23 __all__ = (
"RawIngestTask",
"RawIngestConfig",
"makeTransferChoiceField")
27 from dataclasses
import dataclass
28 from typing
import List, Dict, Iterator, Iterable, Type, Optional, Any, Mapping
29 from collections
import defaultdict
30 from multiprocessing
import Pool
32 from astro_metadata_translator
import ObservationInfo, fix_header, merge_headers
34 from lsst.afw.fits
import readMetadata
35 from lsst.daf.butler
import (
44 from lsst.geom
import Box2D
45 from lsst.pex.config
import Config, Field, ChoiceField
46 from lsst.pipe.base
import Task
47 from lsst.sphgeom
import ConvexPolygon
49 from .fitsRawFormatterBase
import FitsRawFormatterBase
54 """Structure that hold information about a single dataset within a 58 dataId: DataCoordinate
59 """Data ID for this file (`lsst.daf.butler.DataCoordinate`). 61 This may be a minimal `~lsst.daf.butler.DataCoordinate` base instance, or 62 a complete `~lsst.daf.butler.ExpandedDataCoordinate`. 65 obsInfo: ObservationInfo
66 """Standardized observation metadata extracted directly from the file 67 headers (`astro_metadata_translator.ObservationInfo`). 71 """Region on the sky covered by this file, possibly with padding 72 (`lsst.sphgeom.ConvexPolygon`). 78 """Structure that holds information about a single raw file, used during 82 datasets: List[RawFileDatasetInfo]
83 """The information describing each dataset within this raw file. 84 (`list` of `RawFileDatasetInfo`) 88 """Name of the file this information was extracted from (`str`). 90 This is the path prior to ingest, not the path after ingest. 93 FormatterClass: Type[FitsRawFormatterBase]
94 """Formatter class that should be used to ingest this file and compute 95 a spatial region for it (`type`; as subclass of `FitsRawFormatterBase`). 101 """Structure that holds information about a complete raw exposure, used 105 dataId: DataCoordinate
106 """Data ID for this exposure (`lsst.daf.butler.DataCoordinate`). 108 This may be a minimal `~lsst.daf.butler.DataCoordinate` base instance, or 109 a complete `~lsst.daf.butler.ExpandedDataCoordinate`. 112 files: List[RawFileData]
113 """List of structures containing file-level information. 116 records: Optional[Dict[str, List[DimensionRecord]]] =
None 117 """Dictionary containing `DimensionRecord` instances that must be inserted 118 into the `~lsst.daf.butler.Registry` prior to file-level ingest (`dict`). 120 Keys are the names of dimension elements ("exposure" and optionally "visit" 121 and "visit_detector_region"), while values are lists of `DimensionRecord`. 123 May be `None` during some ingest steps. 128 """Create a Config field with options for how to transfer files between 131 The allowed options for the field are exactly those supported by 132 `lsst.daf.butler.Datastore.ingest`. 137 Documentation for the configuration field. 141 field : `lsst.pex.config.ChoiceField` 147 allowed={
"move":
"move",
149 "hardlink":
"hard link",
150 "symlink":
"symbolic (soft) link"},
158 padRegionAmount = Field(
161 doc=
"Pad an image with specified number of pixels before calculating region" 164 doc=(
"Fully-qualified Python name of the `Instrument` subclass to " 165 "associate with all raws."),
173 """Driver Task for ingesting raw data into Gen3 Butler repositories. 175 This Task is intended to be runnable from the command-line, but it doesn't 176 meet the other requirements of CmdLineTask or PipelineTask, and wouldn't 177 gain much from being one. It also wouldn't really be appropriate as a 178 subtask of a CmdLineTask or PipelineTask; it's a Task essentially just to 179 leverage the logging and configurability functionality that provides. 181 Each instance of `RawIngestTask` writes to the same Butler. Each 182 invocation of `RawIngestTask.run` ingests a list of files. 186 config : `RawIngestConfig` 187 Configuration for the task. 188 butler : `~lsst.daf.butler.Butler` 189 Butler instance. Ingested Datasets will be created as part of 190 ``butler.run`` and associated with its Collection. 192 Additional keyword arguments are forwarded to the `lsst.pipe.base.Task` 195 Other keyword arguments are forwarded to the Task base class constructor. 198 ConfigClass = RawIngestConfig
200 _DefaultName =
"ingest" 203 """Return the DatasetType of the Datasets ingested by this Task. 205 return DatasetType(
"raw", (
"instrument",
"detector",
"exposure"),
"Exposure",
206 universe=self.
