Coverage for python/lsst/pipe/base/executionButlerBuilder.py: 16%
Shortcuts 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
Shortcuts 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 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/>.
21from __future__ import annotations
23__all__ = ("buildExecutionButler",)
25import io
26import itertools
27from collections import defaultdict
28from typing import Callable, DefaultDict, Iterable, List, Mapping, Optional, Set, Tuple, Union
30from lsst.daf.butler import Butler, Config, DataCoordinate, DatasetRef, DatasetType
31from lsst.daf.butler.core.repoRelocation import BUTLER_ROOT_TAG
32from lsst.daf.butler.transfers import RepoExportContext
33from lsst.resources import ResourcePath, ResourcePathExpression
34from lsst.utils.introspection import get_class_of
36from .graph import QuantumGraph, QuantumNode
37from .pipeline import PipelineDatasetTypes
39DataSetTypeMap = Mapping[DatasetType, Set[DataCoordinate]]
42def _accumulate(
43 graph: QuantumGraph,
44 dataset_types: PipelineDatasetTypes,
45) -> Tuple[Set[DatasetRef], DataSetTypeMap]:
46 # accumulate the DatasetRefs that will be transferred to the execution
47 # registry
49 # exports holds all the existing data that will be migrated to the
50 # execution butler
51 exports: Set[DatasetRef] = set()
53 # inserts is the mapping of DatasetType to dataIds for what is to be
54 # inserted into the registry. These are the products that are expected
55 # to be produced during processing of the QuantumGraph
56 inserts: DefaultDict[DatasetType, Set[DataCoordinate]] = defaultdict(set)
58 # Add inserts for initOutputs (including initIntermediates); these are
59 # defined fully by their DatasetType, because they have no dimensions, and
60 # they are by definition not resolved. initInputs are part of Quantum and
61 # that's the only place the graph stores the dataset IDs, so we process
62 # them there even though each Quantum for a task has the same ones.
63 for dataset_type in itertools.chain(dataset_types.initIntermediates, dataset_types.initOutputs):
64 inserts[dataset_type].add(DataCoordinate.makeEmpty(dataset_type.dimensions.universe))
66 n: QuantumNode
67 for quantum in (n.quantum for n in graph):
68 for attrName in ("initInputs", "inputs", "outputs"):
69 attr: Mapping[DatasetType, Union[DatasetRef, List[DatasetRef]]] = getattr(quantum, attrName)
71 for type, refs in attr.items():
72 # This if block is because init inputs has a different
73 # signature for its items
74 if not isinstance(refs, list):
75 refs = [refs]
76 # iterate over all the references, if it has an id, it
77 # means it exists and should be exported, if not it should
78 # be inserted into the new registry
79 for ref in refs:
80 if ref.id is not None:
81 exports.add(ref)
82 else:
83 if ref.isComponent():
84 # We can't insert a component, and a component will
85 # be part of some other upstream dataset, so it
86 # should be safe to skip them here
87 continue
88 inserts[type].add(ref.dataId)
89 return exports, inserts
92def _discoverCollections(butler: Butler, collections: Iterable[str]) -> set[str]:
93 # Recurse through any discovered collections to make sure all collections
94 # are exported. This exists because I ran into a situation where some
95 # collections were not properly being discovered and exported. This
96 # method may be able to be removed in the future if collection export
97 # logic changes
98 collections = set(collections)
99 while True:
100 discoveredCollections = set(
101 butler.registry.queryCollections(collections, flattenChains=True, includeChains=True)
102 )
103 if len(discoveredCollections) > len(collections):
104 collections = discoveredCollections
105 else:
106 break
107 return collections
110def _export(
111 butler: Butler, collections: Optional[Iterable[str]], exports: Set[DatasetRef], inserts: DataSetTypeMap
112) -> io.StringIO:
113 # This exports the datasets that exist in the input butler using
114 # daf butler objects, however it reaches in deep and does not use the
115 # public methods so that it can export it to a string buffer and skip
116 # disk access.
