Coverage for python/lsst/obs/base/ingest.py : 31%

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/>.
23__all__ = ("RawIngestTask", "RawIngestConfig", "makeTransferChoiceField")
25import os.path
26import itertools
27from dataclasses import dataclass
28from typing import List, Dict, Iterator, Iterable, Type, Optional, Any, Mapping
29from collections import defaultdict
30from multiprocessing import Pool
32from astro_metadata_translator import ObservationInfo, fix_header, merge_headers
33from lsst.utils import doImport
34from lsst.afw.fits import readMetadata
35from lsst.daf.butler import (
36 Butler,
37 DataCoordinate,
38 DatasetRef,
39 DatasetType,
40 DimensionRecord,
41 FileDataset,
42)
43from lsst.obs.base.instrument import makeExposureRecordFromObsInfo, makeVisitRecordFromObsInfo
44from lsst.geom import Box2D
45from lsst.pex.config import Config, Field, ChoiceField
46from lsst.pipe.base import Task
47from lsst.sphgeom import ConvexPolygon
49from .fitsRawFormatterBase import FitsRawFormatterBase
52@dataclass
53class RawFileDatasetInfo:
54 """Structure that hold information about a single dataset within a
55 raw file.
56 """
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`.
63 """
65 obsInfo: ObservationInfo
66 """Standardized observation metadata extracted directly from the file
67 headers (`astro_metadata_translator.ObservationInfo`).
68 """
70 region: ConvexPolygon
71 """Region on the sky covered by this file, possibly with padding
72 (`lsst.sphgeom.ConvexPolygon`).
73 """
76@dataclass
77class RawFileData:
78 """Structure that holds information about a single raw file, used during
79 ingest.
80 """
82 datasets: List[RawFileDatasetInfo]
83 """The information describing each dataset within this raw file.
84 (`list` of `RawFileDatasetInfo`)
85 """
87 filename: str
88 """Name of the file this information was extracted from (`str`).
90 This is the path prior to ingest, not the path after ingest.
91 """
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`).
96 """
99@dataclass
100class RawExposureData:
101 """Structure that holds information about a complete raw exposure, used
102 during ingest.
103 """
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`.
110 """
112 files: List[RawFileData]
113 """List of structures containing file-level information.
114 """
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.
124 """
127def makeTransferChoiceField(doc="How to transfer files (None for no transfer).", default=None):
128 """Create a Config field with options for how to transfer files between
129 data repositories.
131 The allowed options for the field are exactly those supported by
132 `lsst.daf.butler.Datastore.ingest`.
134 Parameters
135 ----------
136 doc : `str`
137 Documentation for the configuration field.
139 Returns
140 -------
141 field : `lsst.pex.config.ChoiceField`
142 Configuration field.
143 """
144 return ChoiceField(
145 doc=doc,
146 dtype=str,
147 allowed={"move": "move",
148 "copy": "copy",
149 "hardlink": "hard link",
150 "symlink": "symbolic (soft) link"},
151 optional=True,
152 default=default
153 )
156class RawIngestConfig(Config):
157 transfer = makeTransferChoiceField()
158 padRegionAmount = Field(
159 dtype=int,
160 default=0,
161 doc="Pad an image with specified number of pixels before calculating region"
162 )
163 instrument = Field(
164 doc=("Fully-qualified Python name of the `Instrument` subclass to "
165 "associate with all raws."),
166 dtype=str,
167 optional=False,
168 default=None,
169 )
172class RawIngestTask(Task):
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.
184 Parameters
185 ----------
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.
191 kwds
192 Additional keyword arguments are forwarded to the `lsst.pipe.base.Task`
193 constructor.
195 Other keyword arguments are forwarded to the Task base class constructor.
196 """
198 ConfigClass = RawIngestConfig
200 _DefaultName = "ingest"
202 def getDatasetType(self):
203 """Return the DatasetType of the Datasets ingested by this Task.
