Coverage for python/lsst/obs/base/gen2to3/rootRepoConverter.py : 16%

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/>.
21from __future__ import annotations
23__all__ = ["RootRepoConverter"]
25import os
26import re
27import itertools
28from typing import TYPE_CHECKING, Iterator, Optional, Tuple, List
30from lsst.skymap import BaseSkyMap
31from lsst.daf.butler import DatasetType, DatasetRef, FileDataset
32from .standardRepoConverter import StandardRepoConverter
34SKYMAP_DATASET_TYPES = {
35 coaddName: f"{coaddName}Coadd_skyMap" for coaddName in ("deep", "goodSeeing", "dcr")
36}
38if TYPE_CHECKING: 38 ↛ 39line 38 didn't jump to line 39, because the condition on line 38 was never true
39 from lsst.daf.butler import SkyPixDimension
40 from ..ingest import RawExposureData
43def getDataPaths(dataRefs):
44 """Strip HDU identifiers from paths and return a unique set of paths.
46 Parameters
47 ----------
48 dataRefs : `lsst.daf.persistence.ButlerDataRef`
49 The gen2 datarefs to strip "[HDU]" values from.
51 Returns
52 -------
53 paths : `set` [`str`]
54 The unique file paths without appended "[HDU]".
55 """
56 paths = set()
57 for dataRef in dataRefs:
58 path = dataRef.getUri()
59 # handle with FITS files with multiple HDUs (e.g. decam raw)
60 paths.add(path.split('[')[0])
61 return paths
64class RootRepoConverter(StandardRepoConverter):
65 """A specialization of `RepoConverter` for root data repositories.
67 `RootRepoConverter` adds support for raw images (mostly delegated to the
68 parent task's `RawIngestTask` subtask) and reference catalogs.
70 Parameters
71 ----------
72 kwds
73 Keyword arguments are forwarded to (and required by) `RepoConverter`.
74 """
76 def __init__(self, **kwds):
77 super().__init__(**kwds)
78 self._exposureData: List[RawExposureData] = []
79 self._refCats: List[Tuple[str, SkyPixDimension]] = []
80 if self.task.config.rootSkyMapName is not None:
81 self._rootSkyMap = self.task.config.skyMaps[self.task.config.rootSkyMapName].skyMap.apply()
82 else:
83 self._rootSkyMap = None
85 def isDatasetTypeSpecial(self, datasetTypeName: str) -> bool:
86 # Docstring inherited from RepoConverter.
87 return (
88 super().isDatasetTypeSpecial(datasetTypeName)
89 or datasetTypeName in ("raw", "ref_cat", "ref_cat_config")
90 # in Gen2, some of these are in the root repo, not a calib repo
91 or datasetTypeName in self.task.config.curatedCalibrations
92 )
94 def getSpecialDirectories(self) -> List[str]:
95 # Docstring inherited from RepoConverter.
96 return super().getSpecialDirectories() + ["CALIB", "ref_cats", "rerun"]
98 def findMatchingSkyMap(self, datasetTypeName: str) -> Tuple[Optional[BaseSkyMap], Optional[str]]:
99 # Docstring inherited from StandardRepoConverter.findMatchingSkyMap.
100 skyMap, name = super().findMatchingSkyMap(datasetTypeName)
101 if skyMap is None and self.task.config.rootSkyMapName is not None:
102 self.task.log.debug(
103 ("Assuming configured root skymap with name '%s' for dataset %s."),
104 self.task.config.rootSkyMapName, datasetTypeName
105 )
106 skyMap = self._rootSkyMap
107 name = self.task.config.rootSkyMapName
108 return skyMap, name
110 def prep(self):
111 # Docstring inherited from RepoConverter.
112 # Gather information about raws.
113 if self.task.raws is not None:
114 self.task.log.info(f"Preparing raws from root {self.root}.")
115 if self.subset is not None:
116 dataRefs = itertools.chain.from_iterable(
117 self.butler2.subset(self.task.config.rawDatasetType,
118 visit=visit) for visit in self.subset.visits
119 )
120 else:
121 dataRefs = self.butler2.subset(self.task.config.rawDatasetType)
122 dataPaths = getDataPaths(dataRefs)
123 self.task.log.debug("Prepping files: %s", dataPaths)
124 self._exposureData.extend(self.task.raws.prep(dataPaths))
125 # Gather information about reference catalogs.
