Coverage for python / lsst / daf / butler / transfers / _context.py: 12%
112 statements
« prev ^ index » next coverage.py v7.13.2, created at 2026-02-04 02:35 -0800
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 software is dual licensed under the GNU General Public License and also
10# under a 3-clause BSD license. Recipients may choose which of these licenses
11# to use; please see the files gpl-3.0.txt and/or bsd_license.txt,
12# respectively. If you choose the GPL option then the following text applies
13# (but note that there is still no warranty even if you opt for BSD instead):
14#
15# This program is free software: you can redistribute it and/or modify
16# it under the terms of the GNU General Public License as published by
17# the Free Software Foundation, either version 3 of the License, or
18# (at your option) any later version.
19#
20# This program is distributed in the hope that it will be useful,
21# but WITHOUT ANY WARRANTY; without even the implied warranty of
22# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23# GNU General Public License for more details.
24#
25# You should have received a copy of the GNU General Public License
26# along with this program. If not, see <http://www.gnu.org/licenses/>.
28from __future__ import annotations
30__all__ = ["RepoExportContext"]
32from collections import defaultdict
33from collections.abc import Callable, Iterable, Set
34from typing import TYPE_CHECKING
36from .._collection_type import CollectionType
37from .._dataset_association import DatasetAssociation
38from .._dataset_ref import DatasetId, DatasetRef
39from .._dataset_type import DatasetType
40from .._file_dataset import FileDataset
41from ..dimensions import DataCoordinate, DimensionElement, DimensionRecord
42from ..registry.interfaces import ChainedCollectionRecord, CollectionRecord
44if TYPE_CHECKING:
45 from lsst.resources import ResourcePathExpression
47 from ..direct_butler import DirectButler
48 from ._interfaces import RepoExportBackend
51class RepoExportContext:
52 """Public interface for exporting a subset of a data repository.
54 Instances of this class are obtained by calling `Butler.export` as the
55 value returned by that context manager::
57 with butler.export(filename="export.yaml") as export:
58 export.saveDataIds(...)
59 export.saveDatasets(...)
61 Parameters
62 ----------
63 butler : `lsst.daf.butler.direct_butler.DirectButler`
64 Butler to export from.
65 backend : `RepoExportBackend`
66 Implementation class for a particular export file format.
67 directory : `~lsst.resources.ResourcePathExpression`, optional
68 Directory to pass to `Datastore.export`. Can be `None` to use
69 the current working directory.
70 transfer : `str`, optional
71 Transfer mode to pass to `Datastore.export`.
72 """
74 def __init__(
75 self,
76 butler: DirectButler, # Requires butler._registry to work for now.
77 backend: RepoExportBackend,
78 *,
79 directory: ResourcePathExpression | None = None,
80 transfer: str | None = None,
81 ):
82 self._butler = butler
83 self._backend = backend
84 self._directory = directory
85 self._transfer = transfer
86 self._records: dict[DimensionElement, dict[DataCoordinate, DimensionRecord]] = defaultdict(dict)
87 self._dataset_ids: set[DatasetId] = set()
88 self._datasets: dict[DatasetType, dict[str, list[FileDataset]]] = defaultdict(
89 lambda: defaultdict(list)
90 )
91 self._collections: dict[str, CollectionRecord] = {}
93 def saveCollection(self, name: str) -> None:
94 """Export the given collection.
96 Parameters
97 ----------
98 name : `str`
99 Name of the collection.
101 Notes
102 -----
103 `~CollectionType.RUN` collections are also exported automatically when
104 any dataset referencing them is exported. They may also be explicitly
105 exported this method to export the collection with no datasets.
106 Duplicate exports of collections are ignored.
108 Exporting a `~CollectionType.TAGGED` or `~CollectionType.CALIBRATION`
109 collection will cause its associations with exported datasets to also
110 be exported, but it does not export those datasets automatically.
112 Exporting a `~CollectionType.CHAINED` collection does not automatically
113 export its child collections; these must be explicitly exported or
114 already be present in the repository they are being imported into.