butler.registry.dimensions)
208 def __init__(self, config: Optional[RawIngestConfig] =
None, *, butler: Butler, **kwds: Any):
221 """Extract and process metadata from a single raw file. 231 A structure containing the metadata extracted from the file, 232 as well as the original filename. All fields will be populated, 233 but the `RawFileData.dataId` attribute will be a minimal 234 (unexpanded) `DataCoordinate` instance. 238 Assumes that there is a single dataset associated with the given 239 file. Instruments using a single file to store multiple datasets 240 must implement their own version of this method. 242 phdu = readMetadata(filename, 0)
243 header = merge_headers([phdu, readMetadata(filename)], mode=
"overwrite")
250 FormatterClass = self.
instrument.getRawFormatter(datasets[0].dataId)
252 return RawFileData(datasets=datasets, filename=filename,
253 FormatterClass=FormatterClass)
255 def _calculate_dataset_info(self, header, filename):
256 """Calculate a RawFileDatasetInfo from the supplied information. 261 Header from the dataset. 263 Filename to use for error messages. 267 dataset : `RawFileDatasetInfo` 268 The region, dataId, and observation information associated with 271 obsInfo = ObservationInfo(header)
272 dataId = DataCoordinate.standardize(instrument=obsInfo.instrument,
273 exposure=obsInfo.exposure_id,
274 detector=obsInfo.detector_num,
276 if obsInfo.instrument != self.
instrument.getName():
277 raise ValueError(f
"Incorrect instrument (expected {self.instrument.getName()}, " 278 f
"got {obsInfo.instrument}) for file {filename}.")
280 FormatterClass = self.
instrument.getRawFormatter(dataId)
284 def _calculate_region_from_dataset_metadata(self, obsInfo, header, FormatterClass):
285 """Calculate the sky region covered by the supplied observation 290 obsInfo : `~astro_metadata_translator.ObservationInfo` 291 Summary information of this dataset. 293 Header from the dataset. 294 FormatterClass: `type` as subclass of `FitsRawFormatterBase` 295 Formatter class that should be used to compute the spatial region. 299 region : `lsst.sphgeom.ConvexPolygon` 300 Region of sky covered by this observation. 302 if obsInfo.visit_id
is not None and obsInfo.tracking_radec
is not None:
303 formatter = FormatterClass.fromMetadata(metadata=header, obsInfo=obsInfo)
304 visitInfo = formatter.makeVisitInfo()
305 detector = self.
camera[obsInfo.detector_num]
306 wcs = formatter.makeWcs(visitInfo, detector)
307 pixBox = Box2D(detector.getBBox())
308 if self.config.padRegionAmount > 0:
309 pixBox.grow(self.config.padRegionAmount)
310 pixCorners = pixBox.getCorners()
311 sphCorners = [wcs.pixelToSky(point).getVector()
for point
in pixCorners]
312 region = ConvexPolygon(sphCorners)
318 """Group an iterable of `RawFileData` by exposure. 322 files : iterable of `RawFileData` 323 File-level information to group. 327 exposures : `list` of `RawExposureData` 328 A list of structures that group the file-level information by 329 exposure. The `RawExposureData.records` attributes of elements 330 will be `None`, but all other fields will be populated. The 331 `RawExposureData.dataId` attributes will be minimal (unexpanded) 332 `DataCoordinate` instances. 334 exposureDimensions = self.
universe[
"exposure"].graph
335 byExposure = defaultdict(list)
338 byExposure[f.datasets[0].dataId.subset(exposureDimensions)].append(f)
341 for dataId, exposureFiles
in byExposure.items()]
344 """Collect the `DimensionRecord` instances that must be inserted into 345 the `~lsst.daf.butler.Registry` before an exposure's raw files may be. 349 exposure : `RawExposureData` 350 A structure containing information about the exposure to be 351 ingested. Should be considered consumed upon return. 355 exposure : `RawExposureData` 356 An updated version of the input structure, with 357 `RawExposureData.records` populated. 359 firstFile = exposure.files[0]
360 firstDataset = firstFile.datasets[0]
361 VisitDetectorRegionRecordClass = self.
universe[
"visit_detector_region"].RecordClass
365 if firstDataset.obsInfo.visit_id
is not None:
366 exposure.records[
"visit_detector_region"] = []
368 for file
in exposure.files:
369 for dataset
in file.datasets:
370 if dataset.obsInfo.visit_id != firstDataset.obsInfo.visit_id:
371 raise ValueError(f
"Inconsistent visit/exposure relationship for " 372 f
"exposure {firstDataset.obsInfo.exposure_id} between " 373 f
"{file.filename} and {firstFile.filename}: " 374 f
"{dataset.obsInfo.visit_id} != {firstDataset.obsInfo.visit_id}.")
375 if dataset.region
is None:
376 self.log.warn(
"No region found for visit=%s, detector=%s.", dataset.obsInfo.visit_id,
377 dataset.obsInfo.detector_num)
379 visitVertices.extend(dataset.region.getVertices())
380 exposure.records[
"visit_detector_region"].append(
381 VisitDetectorRegionRecordClass.fromDict({
382 "instrument": dataset.obsInfo.instrument,
383 "visit": dataset.obsInfo.visit_id,
384 "detector": dataset.obsInfo.detector_num,
385 "region": dataset.region,
389 visitRegion = ConvexPolygon(visitVertices)
391 self.log.warn(
"No region found for visit=%s.", firstDataset.obsInfo.visit_id)
393 exposure.records[
"visit"] = [
399 """Expand the data IDs associated with a raw exposure to include 400 additional metadata records. 404 exposure : `RawExposureData` 405 A structure containing information about the exposure to be 406 ingested. Must have `RawExposureData.records` populated. Should 407 be considered consumed upon return. 411 exposure : `RawExposureData` 412 An updated version of the input structure, with 413 `RawExposureData.dataId` and nested `RawFileData.dataId` attributes 414 containing `~lsst.daf.butler.ExpandedDataCoordinate` instances. 416 hasVisit =
"visit" in data.records
420 data.dataId = self.