117 yamlBuffer = io.StringIO()
118 # Yaml is hard coded, since the class controls both ends of the
119 # export/import
120 BackendClass = get_class_of(butler._config["repo_transfer_formats", "yaml", "export"])
121 backend = BackendClass(yamlBuffer)
122 exporter = RepoExportContext(butler.registry, butler.datastore, backend, directory=None, transfer=None)
123 exporter.saveDatasets(exports)
125 # Need to ensure that the dimension records for outputs are
126 # transferred.
127 for _, dataIds in inserts.items():
128 exporter.saveDataIds(dataIds)
130 # Look for any defined collection, if not get the defaults
131 if collections is None:
132 collections = butler.registry.defaults.collections
134 # look up all collections associated with those inputs, this follows
135 # all chains to make sure everything is properly exported
136 for c in _discoverCollections(butler, collections):
137 exporter.saveCollection(c)
138 exporter._finish()
140 # reset the string buffer to the beginning so the read operation will
141 # actually *see* the data that was exported
142 yamlBuffer.seek(0)
143 return yamlBuffer
146def _setupNewButler(butler: Butler, outputLocation: ResourcePath, dirExists: bool) -> Butler:
147 # Set up the new butler object at the specified location
148 if dirExists:
149 # Remove the existing table, if the code got this far and this exists
150 # clobber must be true
151 executionRegistry = outputLocation.join("gen3.sqlite3")
152 if executionRegistry.exists():
153 executionRegistry.remove()
154 else:
155 outputLocation.mkdir()
157 # Copy the existing butler config, modifying the location of the
158 # registry to the specified location.
159 # Preserve the root path from the existing butler so things like
160 # file data stores continue to look at the old location.
161 config = Config(butler._config)
162 config["root"] = outputLocation.geturl()
163 config["allow_put_of_predefined_dataset"] = True
164 config["registry", "db"] = "sqlite:///<butlerRoot>/gen3.sqlite3"
166 # Remove any namespace that may be set in main registry.
167 config.pop(("registry", "namespace"), None)
169 # record the current root of the datastore if it is specified relative
170 # to the butler root
171 if config.get(("datastore", "root")) == BUTLER_ROOT_TAG:
172 config["datastore", "root"] = butler._config.configDir.geturl()
173 config["datastore", "trust_get_request"] = True
175 # Requires that we use the dimension configuration from the original
176 # butler and not use the defaults.
177 config = Butler.makeRepo(
178 root=outputLocation,
179 config=config,
180 dimensionConfig=butler.registry.dimensions.dimensionConfig,
181 overwrite=True,
182 forceConfigRoot=False,
183 )
185 # Return a newly created butler
186 return Butler(config, writeable=True)
189def _import(
190 yamlBuffer: io.StringIO,
191 newButler: Butler,
192 inserts: DataSetTypeMap,
193 run: str,
194 butlerModifier: Optional[Callable[[Butler], Butler]],
195) -> Butler:
196 # This method takes the exports from the existing butler, imports
197 # them into the newly created butler, and then inserts the datasets
198 # that are expected to be produced.
200 # import the existing datasets using "split" mode. "split" is safe
201 # because execution butler is assumed to be able to see all the file
202 # locations that the main datastore can see. "split" supports some
203 # absolute URIs in the datastore.
204 newButler.import_(filename=yamlBuffer, format="yaml", reuseIds=True, transfer="split")
206 # If there is modifier callable, run it to make necessary updates
207 # to the new butler.