204 """
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):
209 super().__init__(config, **kwds)
210 self.butler = butler
211 self.universe = self.butler.registry.dimensions
212 self.instrument = doImport(self.config.instrument)()
213 # For now, we get a nominal Camera from the Instrument.
214 # In the future, we may want to load one from a Butler calibration
215 # collection that's appropriate for the observation timestamp of
216 # the exposure.
217 self.camera = self.instrument.getCamera()
218 self.datasetType = self.getDatasetType()
220 def extractMetadata(self, filename: str) -> RawFileData:
221 """Extract and process metadata from a single raw file.
223 Parameters
224 ----------
225 filename : `str`
226 Path to the file.
228 Returns
229 -------
230 data : `RawFileData`
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.
236 Notes
237 -----
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.
241 """
242 # Manually merge the primary and "first data" headers here because we
243 # do not know in general if an input file has set INHERIT=T.
244 phdu = readMetadata(filename, 0)
245 header = merge_headers([phdu, readMetadata(filename)], mode="overwrite")
246 fix_header(header)
247 datasets = [self._calculate_dataset_info(header, filename)]
249 # The data model currently assumes that whilst multiple datasets
250 # can be associated with a single file, they must all share the
251 # same formatter.
252 FormatterClass = self.instrument.getRawFormatter(datasets[0].dataId)
254 return RawFileData(datasets=datasets, filename=filename,
255 FormatterClass=FormatterClass)
257 def _calculate_dataset_info(self, header, filename):
258 """Calculate a RawFileDatasetInfo from the supplied information.
260 Parameters
261 ----------
262 header : `Mapping`
263 Header from the dataset.
264 filename : `str`
265 Filename to use for error messages.
267 Returns
268 -------
269 dataset : `RawFileDatasetInfo`
270 The region, dataId, and observation information associated with
271 this dataset.
272 """
273 obsInfo = ObservationInfo(header)
274 dataId = DataCoordinate.standardize(instrument=obsInfo.instrument,
275 exposure=obsInfo.exposure_id,
276 detector=obsInfo.detector_num,
277 universe=self.universe)
278 if obsInfo.instrument != self.instrument.getName():
279 raise ValueError(f"Incorrect instrument (expected {self.instrument.getName()}, "
280 f"got {obsInfo.instrument}) for file {filename}.")
282 FormatterClass = self.instrument.getRawFormatter(dataId)
283 region = self._calculate_region_from_dataset_metadata(obsInfo, header, FormatterClass)
284 return RawFileDatasetInfo(obsInfo=obsInfo, region=region, dataId=dataId)
286 def _calculate_region_from_dataset_metadata(self, obsInfo, header, FormatterClass):
287 """Calculate the sky region covered by the supplied observation
288 information.
290 Parameters
291 ----------
292 obsInfo : `~astro_metadata_translator.ObservationInfo`
293 Summary information of this dataset.
294 header : `Mapping`
295 Header from the dataset.
296 FormatterClass: `type` as subclass of `FitsRawFormatterBase`
297 Formatter class that should be used to compute the spatial region.
299 Returns
300 -------
301 region : `lsst.sphgeom.ConvexPolygon`
302 Region of sky covered by this observation.
303 """
304 if obsInfo.visit_id is not None and obsInfo.tracking_radec is not None:
305 formatter = FormatterClass.fromMetadata(metadata=header, obsInfo=obsInfo)
306 visitInfo = formatter.makeVisitInfo()
307 detector = self.camera[obsInfo.detector_num]
308 wcs = formatter.makeWcs(visitInfo, detector)
309 pixBox = Box2D(detector.getBBox())
310 if self.config.padRegionAmount > 0:
311 pixBox.grow(self.config.padRegionAmount)
312 pixCorners = pixBox.getCorners()
313 sphCorners = [wcs.pixelToSky(point).getVector() for point in pixCorners]
314 region = ConvexPolygon(sphCorners)
315 else:
316 region = None
317 return region
319 def groupByExposure(self, files: Iterable[RawFileData]) -> List[RawExposureData]:
320 """Group an iterable of `RawFileData` by exposure.
