

234 # Manually merge the primary and "first data" headers here because 

235 # we do not know in general if an input file has set INHERIT=T. 

236 phdu = readMetadata(filename, 0) 

237 header = merge_headers([phdu, readMetadata(filename)], mode="overwrite") 

238 fix_header(header) 

239 datasets = [self._calculate_dataset_info(header, filename)] 

240 except Exception as e: 

241 self.log.debug("Problem extracting metadata from %s: %s", filename, e) 

242 # Indicate to the caller that we failed to read 

243 datasets = [] 

244 FormatterClass = Formatter 

245 instrument = None 

246 else: 

247 self.log.debug("Extracted metadata from file %s", filename) 

248 # The data model currently assumes that whilst multiple datasets 

249 # can be associated with a single file, they must all share the 

250 # same formatter. 

251 try: 

252 instrument = Instrument.fromName(datasets[0].dataId["instrument"], self.butler.registry) 

253 except LookupError: 

254 self.log.warning("Instrument %s for file %s not known to registry", 

255 datasets[0].dataId["instrument"], filename) 

256 datasets = [] 

257 FormatterClass = Formatter 

258 instrument = None 

259 else: 

260 FormatterClass = instrument.getRawFormatter(datasets[0].dataId) 

261 

262 return RawFileData(datasets=datasets, filename=filename, 

263 FormatterClass=FormatterClass, 

264 instrumentClass=instrument) 

265 

266 def _calculate_dataset_info(self, header, filename): 

267 """Calculate a RawFileDatasetInfo from the supplied information. 

268 

269 Parameters 

270 ---------- 

271 header : `Mapping` 

272 Header from the dataset. 

273 filename : `str` 

274 Filename to use for error messages. 

275 

276 Returns 

277 ------- 

278 dataset : `RawFileDatasetInfo` 

279 The dataId, and observation information associated with this 

280 dataset. 

281 """ 

282 obsInfo = ObservationInfo(header) 

283 dataId = DataCoordinate.standardize(instrument=obsInfo.instrument, 

284 exposure=obsInfo.exposure_id, 

285 detector=obsInfo.detector_num, 

286 universe=self.universe) 

287 return RawFileDatasetInfo(obsInfo=obsInfo, dataId=dataId) 

288 

289 def groupByExposure(self, files: Iterable[RawFileData]) -> List[RawExposureData]: 

290 """Group an iterable of `RawFileData` by exposure. 

291 

292 Parameters 

293 ---------- 

294 files : iterable of `RawFileData` 

295 File-level information to group. 

296 

297 Returns 

298 ------- 

299 exposures : `list` of `RawExposureData` 

300 A list of structures that group the file-level information by 

301 exposure. All fields will be populated. The 

302 `RawExposureData.dataId` attributes will be minimal (unexpanded) 

303 `DataCoordinate` instances. 

304 """ 

305 exposureDimensions = self.universe["exposure"].graph 

306 byExposure = defaultdict(list) 

307 for f in files: 

308 # Assume that the first dataset is representative for the file 

309 byExposure[f.datasets[0].dataId.subset(exposureDimensions)].append(f) 

310 

311 return [RawExposureData(dataId=dataId, files=exposureFiles, universe=self.universe) 

312 for dataId, exposureFiles in byExposure.items()] 

313 

314 def expandDataIds(self, data: RawExposureData) -> RawExposureData: 

315 """Expand the data IDs associated with a raw exposure to include 

316 additional metadata records. 

317 

318 Parameters 

319 ---------- 

320 exposure : `RawExposureData` 

321 A structure containing information about the exposure to be 

322 ingested. Must have `RawExposureData.records` populated. Should 

323 be considered consumed upon return. 

324 

325 Returns 

326 ------- 

327 exposure : `RawExposureData` 

328 An updated version of the input structure, with 

329 `RawExposureData.dataId` and nested `RawFileData.dataId` attributes 

330 updated to data IDs for which `DataCoordinate.hasRecords` returns 

331 `True`. 

332 """ 

333 # We start by expanded the exposure-level data ID; we won't use that 

334 # directly in file ingest, but this lets us do some database lookups 

335 # once per exposure instead of once per file later. 

336 data.dataId = self.butler.registry.expandDataId( 

337 data.dataId, 

338 # We pass in the records we'll be inserting shortly so they aren't 

339 # looked up from the database. We do expect instrument and filter 

340 # records to be retrieved from the database here (though the 

341 # Registry may cache them so there isn't a lookup every time). 

342 records={ 

343 self.butler.registry.dimensions["exposure"]: data.record, 

344 } 

345 ) 

346 # Now we expand the per-file (exposure+detector) data IDs. This time 

347 # we pass in the records we just retrieved from the exposure data ID 

348 # expansion. 

