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) 

43from lsst.pex.config import Config, ChoiceField 

44from lsst.pipe.base import Task 

45 

46from ._instrument import Instrument, makeExposureRecordFromObsInfo 

47from ._fitsRawFormatterBase import FitsRawFormatterBase 

48 

49 

50@dataclass 

51class RawFileDatasetInfo: 

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

53 raw file. 

54 """ 

55 

56 dataId: DataCoordinate 

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

58 """ 

59 

60 obsInfo: ObservationInfo 

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

62 headers (`astro_metadata_translator.ObservationInfo`). 

63 """ 

64 

65 

66@dataclass 

67class RawFileData: 

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

69 ingest. 

70 """ 

71 

72 datasets: List[RawFileDatasetInfo] 

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

74 (`list` of `RawFileDatasetInfo`) 

75 """ 

76 

77 filename: str 

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

79 

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

81 """ 

82 

83 FormatterClass: Type[FitsRawFormatterBase] 

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

85 subclass of `FitsRawFormatterBase`). 

86 """ 

87 

88 instrumentClass: Type[Instrument] 

89 """The `Instrument` class associated with this file.""" 

90 

91 

92@dataclass 

93class RawExposureData: 

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

95 during ingest. 

96 """ 

97 

98 dataId: DataCoordinate 

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

100 """ 

101 

102 files: List[RawFileData] 

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

104 """ 

105 

106 universe: InitVar[DimensionUniverse] 

107 """Set of all known dimensions. 

108 """ 

109 

110 record: Optional[DimensionRecord] = None 

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

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

113 """ 

114 

115 def __post_init__(self, universe: DimensionUniverse): 

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

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

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

119 

120 

121def makeTransferChoiceField(doc="How to transfer files (None for no transfer).", default="auto"): 

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

123 data repositories. 

124 

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

126 `lsst.daf.butler.Datastore.ingest`. 

127 

128 Parameters 

129 ---------- 

130 doc : `str` 

131 Documentation for the configuration field. 

132 

133 Returns 

134 ------- 

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

136 Configuration field. 

137 """ 

138 return ChoiceField( 

139 doc=doc, 

140 dtype=str, 

141 allowed={"move": "move", 

142 "copy": "copy", 

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

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

145 "hardlink": "hard link", 

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

147 "relsymlink": "relative symbolic link", 

148 }, 

149 optional=True, 

150 default=default 

151 ) 

152 

153 

154class RawIngestConfig(Config): 

155 transfer = makeTransferChoiceField() 

156 

157 

158class RawIngestTask(Task): 

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

160 

161 Parameters 

162 ---------- 

163 config : `RawIngestConfig` 

164 Configuration for the task. 

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

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

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

168 datasets. 

169 **kwargs 

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

171 constructor. 

172 

173 Notes 

174 ----- 

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

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

177 """ 

178 

179 ConfigClass = RawIngestConfig 

180 

181 _DefaultName = "ingest" 

182 

183 def getDatasetType(self): 

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

185 """ 

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

187 universe=self.butler.registry.dimensions) 

188 

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

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

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

192 self.butler = butler 

193 self.universe = self.butler.registry.dimensions 

194 self.datasetType = self.getDatasetType() 

195 

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

197 # have all the relevant metadata translators loaded. 

198 Instrument.importAll(self.butler.registry) 

199 

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

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

202 

203 Parameters 

204 ---------- 

205 filename : `str` 

206 Path to the file. 

207 

208 Returns 

209 ------- 

210 data : `RawFileData` 

211 A structure containing the metadata extracted from the file, 

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

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

214 (unexpanded) `DataCoordinate` instance. 

215 

216 Notes 

217 ----- 

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

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

220 must implement their own version of this method. 

221 """ 

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

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

224 phdu = readMetadata(filename, 0) 

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

226 fix_header(header) 

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

228 

229 # The data model currently assumes that whilst multiple datasets 

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

231 # same formatter. 