butler.registry.expandDataId(
427 "exposure": data.records[
"exposure"][0],
428 "visit": data.records[
"visit"][0]
if hasVisit
else None,
435 vdrRecords = data.records[
"visit_detector_region"]
if hasVisit
else itertools.repeat(
None)
436 for file, vdrRecord
in zip(data.files, vdrRecords):
437 for dataset
in file.datasets:
438 dataset.dataId = self.
butler.registry.expandDataId(
440 records=dict(data.dataId.records, visit_detector_region=vdrRecord)
444 def prep(self, files, pool: Optional[Pool] =
None, processes: int = 1) -> Iterator[RawExposureData]:
445 """Perform all ingest preprocessing steps that do not involve actually 446 modifying the database. 450 files : iterable over `str` or path-like objects 451 Paths to the files to be ingested. Will be made absolute 452 if they are not already. 453 pool : `multiprocessing.Pool`, optional 454 If not `None`, a process pool with which to parallelize some 456 processes : `int`, optional 457 The number of processes to use. Ignored if ``pool`` is not `None`. 461 exposure : `RawExposureData` 462 Data structures containing dimension records, filenames, and data 463 IDs to be ingested (one structure for each exposure). 465 if pool
is None and processes > 1:
466 pool = Pool(processes)
467 mapFunc = map
if pool
is None else pool.imap_unordered
501 """Insert dimension records for one or more exposures. 505 records : `dict` mapping `str` to `list` 506 Dimension records to be inserted, organized as a mapping from 507 dimension name to a list of records for that dimension. This 508 may be a single `RawExposureData.records` dict, or an aggregate 509 for multiple exposures created by concatenating the value lists 510 of those dictionaries. 514 refs : `list` of `lsst.daf.butler.DatasetRef` 515 Dataset references for ingested raws. 524 for dimension
in (
"visit",
"exposure",
"visit_detector_region"):
525 recordsForDimension = records.get(dimension)
526 if recordsForDimension:
531 self.
butler.registry.insertDimensionData(dimension, *recordsForDimension)
534 ) -> List[DatasetRef]:
535 """Ingest all raw files in one exposure. 539 exposure : `RawExposureData` 540 A structure containing information about the exposure to be 541 ingested. Must have `RawExposureData.records` populated and all 542 data ID attributes expanded. 543 butler : `lsst.daf.butler.Butler`, optional 544 Butler to use for ingest. If not provided, ``self.butler`` will 549 refs : `list` of `lsst.daf.butler.DatasetRef` 550 Dataset references for ingested raws. 554 datasets = [FileDataset(path=os.path.abspath(file.filename),
555 refs=[DatasetRef(self.
datasetType, d.dataId)
for d
in file.datasets],
556 formatter=file.FormatterClass)
557 for file
in exposure.files]
558 butler.ingest(*datasets, transfer=self.config.transfer)
559 return [ref
for dataset
in datasets
for ref
in dataset.refs]
561 def run(self, files, pool: Optional[Pool] =
None, processes: int = 1):
562 """Ingest files into a Butler data repository. 564 This creates any new exposure or visit Dimension entries needed to 565 identify the ingested files, creates new Dataset entries in the 566 Registry and finally ingests the files themselves into the Datastore. 567 Any needed instrument, detector, and physical_filter Dimension entries 568 must exist in the Registry before `run` is called. 572 files : iterable over `str` or path-like objects 573 Paths to the files to be ingested. Will be made absolute 574 if they are not already. 575 pool : `multiprocessing.Pool`, optional 576 If not `None`, a process pool with which to parallelize some 578 processes : `int`, optional 579 The number of processes to use. Ignored if ``pool`` is not `None`. 583 refs : `list` of `lsst.daf.butler.DatasetRef` 584 Dataset references for ingested raws. 588 This method inserts all records (dimensions and datasets) for an 589 exposure within a transaction, guaranteeing that partial exposures 592 exposureData = self.
prep(files, pool=pool, processes=processes)
603 for exposure
in exposureData:
604 with self.
butler.transaction():
def ingestExposureDatasets
def _calculate_region_from_dataset_metadata(self, obsInfo, header, FormatterClass)
def makeExposureRecordFromObsInfo(obsInfo, universe)
def _calculate_dataset_info(self, header, filename)
def makeVisitRecordFromObsInfo(obsInfo, universe, region=None)
def makeTransferChoiceField(doc="How to transfer files (None for no transfer).", default=None)
def collectDimensionRecords