Coverage for python/lsst/daf/butler/datastores/genericDatastore.py : 86%

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 daf_butler.
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/>.
22"""Generic datastore code useful for most datastores."""
24__all__ = ("GenericBaseDatastore", )
26import logging
27from abc import abstractmethod
29from lsst.daf.butler import Datastore, DatasetTypeNotSupportedError
30from lsst.daf.butler.registry.interfaces import DatastoreRegistryBridge
32log = logging.getLogger(__name__)
35class GenericBaseDatastore(Datastore):
36 """Methods useful for most implementations of a `Datastore`.
38 Should always be sub-classed since key abstract methods are missing.
39 """
41 @property
42 @abstractmethod
43 def bridge(self) -> DatastoreRegistryBridge:
44 """Object that manages the interface between this `Datastore` and the
45 `Registry` (`DatastoreRegistryBridge`).
46 """
47 raise NotImplementedError()
49 @abstractmethod
50 def addStoredItemInfo(self, refs, infos):
51 """Record internal storage information associated with one or more
52 datasets.
54 Parameters
55 ----------
56 refs : sequence of `DatasetRef`
57 The datasets that have been stored.
58 infos : sequence of `StoredDatastoreItemInfo`
59 Metadata associated with the stored datasets.
60 """
61 raise NotImplementedError()
63 @abstractmethod
64 def getStoredItemInfo(self, ref):
65 """Retrieve information associated with file stored in this
66 `Datastore`.
68 Parameters
69 ----------
70 ref : `DatasetRef`
71 The dataset that is to be queried.
73 Returns
74 -------
75 info : `StoredDatastoreItemInfo`
76 Stored information about this file and its formatter.
78 Raises
79 ------
80 KeyError
81 Dataset with that id can not be found.
82 """
83 raise NotImplementedError()
85 @abstractmethod
86 def getStoredItemsInfo(self, ref):
87 """Retrieve information associated with files stored in this
88 `Datastore` associated with this dataset ref.
90 Parameters
91 ----------
92 ref : `DatasetRef`
93 The dataset that is to be queried.
95 Returns
96 -------
97 items : `list` [`StoredDatastoreItemInfo`]
98 Stored information about the files and associated formatters
99 associated with this dataset. Only one file will be returned
100 if the dataset has not been disassembled. Can return an empty
101 list if no matching datasets can be found.
102 """
103 raise NotImplementedError()
105 @abstractmethod
106 def removeStoredItemInfo(self, ref):
107 """Remove information about the file associated with this dataset.
109 Parameters
110 ----------
111 ref : `DatasetRef`
112 The dataset that has been removed.
113 """
114 raise NotImplementedError()
116 def _register_datasets(self, refsAndInfos):
117 """Update registry to indicate that one or more datasets have been
118 stored.
120 Parameters
121 ----------
122 refsAndInfos : sequence `tuple` [`DatasetRef`,
123 `StoredDatastoreItemInfo`]
124 Datasets to register and the internal datastore metadata associated
125 with them.
126 """
127 expandedRefs = []
128 expandedItemInfos = []
130 for ref, itemInfo in refsAndInfos:
131 # Need the main dataset and the components
132 expandedRefs.extend(ref.flatten([ref]))
134 # Need one for the main ref and then one for each registered
135 # component
136 expandedItemInfos.extend([itemInfo] * (len(ref.components) + 1))
138 # Dataset location only cares about registry ID so if we have
139 # disassembled in datastore we have to deduplicate. Since they
140 # will have different datasetTypes we can't use a set
141 registryRefs = {r.id: r for r in expandedRefs}
142 self.bridge.insert(registryRefs.values())
143 self.addStoredItemInfo(expandedRefs, expandedItemInfos)
145 def _move_to_trash_in_registry(self, ref):
146 """Tell registry that this dataset and associated components
147 are to be trashed.
149 Parameters
150 ----------
151 ref : `DatasetRef`
152 Dataset to mark for removal from registry.
154 Notes
155 -----
156 Dataset is not removed from internal stored item info table.
157 """
158 # Note that a ref can point to component dataset refs that
159 # have been deleted already from registry but are still in
160 # the python object. moveToTrash will deal with that.
