Coverage for python/lsst/pipe/base/butlerQuantumContext.py: 14%

106 statements  

« prev     ^ index     » next       coverage.py v7.2.5, created at 2023-05-05 03:30 -0700

1# This file is part of pipe_base. 

2# 

3# Developed for the LSST Data Management System. 

4# This product includes software developed by the LSST Project 

5# (http://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 

22from __future__ import annotations 

23 

24"""Module defining a butler like object specialized to a specific quantum. 

25""" 

26 

27__all__ = ("ButlerQuantumContext",) 

28 

29from typing import Any, List, Optional, Sequence, Union 

30 

31from lsst.daf.butler import Butler, DatasetRef, DimensionUniverse, LimitedButler, Quantum 

32from lsst.utils.introspection import get_full_type_name 

33from lsst.utils.logging import PeriodicLogger, getLogger 

34 

35from .connections import DeferredDatasetRef, InputQuantizedConnection, OutputQuantizedConnection 

36from .struct import Struct 

37 

38_LOG = getLogger(__name__) 

39 

40 

41class ButlerQuantumContext: 

42 """A Butler-like class specialized for a single quantum. 

43 

44 A ButlerQuantumContext class wraps a standard butler interface and 

45 specializes it to the context of a given quantum. What this means 

46 in practice is that the only gets and puts that this class allows 

47 are DatasetRefs that are contained in the quantum. 

48 

49 In the future this class will also be used to record provenance on 

50 what was actually get and put. This is in contrast to what the 

51 preflight expects to be get and put by looking at the graph before 

52 execution. 

53 

54 Do not use constructor directly, instead use `from_full` or `from_limited` 

55 factory methods. 

56 

57 Notes 

58 ----- 

59 `ButlerQuantumContext` instances are backed by either 

60 `lsst.daf.butler.Butler` or `lsst.daf.butler.LimitedButler`. When a 

61 limited butler is used then quantum has to contain dataset references 

62 that are completely resolved (usually when graph is constructed by 

63 GraphBuilder). 

64 

65 When instances are backed by full butler, the quantum graph does not have 

66 to resolve output or intermediate references, but input references of each 

67 quantum have to be resolved before they can be used by this class. When 

68 executing such graphs, intermediate references used as input to some 

69 Quantum are resolved by ``lsst.ctrl.mpexec.SingleQuantumExecutor``. If 

70 output references of a quanta are resolved, they will be unresolved when 

71 full butler is used. 

72 """ 

73 

74 def __init__(self, *, limited: LimitedButler, quantum: Quantum, butler: Butler | None = None): 

75 self.quantum = quantum 

76 self.allInputs = set() 

77 self.allOutputs = set() 

78 for refs in quantum.inputs.values(): 

79 for ref in refs: 

80 self.allInputs.add((ref.datasetType, ref.dataId)) 

81 for refs in quantum.outputs.values(): 

82 for ref in refs: 

83 self.allOutputs.add((ref.datasetType, ref.dataId)) 

84 self.__full_butler = butler 

85 self.__butler = limited 

86 

87 @classmethod 

88 def from_full(cls, butler: Butler, quantum: Quantum) -> ButlerQuantumContext: 

89 """Make ButlerQuantumContext backed by `lsst.daf.butler.Butler`. 

90 

91 Parameters 

92 ---------- 

93 butler : `lsst.daf.butler.Butler` 

94 Butler object from/to which datasets will be get/put. 

95 quantum : `lsst.daf.butler.core.Quantum` 

96 Quantum object that describes the datasets which will be get/put by 

97 a single execution of this node in the pipeline graph. All input 

98 dataset references must be resolved in this Quantum. Output 

99 references can be resolved, but they will be unresolved. 

100 

101 Returns 

102 ------- 

103 butlerQC : `ButlerQuantumContext` 

104 Instance of butler wrapper. 

105 """ 

106 return ButlerQuantumContext(limited=butler, butler=butler, quantum=quantum) 

107 

108 @classmethod 

109 def from_limited(cls, butler: LimitedButler, quantum: Quantum) -> ButlerQuantumContext: 

110 """Make ButlerQuantumContext backed by `lsst.daf.butler.LimitedButler`. 

111 

112 Parameters 

113 ---------- 

114 butler : `lsst.daf.butler.LimitedButler` 

115 Butler object from/to which datasets will be get/put. 

116 quantum : `lsst.daf.butler.core.Quantum` 

117 Quantum object that describes the datasets which will be get/put by 

118 a single execution of this node in the pipeline graph. Both input 

119 and output dataset references must be resolved in this Quantum. 