322 Parameters
323 ----------
324 files : iterable of `RawFileData`
325 File-level information to group.
327 Returns
328 -------
329 exposures : `list` of `RawExposureData`
330 A list of structures that group the file-level information by
331 exposure. The `RawExposureData.records` attributes of elements
332 will be `None`, but all other fields will be populated. The
333 `RawExposureData.dataId` attributes will be minimal (unexpanded)
334 `DataCoordinate` instances.
335 """
336 exposureDimensions = self.universe["exposure"].graph
337 byExposure = defaultdict(list)
338 for f in files:
339 # Assume that the first dataset is representative for the file
340 byExposure[f.datasets[0].dataId.subset(exposureDimensions)].append(f)
342 return [RawExposureData(dataId=dataId, files=exposureFiles)
343 for dataId, exposureFiles in byExposure.items()]
345 def collectDimensionRecords(self, exposure: RawExposureData) -> RawExposureData:
346 """Collect the `DimensionRecord` instances that must be inserted into
347 the `~lsst.daf.butler.Registry` before an exposure's raw files may be.
349 Parameters
350 ----------
351 exposure : `RawExposureData`
352 A structure containing information about the exposure to be
353 ingested. Should be considered consumed upon return.
355 Returns
356 -------
357 exposure : `RawExposureData`
358 An updated version of the input structure, with
359 `RawExposureData.records` populated.
360 """
361 firstFile = exposure.files[0]
362 firstDataset = firstFile.datasets[0]
363 VisitDetectorRegionRecordClass = self.universe["visit_detector_region"].RecordClass
364 exposure.records = {
365 "exposure": [makeExposureRecordFromObsInfo(firstDataset.obsInfo, self.universe)],
366 }
367 if firstDataset.obsInfo.visit_id is not None:
368 exposure.records["visit_detector_region"] = []
369 visitVertices = []
370 for file in exposure.files:
371 for dataset in file.datasets:
372 if dataset.obsInfo.visit_id != firstDataset.obsInfo.visit_id:
373 raise ValueError(f"Inconsistent visit/exposure relationship for "
374 f"exposure {firstDataset.obsInfo.exposure_id} between "
375 f"{file.filename} and {firstFile.filename}: "
376 f"{dataset.obsInfo.visit_id} != {firstDataset.obsInfo.visit_id}.")
377 if dataset.region is None:
378 self.log.warn("No region found for visit=%s, detector=%s.", dataset.obsInfo.visit_id,
379 dataset.obsInfo.detector_num)
380 continue
381 visitVertices.extend(dataset.region.getVertices())
382 exposure.records["visit_detector_region"].append(
383 VisitDetectorRegionRecordClass.fromDict({
384 "instrument": dataset.obsInfo.instrument,
385 "visit": dataset.obsInfo.visit_id,
386 "detector": dataset.obsInfo.detector_num,
387 "region": dataset.region,
388 })
389 )
390 if visitVertices:
391 visitRegion = ConvexPolygon(visitVertices)
392 else:
393 self.log.warn("No region found for visit=%s.", firstDataset.obsInfo.visit_id)
394 visitRegion = None
395 exposure.records["visit"] = [
396 makeVisitRecordFromObsInfo(firstDataset.obsInfo, self.universe, region=visitRegion)
397 ]
398 return exposure
400 def expandDataIds(self, data: RawExposureData) -> RawExposureData:
401 """Expand the data IDs associated with a raw exposure to include
402 additional metadata records.
404 Parameters
405 ----------
406 exposure : `RawExposureData`
407 A structure containing information about the exposure to be
408 ingested. Must have `RawExposureData.records` populated. Should
409 be considered consumed upon return.
411 Returns
412 -------
413 exposure : `RawExposureData`
414 An updated version of the input structure, with
415 `RawExposureData.dataId` and nested `RawFileData.dataId` attributes
416 containing `~lsst.daf.butler.ExpandedDataCoordinate` instances.