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

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

234 

235 return RawFileData(datasets=datasets, filename=filename, 

236 FormatterClass=FormatterClass, 

237 instrumentClass=instrument) 

238 

239 def _calculate_dataset_info(self, header, filename): 

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

241 

242 Parameters 

243 ---------- 

244 header : `Mapping` 

245 Header from the dataset. 

246 filename : `str` 

247 Filename to use for error messages. 

248 

249 Returns 

250 ------- 

251 dataset : `RawFileDatasetInfo` 

252 The dataId, and observation information associated with this 

253 dataset. 

254 """ 

255 obsInfo = ObservationInfo(header) 

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

257 exposure=obsInfo.exposure_id, 

258 detector=obsInfo.detector_num, 

259 universe=self.universe) 

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

261 

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

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

264 

265 Parameters 

266 ---------- 

267 files : iterable of `RawFileData` 

268 File-level information to group. 

269 

270 Returns 

271 ------- 

272 exposures : `list` of `RawExposureData` 

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

274 exposure. All fields will be populated. The 

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

276 `DataCoordinate` instances. 

277 """ 

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

279 byExposure = defaultdict(list) 

280 for f in files: 

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

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

283 

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

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

286 

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

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

289 additional metadata records. 

290 

291 Parameters 

292 ---------- 

293 exposure : `RawExposureData` 

294 A structure containing information about the exposure to be 

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

296 be considered consumed upon return. 

297 

298 Returns 

299 ------- 

300 exposure : `RawExposureData` 

301 An updated version of the input structure, with 

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

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

304 `True`. 

305 """ 

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

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

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

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

310 data.dataId, 

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

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

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

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

315 records={ 

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

317 } 

318 ) 

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

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

321 # expansion. 

322 for file in data.files: 

323 for dataset in file.datasets: 

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

325 dataset.dataId, 

326 records=dict(data.dataId.records) 

327 ) 

328 return data 

329 

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

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

332 modifying the database. 

333 

334 Parameters 

335 ---------- 

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

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

338 if they are not already. 

339 pool : `multiprocessing.Pool`, optional 

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

341 operations. 

342 processes : `int`, optional 

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

344 

345 Yields 

346 ------ 

347 exposure : `RawExposureData` 

348 Data structures containing dimension records, filenames, and data 

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

350 """ 

351 if pool is None and processes > 1: 

352 pool = Pool(processes) 

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

354 

355 # Extract metadata and build per-detector regions. 

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

357 

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

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

360 # step. 

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

362 

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

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

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

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

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

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

369 # work. 

370 

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

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

373 # metadata. 

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

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

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

377 # down, it'll happen here. 

378 return mapFunc(self.expandDataIds, exposureData) 

379 

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

381 ) -> List[DatasetRef]: 

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

383 

384 Parameters 

385 ---------- 

386 exposure : `RawExposureData` 

387 A structure containing information about the exposure to be 

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

389 data ID attributes expanded. 

390 run : `str`, optional 

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

392 ``self.butler.run``. 

393 

394 Returns 

395 ------- 

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

397 Dataset references for ingested raws. 

398 """ 

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

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

401 formatter=file.FormatterClass) 

402 for file in exposure.files] 

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

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

405 

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

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

408 

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

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

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

412 Any needed instrument, detector, and physical_filter Dimension entries 

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

414 

415 Parameters 

416 ---------- 

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

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

419 if they are not already. 

420 pool : `multiprocessing.Pool`, optional 

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

422 operations. 

423 processes : `int`, optional 

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

425 run : `str`, optional 

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

427 the default derived from the instrument name. 

428 

429 Returns 

430 ------- 

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

432 Dataset references for ingested raws. 

433 

434 Notes 

435 ----- 

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

437 guaranteeing that partial exposures are never ingested. The exposure 

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

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

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

441 the same exposure to be incremented in different runs. 

442 """ 

443 exposureData = self.prep(files, pool=pool, processes=processes) 

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

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

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

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

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

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

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

451 # transactions. 

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

453 refs = [] 

454 runs = set() 

455 for exposure in exposureData: 

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

457 # Override default run if nothing specified explicitly 

458 if run is None: 

459 instrumentClass = exposure.files[0].instrumentClass 

460 this_run = instrumentClass.makeDefaultRawIngestRunName() 

461 else: 

462 this_run = run 

463 if this_run not in runs: 

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

465 runs.add(this_run) 

466 with self.butler.transaction(): 

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

468 return refs