120 

121 Returns 

122 ------- 

123 butlerQC : `ButlerQuantumContext` 

124 Instance of butler wrapper. 

125 """ 

126 return ButlerQuantumContext(limited=butler, quantum=quantum) 

127 

128 def _get(self, ref: Optional[Union[DeferredDatasetRef, DatasetRef]]) -> Any: 

129 # Butler methods below will check for unresolved DatasetRefs and 

130 # raise appropriately, so no need for us to do that here. 

131 if isinstance(ref, DeferredDatasetRef): 

132 self._checkMembership(ref.datasetRef, self.allInputs) 

133 return self.__butler.getDeferred(ref.datasetRef) 

134 elif ref is None: 

135 return None 

136 else: 

137 self._checkMembership(ref, self.allInputs) 

138 return self.__butler.get(ref) 

139 

140 def _put(self, value: Any, ref: DatasetRef) -> None: 

141 """Store data in butler""" 

142 self._checkMembership(ref, self.allOutputs) 

143 if self.__full_butler is not None: 

144 self.__full_butler.put(value, ref) 

145 else: 

146 self.__butler.put(value, ref) 

147 

148 def get( 

149 self, 

150 dataset: Union[ 

151 InputQuantizedConnection, 

152 List[Optional[DatasetRef]], 

153 List[Optional[DeferredDatasetRef]], 

154 DatasetRef, 

155 DeferredDatasetRef, 

156 None, 

157 ], 

158 ) -> Any: 

159 """Fetches data from the butler 

160 

161 Parameters 

162 ---------- 

163 dataset 

164 This argument may either be an `InputQuantizedConnection` which 

165 describes all the inputs of a quantum, a list of 

166 `~lsst.daf.butler.DatasetRef`, or a single 

167 `~lsst.daf.butler.DatasetRef`. The function will get and return 

168 the corresponding datasets from the butler. If `None` is passed in 

169 place of a `~lsst.daf.butler.DatasetRef` then the corresponding 

170 returned object will be `None`. 

171 

172 Returns 

173 ------- 

174 return : `object` 

175 This function returns arbitrary objects fetched from the bulter. 

176 The structure these objects are returned in depends on the type of 

177 the input argument. If the input dataset argument is a 

178 `InputQuantizedConnection`, then the return type will be a 

179 dictionary with keys corresponding to the attributes of the 

180 `InputQuantizedConnection` (which in turn are the attribute 

181 identifiers of the connections). If the input argument is of type 

182 `list` of `~lsst.daf.butler.DatasetRef` then the return type will 

183 be a list of objects. If the input argument is a single 

184 `~lsst.daf.butler.DatasetRef` then a single object will be 

185 returned. 

186 

187 Raises 

188 ------ 

189 ValueError 

190 Raised if a `DatasetRef` is passed to get that is not defined in 

191 the quantum object 

192 """ 

193 # Set up a periodic logger so log messages can be issued if things 

194 # are taking too long. 

195 periodic = PeriodicLogger(_LOG) 

196 

197 if isinstance(dataset, InputQuantizedConnection): 

198 retVal = {} 

199 n_connections = len(dataset) 

200 n_retrieved = 0 

201 for i, (name, ref) in enumerate(dataset): 

202 if isinstance(ref, list): 

203 val = [] 

204 n_refs = len(ref) 

205 for j, r in enumerate(ref): 

206 val.append(self._get(r)) 

207 n_retrieved += 1 

208 periodic.log( 

209 "Retrieved %d out of %d datasets for connection '%s' (%d out of %d)", 

210 j + 1, 

211 n_refs, 

212 name, 

213 i + 1, 

214 n_connections, 

215 ) 

216 else: 

217 val = self._get(ref) 

218 periodic.log( 

219 "Retrieved dataset for connection '%s' (%d out of %d)", 

220 name, 

221 i + 1, 

222 n_connections, 

223 ) 

224 n_retrieved += 1 

225 retVal[name] = val 

226 if periodic.num_issued > 0: 

227 # This took long enough that we issued some periodic log 

228 # messages, so issue a final confirmation message as well. 

229 _LOG.verbose( 

230 "Completed retrieval of %d datasets from %d connections", n_retrieved, n_connections 

231 ) 

232 return retVal 

233 elif isinstance(dataset, list): 

234 n_datasets = len(dataset) 

235 retrieved = [] 

236 for i, x in enumerate(dataset): 

237 # Mypy is not sure of the type of x because of the union 

238 # of lists so complains. Ignoring it is more efficient 

239 # than adding an isinstance assert. 

