23 __all__ = (
"RawIngestTask",
"RawIngestConfig",
"makeTransferChoiceField")
26 from dataclasses
import dataclass, InitVar
27 from typing
import List, Iterator, Iterable, Type, Optional, Any
28 from collections
import defaultdict
29 from multiprocessing
import Pool
31 from astro_metadata_translator
import ObservationInfo, fix_header, merge_headers
32 from lsst.afw.fits
import readMetadata
33 from lsst.daf.butler
import (
44 from lsst.pex.config
import Config, ChoiceField
45 from lsst.pipe.base
import Task
47 from ._instrument
import Instrument, makeExposureRecordFromObsInfo
48 from ._fitsRawFormatterBase
import FitsRawFormatterBase
53 """Structure that holds information about a single dataset within a
57 dataId: DataCoordinate
58 """Data ID for this file (`lsst.daf.butler.DataCoordinate`).
61 obsInfo: ObservationInfo
62 """Standardized observation metadata extracted directly from the file
63 headers (`astro_metadata_translator.ObservationInfo`).
69 """Structure that holds information about a single raw file, used during
73 datasets: List[RawFileDatasetInfo]
74 """The information describing each dataset within this raw file.
75 (`list` of `RawFileDatasetInfo`)
79 """Name of the file this information was extracted from (`str`).
81 This is the path prior to ingest, not the path after ingest.
84 FormatterClass: Type[FitsRawFormatterBase]
85 """Formatter class that should be used to ingest this file (`type`; as
86 subclass of `FitsRawFormatterBase`).
89 instrumentClass: Optional[Type[Instrument]]
90 """The `Instrument` class associated with this file. Can be `None`
91 if ``datasets`` is an empty list."""
96 """Structure that holds information about a complete raw exposure, used
100 dataId: DataCoordinate
101 """Data ID for this exposure (`lsst.daf.butler.DataCoordinate`).
104 files: List[RawFileData]
105 """List of structures containing file-level information.
108 universe: InitVar[DimensionUniverse]
109 """Set of all known dimensions.
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`).
124 """Create a Config field with options for how to transfer files between
127 The allowed options for the field are exactly those supported by
128 `lsst.daf.butler.Datastore.ingest`.
133 Documentation for the configuration field.
137 field : `lsst.pex.config.ChoiceField`
143 allowed={
"move":
"move",
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",
161 """Driver Task for ingesting raw data into Gen3 Butler repositories.
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
172 Additional keyword arguments are forwarded to the `lsst.pipe.base.Task`
177 Each instance of `RawIngestTask` writes to the same Butler. Each
178 invocation of `RawIngestTask.run` ingests a list of files.
181 ConfigClass = RawIngestConfig
183 _DefaultName =
"ingest"
186 """Return the DatasetType of the datasets ingested by this Task.
188 return DatasetType(
"raw", (
"instrument",
"detector",
"exposure"),
"Exposure",
189 universe=self.
butler.registry.dimensions)
191 def __init__(self, config: Optional[RawIngestConfig] =
None, *, butler: Butler, **kwargs: Any):
200 Instrument.importAll(self.
butler.registry)
202 def _reduce_kwargs(self):
204 return dict(**super()._reduce_kwargs(), butler=self.
butler)
207 """Extract and process metadata from a single raw file.
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.
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.
236 phdu = readMetadata(filename, 0)
237 header = merge_headers([phdu, readMetadata(filename)], mode=
"overwrite")
240 except Exception
as e:
241 self.log.debug(
"Problem extracting metadata from %s: %s", filename, e)
244 FormatterClass = Formatter
247 self.log.debug(
"Extracted metadata from file %s", filename)
252 instrument = Instrument.fromName(datasets[0].dataId[
"instrument"], self.
butler.registry)
254 self.log.warning(
"Instrument %s for file %s not known to registry",
255 datasets[0].dataId[
"instrument"], filename)
257 FormatterClass = Formatter
260 FormatterClass = instrument.getRawFormatter(datasets[0].dataId)
262 return RawFileData(datasets=datasets, filename=filename,
263 FormatterClass=FormatterClass,
264 instrumentClass=instrument)
266 def _calculate_dataset_info(self, header, filename):
267 """Calculate a RawFileDatasetInfo from the supplied information.
272 Header from the dataset.
274 Filename to use for error messages.
278 dataset : `RawFileDatasetInfo`
279 The dataId, and observation information associated with this
282 obsInfo = ObservationInfo(header)
283 dataId = DataCoordinate.standardize(instrument=obsInfo.instrument,
284 exposure=obsInfo.exposure_id,
285 detector=obsInfo.detector_num,
290 """Group an iterable of `RawFileData` by exposure.
294 files : iterable of `RawFileData`
295 File-level information to group.
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.
305 exposureDimensions = self.
universe[
"exposure"].graph
306 byExposure = defaultdict(list)
309 byExposure[f.datasets[0].dataId.subset(exposureDimensions)].append(f)
312 for dataId, exposureFiles
in byExposure.items()]
315 """Expand the data IDs associated with a raw exposure to include
316 additional metadata records.
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.
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
336 data.dataId = self.
butler.registry.expandDataId(
343 self.
butler.registry.dimensions[
"exposure"]: data.record,
349 for file
in data.files:
350 for dataset
in file.datasets:
351 dataset.dataId = self.
butler.registry.expandDataId(
353 records=dict(data.dataId.records)
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.
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
369 processes : `int`, optional
370 The number of processes to use. Ignored if ``pool`` is not `None`.
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.
380 if pool
is None and processes > 1:
381 pool = Pool(processes)
382 mapFunc = map
if pool
is None else pool.imap_unordered
393 for fileDatum
in fileData:
394 if not fileDatum.datasets:
395 bad_files.append(fileDatum.filename)
397 good_files.append(fileDatum)
398 fileData = good_files
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")
427 ) -> List[DatasetRef]:
428 """Ingest all raw files in one exposure.
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
442 refs : `list` of `lsst.daf.butler.DatasetRef`
443 Dataset references for ingested raws.
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]
452 def run(self, files, *, pool: Optional[Pool] =
None, processes: int = 1, run: Optional[str] =
None):
453 """Ingest files into a Butler data repository.
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.
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
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.
477 refs : `list` of `lsst.daf.butler.DatasetRef`
478 Dataset references for ingested raws.
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.
489 exposureData, bad_files = self.
prep(files, pool=pool, processes=processes)
502 n_exposures_failed = 0
504 for exposure
in exposureData:
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)
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)
520 instrumentClass = exposure.files[0].instrumentClass
521 this_run = instrumentClass.makeDefaultRawIngestRunName()
524 if this_run
not in runs:
525 self.
butler.registry.registerCollection(this_run, type=CollectionType.RUN)
528 with self.
butler.transaction():
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)
539 self.log.info(
"Exposure %s:%s ingested successfully",
540 exposure.record.instrument, exposure.record.name)
546 self.log.warning(
"Could not extract observation metadata from the following:")
548 self.log.warning(
"- %s", f)
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:
557 self.log.info(
"Ingested %d distinct Butler dataset%s",
558 len(refs),
"" if len(refs) == 1
else "s")
561 raise RuntimeError(
"Some failures encountered during ingestion")