417 """
418 hasVisit = "visit" in data.records
419 # We start by expanded the exposure-level data ID; we won't use that
420 # directly in file ingest, but this lets us do some database lookups
421 # once per exposure instead of once per file later.
422 data.dataId = self.butler.registry.expandDataId(
423 data.dataId,
424 # We pass in the records we'll be inserting shortly so they aren't
425 # looked up from the database. We do expect instrument and filter
426 # records to be retrieved from the database here (though the
427 # Registry may cache them so there isn't a lookup every time).
428 records={
429 "exposure": data.records["exposure"][0],
430 "visit": data.records["visit"][0] if hasVisit else None,
431 }
432 )
433 # Now we expand the per-file (exposure+detector) data IDs. This time
434 # we pass in the records we just retrieved from the exposure data ID
435 # expansion as well as the visit_detector_region record, if there is
436 # one.
437 vdrRecords = data.records["visit_detector_region"] if hasVisit else itertools.repeat(None)
438 for file, vdrRecord in zip(data.files, vdrRecords):
439 for dataset in file.datasets:
440 dataset.dataId = self.butler.registry.expandDataId(
441 dataset.dataId,
442 records=dict(data.dataId.records, visit_detector_region=vdrRecord)
443 )
444 return data
446 def prep(self, files, pool: Optional[Pool] = None, processes: int = 1) -> Iterator[RawExposureData]:
447 """Perform all ingest preprocessing steps that do not involve actually
448 modifying the database.
450 Parameters
451 ----------
452 files : iterable over `str` or path-like objects
453 Paths to the files to be ingested. Will be made absolute
454 if they are not already.
455 pool : `multiprocessing.Pool`, optional
456 If not `None`, a process pool with which to parallelize some
457 operations.
458 processes : `int`, optional
459 The number of processes to use. Ignored if ``pool`` is not `None`.
461 Yields
462 ------
463 exposure : `RawExposureData`
464 Data structures containing dimension records, filenames, and data
465 IDs to be ingested (one structure for each exposure).
466 """
467 if pool is None and processes > 1:
468 pool = Pool(processes)
469 mapFunc = map if pool is None else pool.imap_unordered
471 # Extract metadata and build per-detector regions.
472 fileData: Iterator[RawFileData] = mapFunc(self.extractMetadata, files)
474 # Use that metadata to group files (and extracted metadata) by
475 # exposure. Never parallelized because it's intrinsically a gather
476 # step.
477 exposureData: List[RawExposureData] = self.groupByExposure(fileData)
479 # The next few operations operate on RawExposureData instances (one at
480 # a time) in-place and then return the modified instance. We call them
481 # as pass-throughs instead of relying on the arguments we pass in to
482 # have been modified because in the parallel case those arguments are
483 # going to be pickled and unpickled, and I'm not certain
484 # multiprocessing is careful enough with that for output arguments to
485 # work. We use the same variable names to reflect the fact that we
486 # consider the arguments to have been consumed/invalidated.
488 # Extract DimensionRecords from the metadata that will need to be
489 # inserted into the Registry before the raw datasets themselves are
490 # ingested.
491 exposureData: Iterator[RawExposureData] = mapFunc(self.collectDimensionRecords, exposureData)
493 # Expand the data IDs to include all dimension metadata; we need this
494 # because we may need to generate path templates that rely on that
495 # metadata.
496 # This is the first step that involves actual database calls (but just
497 # SELECTs), so if there's going to be a problem with connections vs.
498 # multiple processes, or lock contention (in SQLite) slowing things
499 # down, it'll happen here.
500 return mapFunc(self.expandDataIds, exposureData)
502 def insertDimensionData(self, records: Mapping[str, List[DimensionRecord]]):
503 """Insert dimension records for one or more exposures.
505 Parameters
506 ----------
507 records : `dict` mapping `str` to `list`
508 Dimension records to be inserted, organized as a mapping from
509 dimension name to a list of records for that dimension. This
510 may be a single `RawExposureData.records` dict, or an aggregate
511 for multiple exposures created by concatenating the value lists
512 of those dictionaries.