208 if butlerModifier is not None:
209 newButler = butlerModifier(newButler)
211 # Register datasets to be produced and insert them into the registry
212 for dsType, dataIds in inserts.items():
213 newButler.registry.registerDatasetType(dsType)
214 newButler.registry.insertDatasets(dsType, dataIds, run)
216 return newButler
219def buildExecutionButler(
220 butler: Butler,
221 graph: QuantumGraph,
222 outputLocation: ResourcePathExpression,
223 run: str,
224 *,
225 clobber: bool = False,
226 butlerModifier: Optional[Callable[[Butler], Butler]] = None,
227 collections: Optional[Iterable[str]] = None,
228) -> Butler:
229 r"""buildExecutionButler is a function that is responsible for exporting
230 input `QuantumGraphs` into a new minimal `~lsst.daf.butler.Butler` which
231 only contains datasets specified by the `QuantumGraph`. These datasets are
232 both those that already exist in the input `~lsst.daf.butler.Butler`, and
233 those that are expected to be produced during the execution of the
234 `QuantumGraph`.
236 Parameters
237 ----------
238 butler : `lsst.daf.butler.Bulter`
239 This is the existing `~lsst.daf.butler.Butler` instance from which
240 existing datasets will be exported. This should be the
241 `~lsst.daf.butler.Butler` which was used to create any `QuantumGraphs`
242 that will be converted with this object.
243 graph : `QuantumGraph`
244 Graph containing nodes that are to be exported into an execution
245 butler
246 outputLocation : convertible to `ResourcePath
247 URI Location at which the execution butler is to be exported. May be
248 specified as a string or a `ResourcePath` instance.
249 run : `str` optional
250 The run collection that the exported datasets are to be placed in. If
251 None, the default value in registry.defaults will be used.
252 clobber : `bool`, Optional
253 By default a butler will not be created if a file or directory
254 already exists at the output location. If this is set to `True`
255 what is at the location will be deleted prior to running the
256 export. Defaults to `False`
257 butlerModifier : `~typing.Callable`, Optional
258 If supplied this should be a callable that accepts a
259 `~lsst.daf.butler.Butler`, and returns an instantiated
260 `~lsst.daf.butler.Butler`. This callable may be used to make any
261 modifications to the `~lsst.daf.butler.Butler` desired. This
262 will be called after importing all datasets that exist in the input
263 `~lsst.daf.butler.Butler` but prior to inserting Datasets expected
264 to be produced. Examples of what this method could do include
265 things such as creating collections/runs/ etc.
266 collections : `~typing.Iterable` of `str`, Optional
267 An iterable of collection names that will be exported from the input
268 `~lsst.daf.butler.Butler` when creating the execution butler. If not
269 supplied the `~lsst.daf.butler.Butler`\ 's `~lsst.daf.butler.Registry`
270 default collections will be used.
272 Returns
273 -------
274 executionButler : `lsst.daf.butler.Butler`
275 An instance of the newly created execution butler
277 Raises
278 ------
279 FileExistsError
280 Raised if something exists in the filesystem at the specified output
281 location and clobber is `False`
282 NotADirectoryError
283 Raised if specified output URI does not correspond to a directory
284 """
285 # We know this must refer to a directory.
286 outputLocation = ResourcePath(outputLocation, forceDirectory=True)
288 # Do this first to Fail Fast if the output exists
289 if (dirExists := outputLocation.exists()) and not clobber:
290 raise FileExistsError("Cannot create a butler at specified location, location exists")
291 if not outputLocation.isdir():
292 raise NotADirectoryError("The specified output URI does not appear to correspond to a directory")
294 # Gather all DatasetTypes from the Python and check any that already exist
295 # in the registry for consistency. This does not check that all dataset
296 # types here exist, because they might want to register dataset types
297 # later. It would be nice to also check that, but to that we would need to
298 # be told whether they plan to register dataset types later (DM-30845).
299 dataset_types = PipelineDatasetTypes.fromPipeline(graph.iterTaskGraph(), registry=butler.registry)
301 exports, inserts = _accumulate(graph, dataset_types)
302 yamlBuffer = _export(butler, collections, exports, inserts)
304 newButler = _setupNewButler(butler, outputLocation, dirExists)
306 return _import(yamlBuffer, newButler, inserts, run, butlerModifier)