240 retrieved.append(self._get(x)) 

241 periodic.log("Retrieved %d out of %d datasets", i + 1, n_datasets) 

242 if periodic.num_issued > 0: 

243 _LOG.verbose("Completed retrieval of %d datasets", n_datasets) 

244 return retrieved 

245 elif isinstance(dataset, DatasetRef) or isinstance(dataset, DeferredDatasetRef) or dataset is None: 

246 return self._get(dataset) 

247 else: 

248 raise TypeError( 

249 f"Dataset argument ({get_full_type_name(dataset)}) is not a type that can be used to get" 

250 ) 

251 

252 def put( 

253 self, 

254 values: Union[Struct, List[Any], Any], 

255 dataset: Union[OutputQuantizedConnection, List[DatasetRef], DatasetRef], 

256 ) -> None: 

257 """Puts data into the butler 

258 

259 Parameters 

260 ---------- 

261 values : `Struct` or `list` of `object` or `object` 

262 The data that should be put with the butler. If the type of the 

263 dataset is `OutputQuantizedConnection` then this argument should be 

264 a `Struct` with corresponding attribute names. Each attribute 

265 should then correspond to either a list of object or a single 

266 object depending of the type of the corresponding attribute on 

267 dataset. I.e. if ``dataset.calexp`` is 

268 ``[datasetRef1, datasetRef2]`` then ``values.calexp`` should be 

269 ``[calexp1, calexp2]``. Like wise if there is a single ref, then 

270 only a single object need be passed. The same restriction applies 

271 if dataset is directly a `list` of `DatasetRef` or a single 

272 `DatasetRef`. 

273 dataset 

274 This argument may either be an `InputQuantizedConnection` which 

275 describes all the inputs of a quantum, a list of 

276 `lsst.daf.butler.DatasetRef`, or a single 

277 `lsst.daf.butler.DatasetRef`. The function will get and return 

278 the corresponding datasets from the butler. 

279 

280 Raises 

281 ------ 

282 ValueError 

283 Raised if a `DatasetRef` is passed to put that is not defined in 

284 the quantum object, or the type of values does not match what is 

285 expected from the type of dataset. 

286 """ 

287 if isinstance(dataset, OutputQuantizedConnection): 

288 if not isinstance(values, Struct): 

289 raise ValueError( 

290 "dataset is a OutputQuantizedConnection, a Struct with corresponding" 

291 " attributes must be passed as the values to put" 

292 ) 

293 for name, refs in dataset: 

294 valuesAttribute = getattr(values, name) 

295 if isinstance(refs, list): 

296 if len(refs) != len(valuesAttribute): 

297 raise ValueError(f"There must be a object to put for every Dataset ref in {name}") 

298 for i, ref in enumerate(refs): 

299 self._put(valuesAttribute[i], ref) 

300 else: 

301 self._put(valuesAttribute, refs) 

302 elif isinstance(dataset, list): 

303 if not isinstance(values, Sequence): 

304 raise ValueError("Values to put must be a sequence") 

305 if len(dataset) != len(values): 

306 raise ValueError("There must be a common number of references and values to put") 

307 for i, ref in enumerate(dataset): 

308 self._put(values[i], ref) 

309 elif isinstance(dataset, DatasetRef): 

310 self._put(values, dataset) 

311 else: 

312 raise TypeError("Dataset argument is not a type that can be used to put") 

313 

314 def _checkMembership(self, ref: Union[List[DatasetRef], DatasetRef], inout: set) -> None: 

315 """Internal function used to check if a DatasetRef is part of the input 

316 quantum 

317 

318 This function will raise an exception if the ButlerQuantumContext is 

319 used to get/put a DatasetRef which is not defined in the quantum. 

320 

321 Parameters 

322 ---------- 

323 ref : `list` of `DatasetRef` or `DatasetRef` 

324 Either a list or a single `DatasetRef` to check 

325 inout : `set` 

326 The connection type to check, e.g. either an input or an output. 

327 This prevents both types needing to be checked for every operation, 

328 which may be important for Quanta with lots of `DatasetRef`. 

329 """ 

330 if not isinstance(ref, list): 

331 ref = [ref] 

332 for r in ref: 

333 if (r.datasetType, r.dataId) not in inout: 

334 raise ValueError("DatasetRef is not part of the Quantum being processed") 

335 

336 @property 

337 def dimensions(self) -> DimensionUniverse: 

338 """Structure managing all dimensions recognized by this data 

339 repository (`DimensionUniverse`). 

340 """ 

341 return self.__butler.dimensions