349 for file in data.files: 

350 for dataset in file.datasets: 

351 dataset.dataId = self.butler.registry.expandDataId( 

352 dataset.dataId, 

353 records=dict(data.dataId.records) 

354 ) 

355 return data 

356 

357 def prep(self, files, *, pool: Optional[Pool] = None, processes: int = 1) -> Iterator[RawExposureData]: 

358 """Perform all ingest preprocessing steps that do not involve actually 

359 modifying the database. 

360 

361 Parameters 

362 ---------- 

363 files : iterable over `str` or path-like objects 

364 Paths to the files to be ingested. Will be made absolute 

365 if they are not already. 

366 pool : `multiprocessing.Pool`, optional 

367 If not `None`, a process pool with which to parallelize some 

368 operations. 

369 processes : `int`, optional 

370 The number of processes to use. Ignored if ``pool`` is not `None`. 

371 

372 Yields 

373 ------ 

374 exposure : `RawExposureData` 

375 Data structures containing dimension records, filenames, and data 

376 IDs to be ingested (one structure for each exposure). 

377 bad_files : `list` of `str` 

378 List of all the files that could not have metadata extracted. 

379 """ 

380 if pool is None and processes > 1: 

381 pool = Pool(processes) 

382 mapFunc = map if pool is None else pool.imap_unordered 

383 

384 # Extract metadata and build per-detector regions. 

385 # This could run in a subprocess so collect all output 

386 # before looking at failures. 

387 fileData: Iterator[RawFileData] = mapFunc(self.extractMetadata, files) 

388 

389 # Filter out all the failed reads and store them for later 

390 # reporting 

391 good_files = [] 

392 bad_files = [] 

393 for fileDatum in fileData: 

394 if not fileDatum.datasets: 

395 bad_files.append(fileDatum.filename) 

396 else: 

397 good_files.append(fileDatum) 

398 fileData = good_files 

399 

400 self.log.info("Successfully extracted metadata from %d file%s with %d failure%s", 

401 len(fileData), "" if len(fileData) == 1 else "s", 

402 len(bad_files), "" if len(bad_files) == 1 else "s") 

403 

404 # Use that metadata to group files (and extracted metadata) by 

405 # exposure. Never parallelized because it's intrinsically a gather 

406 # step. 

407 exposureData: List[RawExposureData] = self.groupByExposure(fileData) 

408 

409 # The next operation operates on RawExposureData instances (one at 

410 # a time) in-place and then returns the modified instance. We call it 

411 # as a pass-through instead of relying on the arguments we pass in to 

412 # have been modified because in the parallel case those arguments are 

413 # going to be pickled and unpickled, and I'm not certain 

414 # multiprocessing is careful enough with that for output arguments to 

415 # work. 

416 

417 # Expand the data IDs to include all dimension metadata; we need this 

418 # because we may need to generate path templates that rely on that 

419 # metadata. 

420 # This is the first step that involves actual database calls (but just 

421 # SELECTs), so if there's going to be a problem with connections vs. 

422 # multiple processes, or lock contention (in SQLite) slowing things 

423 # down, it'll happen here. 

424 return mapFunc(self.expandDataIds, exposureData), bad_files 

425 

426 def ingestExposureDatasets(self, exposure: RawExposureData, *, run: Optional[str] = None 

427 ) -> List[DatasetRef]: 

428 """Ingest all raw files in one exposure. 

429 

430 Parameters 

431 ---------- 

432 exposure : `RawExposureData` 

433 A structure containing information about the exposure to be 

434 ingested. Must have `RawExposureData.records` populated and all 

435 data ID attributes expanded. 

436 run : `str`, optional 

437 Name of a RUN-type collection to write to, overriding 

438 ``self.butler.run``. 

439 

440 Returns 

441 ------- 

442 refs : `list` of `lsst.daf.butler.DatasetRef` 

443 Dataset references for ingested raws. 

444 """ 

445 datasets = [FileDataset(path=os.path.abspath(file.filename), 

446 refs=[DatasetRef(self.datasetType, d.dataId) for d in file.datasets], 

447 formatter=file.FormatterClass) 

448 for file in exposure.files] 

449 self.butler.ingest(*datasets, transfer=self.config.transfer, run=run) 

450 return [ref for dataset in datasets for ref in dataset.refs] 

451 

452 def run(self, files, *, pool: Optional[Pool] = None, processes: int = 1, run: Optional[str] = None): 

453 """Ingest files into a Butler data repository. 