514 Returns
515 -------
516 refs : `list` of `lsst.daf.butler.DatasetRef`
517 Dataset references for ingested raws.
518 """
519 # TODO: This currently assumes that either duplicate inserts of
520 # visit records are ignored, or there is exactly one visit per
521 # exposure. I expect us to switch up the visit-exposure
522 # relationship and hence rewrite some of this code before that
523 # becomes a practical problem.
524 # Iterate over dimensions explicitly to order for foreign key
525 # relationships.
526 for dimension in ("visit", "exposure", "visit_detector_region"):
527 recordsForDimension = records.get(dimension)
528 if recordsForDimension:
529 # TODO: once Registry has options to ignore or replace
530 # existing dimension records with the same primary keys
531 # instead of aborting on conflicts, add configuration
532 # options and logic to use them.
533 self.butler.registry.insertDimensionData(dimension, *recordsForDimension)
535 def ingestExposureDatasets(self, exposure: RawExposureData, butler: Optional[Butler] = None
536 ) -> List[DatasetRef]:
537 """Ingest all raw files in one exposure.
539 Parameters
540 ----------
541 exposure : `RawExposureData`
542 A structure containing information about the exposure to be
543 ingested. Must have `RawExposureData.records` populated and all
544 data ID attributes expanded.
545 butler : `lsst.daf.butler.Butler`, optional
546 Butler to use for ingest. If not provided, ``self.butler`` will
547 be used.
549 Returns
550 -------
551 refs : `list` of `lsst.daf.butler.DatasetRef`
552 Dataset references for ingested raws.
553 """
554 if butler is None:
555 butler = self.butler
556 datasets = [FileDataset(path=os.path.abspath(file.filename),
557 refs=[DatasetRef(self.datasetType, d.dataId) for d in file.datasets],
558 formatter=file.FormatterClass)
559 for file in exposure.files]
560 butler.ingest(*datasets, transfer=self.config.transfer)
561 return [ref for dataset in datasets for ref in dataset.refs]
563 def run(self, files, pool: Optional[Pool] = None, processes: int = 1):
564 """Ingest files into a Butler data repository.
566 This creates any new exposure or visit Dimension entries needed to
567 identify the ingested files, creates new Dataset entries in the
568 Registry and finally ingests the files themselves into the Datastore.
569 Any needed instrument, detector, and physical_filter Dimension entries
570 must exist in the Registry before `run` is called.
572 Parameters
573 ----------
574 files : iterable over `str` or path-like objects
575 Paths to the files to be ingested. Will be made absolute
576 if they are not already.
577 pool : `multiprocessing.Pool`, optional
578 If not `None`, a process pool with which to parallelize some
579 operations.
580 processes : `int`, optional
581 The number of processes to use. Ignored if ``pool`` is not `None`.
583 Returns
584 -------
585 refs : `list` of `lsst.daf.butler.DatasetRef`
586 Dataset references for ingested raws.
588 Notes
589 -----
590 This method inserts all records (dimensions and datasets) for an
591 exposure within a transaction, guaranteeing that partial exposures
592 are never ingested.
593 """
594 exposureData = self.prep(files, pool=pool, processes=processes)
595 # Up to this point, we haven't modified the data repository at all.
596 # Now we finally do that, with one transaction per exposure. This is
597 # not parallelized at present because the performance of this step is
598 # limited by the database server. That may or may not change in the
599 # future once we increase our usage of bulk inserts and reduce our
600 # usage of savepoints; we've tried to get everything but the database
601 # operations done in advance to reduce the time spent inside
602 # transactions.
603 self.butler.registry.registerDatasetType(self.datasetType)
604 refs = []
605 for exposure in exposureData:
606 with self.butler.transaction():
607 self.insertDimensionData(exposure.records)
608 refs.extend(self.ingestExposureDatasets(exposure))
609 return refs