161 self.bridge.moveToTrash(ref.flatten([ref]))
163 def _post_process_get(self, inMemoryDataset, readStorageClass, assemblerParams=None,
164 isComponent=False):
165 """Given the Python object read from the datastore, manipulate
166 it based on the supplied parameters and ensure the Python
167 type is correct.
169 Parameters
170 ----------
171 inMemoryDataset : `object`
172 Dataset to check.
173 readStorageClass: `StorageClass`
174 The `StorageClass` used to obtain the assembler and to
175 check the python type.
176 assemblerParams : `dict`, optional
177 Parameters to pass to the assembler. Can be `None`.
178 isComponent : `bool`, optional
179 If this is a component, allow the inMemoryDataset to be `None`.
180 """
181 # Process any left over parameters
182 if assemblerParams:
183 inMemoryDataset = readStorageClass.assembler().handleParameters(inMemoryDataset, assemblerParams)
185 # Validate the returned data type matches the expected data type
186 pytype = readStorageClass.pytype
188 allowedTypes = []
189 if pytype: 189 ↛ 193line 189 didn't jump to line 193, because the condition on line 189 was never false
190 allowedTypes.append(pytype)
192 # Special case components to allow them to be None
193 if isComponent:
194 allowedTypes.append(type(None))
196 if allowedTypes and not isinstance(inMemoryDataset, tuple(allowedTypes)): 196 ↛ 197line 196 didn't jump to line 197, because the condition on line 196 was never true
197 raise TypeError("Got Python type {} from datastore but expected {}".format(type(inMemoryDataset),
198 pytype))
200 return inMemoryDataset
202 def _validate_put_parameters(self, inMemoryDataset, ref):
203 """Validate the supplied arguments for put.
205 Parameters
206 ----------
207 inMemoryDataset : `object`
208 The dataset to store.
209 ref : `DatasetRef`
210 Reference to the associated Dataset.
211 """
212 storageClass = ref.datasetType.storageClass
214 # Sanity check
215 if not isinstance(inMemoryDataset, storageClass.pytype): 215 ↛ 216line 215 didn't jump to line 216, because the condition on line 215 was never true
216 raise TypeError("Inconsistency between supplied object ({}) "
217 "and storage class type ({})".format(type(inMemoryDataset),
218 storageClass.pytype))
220 # Confirm that we can accept this dataset
221 if not self.constraints.isAcceptable(ref):
222 # Raise rather than use boolean return value.
223 raise DatasetTypeNotSupportedError(f"Dataset {ref} has been rejected by this datastore via"
224 " configuration.")
226 return
228 def remove(self, ref):
229 """Indicate to the Datastore that a dataset can be removed.
231 .. warning::
233 This method deletes the artifact associated with this
234 dataset and can not be reversed.
236 Parameters
237 ----------
238 ref : `DatasetRef`
239 Reference to the required Dataset.
241 Raises
242 ------
243 FileNotFoundError
244 Attempt to remove a dataset that does not exist.
246 Notes
247 -----
248 This method is used for immediate removal of a dataset and is
249 generally reserved for internal testing of datastore APIs.
250 It is implemented by calling `trash()` and then immediately calling
251 `emptyTrash()`. This call is meant to be immediate so errors
252 encountered during removal are not ignored.
253 """
254 self.trash(ref, ignore_errors=False)
255 self.emptyTrash(ignore_errors=False)
257 def transfer(self, inputDatastore, ref):
258 """Retrieve a dataset from an input `Datastore`,
259 and store the result in this `Datastore`.
261 Parameters
262 ----------
263 inputDatastore : `Datastore`
264 The external `Datastore` from which to retreive the Dataset.
265 ref : `DatasetRef`
266 Reference to the required dataset in the input data store.
268 """
269 assert inputDatastore is not self # unless we want it for renames?
270 inMemoryDataset = inputDatastore.get(ref)
271 return self.put(inMemoryDataset, ref)