126 if self.task.isDatasetTypeIncluded("ref_cat") and len(self.task.config.refCats) != 0:
127 from lsst.meas.algorithms import DatasetConfig as RefCatDatasetConfig
128 for refCat in os.listdir(os.path.join(self.root, "ref_cats")):
129 path = os.path.join(self.root, "ref_cats", refCat)
130 configFile = os.path.join(path, "config.py")
131 if not os.path.exists(configFile):
132 continue
133 if refCat not in self.task.config.refCats:
134 continue
135 self.task.log.info(f"Preparing ref_cat {refCat} from root {self.root}.")
136 onDiskConfig = RefCatDatasetConfig()
137 onDiskConfig.load(configFile)
138 if onDiskConfig.indexer.name != "HTM":
139 raise ValueError(f"Reference catalog '{refCat}' uses unsupported "
140 f"pixelization '{onDiskConfig.indexer.name}'.")
141 level = onDiskConfig.indexer["HTM"].depth
142 try:
143 dimension = self.task.universe[f"htm{level}"]
144 except KeyError as err:
145 raise ValueError(f"Reference catalog {refCat} uses HTM level {level}, but no htm{level} "
146 f"skypix dimension is configured for this registry.") from err
147 self.task.useSkyPix(dimension)
148 self._refCats.append((refCat, dimension))
149 if self.task.isDatasetTypeIncluded("brightObjectMask") and self.task.config.rootSkyMapName:
150 self.task.useSkyMap(self._rootSkyMap, self.task.config.rootSkyMapName)
151 super().prep()
153 def insertDimensionData(self):
154 # Docstring inherited from RepoConverter.
155 self.task.log.info(f"Inserting observation dimension records from {self.root}.")
156 records = {"visit": [], "exposure": [], "visit_detector_region": []}
157 for exposure in self._exposureData:
158 for dimension, recordsForDimension in exposure.records.items():
159 records[dimension].extend(recordsForDimension)
160 self.task.raws.insertDimensionData(records)
162 def iterDatasets(self) -> Iterator[FileDataset]:
163 # Docstring inherited from RepoConverter.
164 # Iterate over reference catalog files.
165 for refCat, dimension in self._refCats:
166 datasetType = DatasetType(refCat, dimensions=[dimension], universe=self.task.universe,
167 storageClass="SimpleCatalog")
168 if self.subset is None:
169 regex = re.compile(r"(\d+)\.fits")
170 for fileName in os.listdir(os.path.join(self.root, "ref_cats", refCat)):
171 m = regex.match(fileName)
172 if m is not None:
173 htmId = int(m.group(1))
174 dataId = self.task.registry.expandDataId({dimension: htmId})
175 yield FileDataset(path=os.path.join(self.root, "ref_cats", refCat, fileName),
176 refs=DatasetRef(datasetType, dataId))
177 else:
178 for begin, end in self.subset.skypix[dimension]:
179 for htmId in range(begin, end):
180 dataId = self.task.registry.expandDataId({dimension: htmId})
181 yield FileDataset(path=os.path.join(self.root, "ref_cats", refCat, f"{htmId}.fits"),
182 refs=DatasetRef(datasetType, dataId))
183 yield from super().iterDatasets()
185 def ingest(self):
186 # Docstring inherited from RepoConverter.
187 if self.task.raws is not None:
188 self.task.log.info(f"Ingesting raws from root {self.root}.")
189 self.task.registry.registerDatasetType(self.task.raws.datasetType)
190 # We need te delegate to RawIngestTask to actually ingest raws,
191 # rather than just including those datasets in iterDatasets for
192 # the base class to handle, because we don't want to assume we
193 # can use the Datastore-configured Formatter for raw data.
194 refs = []
195 collections = self.getCollections("raw")
196 for exposure in self._exposureData:
197 refs.extend(self.task.raws.ingestExposureDatasets(exposure))
198 for collection in collections[1:]:
199 self.task.registry.associate(collection, refs)
200 super().ingest()
202 def getCollections(self, datasetTypeName: str) -> List[str]:
203 # override to put reference catalogs in the right collection
204 if datasetTypeName in self.task.config.refCats:
205 return ['refcats']
206 else:
207 return super().getCollections(datasetTypeName)