454 

455 This creates any new exposure or visit Dimension entries needed to 

456 identify the ingested files, creates new Dataset entries in the 

457 Registry and finally ingests the files themselves into the Datastore. 

458 Any needed instrument, detector, and physical_filter Dimension entries 

459 must exist in the Registry before `run` is called. 

460 

461 Parameters 

462 ---------- 

463 files : iterable over `str` or path-like objects 

464 Paths to the files to be ingested. Will be made absolute 

465 if they are not already. 

466 pool : `multiprocessing.Pool`, optional 

467 If not `None`, a process pool with which to parallelize some 

468 operations. 

469 processes : `int`, optional 

470 The number of processes to use. Ignored if ``pool`` is not `None`. 

471 run : `str`, optional 

472 Name of a RUN-type collection to write to, overriding 

473 the default derived from the instrument name. 

474 

475 Returns 

476 ------- 

477 refs : `list` of `lsst.daf.butler.DatasetRef` 

478 Dataset references for ingested raws. 

479 

480 Notes 

481 ----- 

482 This method inserts all datasets for an exposure within a transaction, 

483 guaranteeing that partial exposures are never ingested. The exposure 

484 dimension record is inserted with `Registry.syncDimensionData` first 

485 (in its own transaction), which inserts only if a record with the same 

486 primary key does not already exist. This allows different files within 

487 the same exposure to be incremented in different runs. 

488 """ 

489 exposureData, bad_files = self.prep(files, pool=pool, processes=processes) 

490 # Up to this point, we haven't modified the data repository at all. 

491 # Now we finally do that, with one transaction per exposure. This is 

492 # not parallelized at present because the performance of this step is 

493 # limited by the database server. That may or may not change in the 

494 # future once we increase our usage of bulk inserts and reduce our 

495 # usage of savepoints; we've tried to get everything but the database 

496 # operations done in advance to reduce the time spent inside 

497 # transactions. 

498 self.butler.registry.registerDatasetType(self.datasetType) 

499 refs = [] 

500 runs = set() 

501 n_exposures = 0 

502 n_exposures_failed = 0 

503 n_ingests_failed = 0 

504 for exposure in exposureData: 

505 

506 self.log.debug("Attempting to ingest %d file%s from exposure %s:%s", 

507 len(exposure.files), "" if len(exposure.files) == 1 else "s", 

508 exposure.record.instrument, exposure.record.name) 

509 

510 try: 

511 self.butler.registry.syncDimensionData("exposure", exposure.record) 

512 except Exception as e: 

513 n_exposures_failed += 1 

514 self.log.warning("Exposure %s:%s could not be registered: %s", 

515 exposure.record.instrument, exposure.record.name, e) 

516 continue 

517 

518 # Override default run if nothing specified explicitly 

519 if run is None: 

520 instrumentClass = exposure.files[0].instrumentClass 

521 this_run = instrumentClass.makeDefaultRawIngestRunName() 

522 else: 

523 this_run = run 

524 if this_run not in runs: 

525 self.butler.registry.registerCollection(this_run, type=CollectionType.RUN) 

526 runs.add(this_run) 

527 try: 

528 with self.butler.transaction(): 

529 refs.extend(self.ingestExposureDatasets(exposure, run=this_run)) 

530 except Exception as e: 

531 n_ingests_failed += 1 

532 self.log.warning("Failed to ingest the following for reason: %s", e) 

533 for f in exposure.files: 

534 self.log.warning("- %s", f.filename) 

535 continue 

536 

537 # Success for this exposure 

538 n_exposures += 1 

539 self.log.info("Exposure %s:%s ingested successfully", 

540 exposure.record.instrument, exposure.record.name) 

541 

542 had_failure = False 

543 

544 if bad_files: 

545 had_failure = True 

546 self.log.warning("Could not extract observation metadata from the following:") 

547 for f in bad_files: 

548 self.log.warning("- %s", f) 

549 

550 self.log.info("Successfully processed data from %d exposure%s with %d failure%s from exposure" 

551 " registration and %d failure%s from file ingest.", 

552 n_exposures, "" if n_exposures == 1 else "s", 

553 n_exposures_failed, "" if n_exposures_failed == 1 else "s", 

554 n_ingests_failed, "" if n_ingests_failed == 1 else "s") 

555 if n_exposures_failed > 0 or n_ingests_failed > 0: 

556 had_failure = True 

557 self.log.info("Ingested %d distinct Butler dataset%s", 

558 len(refs), "" if len(refs) == 1 else "s") 

559 

560 if had_failure: 

561 raise RuntimeError("Some failures encountered during ingestion") 

562 

563 return refs