115 """
116 self._collections[name] = self._butler._registry.get_collection_record(name)
118 def saveDimensionData(
119 self, element: str | DimensionElement, records: Iterable[dict | DimensionRecord]
120 ) -> None:
121 """Export the given dimension records associated with one or more data
122 IDs.
124 Parameters
125 ----------
126 element : `str` or `DimensionElement`
127 `DimensionElement` or `str` indicating the logical table these
128 records are from.
129 records : `~collections.abc.Iterable` [ `DimensionRecord` or `dict` ]
130 Records to export, as an iterable containing `DimensionRecord` or
131 `dict` instances.
132 """
133 if not isinstance(element, DimensionElement):
134 element = self._butler.dimensions[element]
135 for record in records:
136 if not isinstance(record, DimensionRecord):
137 record = element.RecordClass(**record)
138 elif record.definition != element:
139 raise ValueError(
140 f"Mismatch between element={element.name} and "
141 f"dimension record with definition={record.definition.name}."
142 )
143 self._records[element].setdefault(record.dataId, record)
145 def saveDataIds(
146 self,
147 dataIds: Iterable[DataCoordinate],
148 *,
149 elements: Iterable[str | DimensionElement] | None = None,
150 ) -> None:
151 """Export the dimension records associated with one or more data IDs.
153 Parameters
154 ----------
155 dataIds : iterable of `DataCoordinate`
156 Data IDs to export. For large numbers of data IDs obtained by
157 calls to `Registry.queryDataIds`, it will be much more efficient if
158 these are expanded to include records (i.e.
159 `DataCoordinate.hasRecords` returns `True`) prior to the call to
160 `saveDataIds` via e.g. ``Registry.queryDataIds(...).expanded()``.
161 elements : iterable of `DimensionElement` or `str`, optional
162 Dimension elements whose records should be exported. If `None`,
163 records for all dimensions will be exported.
164 """
165 standardized_elements: Set[DimensionElement]
166 if elements is None:
167 standardized_elements = frozenset(
168 element for element in self._butler.dimensions.elements if element.has_own_table
169 )
170 else:
171 standardized_elements = set()
172 for element in elements:
173 if not isinstance(element, DimensionElement):
174 element = self._butler.dimensions[element]
175 if element.has_own_table:
176 standardized_elements.add(element)
178 dimension_records = self._butler._extract_all_dimension_records_from_data_ids(
179 self._butler, set(dataIds), frozenset(standardized_elements)
180 )
181 for element, record_mapping in dimension_records.items():
182 if element in standardized_elements:
183 for record in record_mapping.values():
184 self._records[element].setdefault(record.dataId, record)
186 def saveDatasets(
187 self,
188 refs: Iterable[DatasetRef],
189 *,
190 elements: Iterable[str | DimensionElement] | None = None,
191 rewrite: Callable[[FileDataset], FileDataset] | None = None,
192 ) -> None:
193 """Export one or more datasets.
195 This automatically exports any `DatasetType`, `~CollectionType.RUN`
196 collections, and dimension records associated with the datasets.
198 Parameters
199 ----------
200 refs : iterable of `DatasetRef`
201 References to the datasets to export. Their `DatasetRef.id`
202 attributes must not be `None`. Duplicates are automatically
203 ignored. Nested data IDs must have `DataCoordinate.hasRecords`
204 return `True`. If any reference is to a component dataset, the
205 parent will be exported instead.
206 elements : iterable of `DimensionElement` or `str`, optional
207 Dimension elements whose records should be exported; this is
208 forwarded to `saveDataIds` when exporting the data IDs of the
209 given datasets.
210 rewrite : callable, optional
211 A callable that takes a single `FileDataset` argument and returns
212 a modified `FileDataset`. This is typically used to rewrite the
213 path generated by the datastore. If `None`, the `FileDataset`
214 returned by `Datastore.export` will be used directly.
216 Notes
217 -----
218 At present, this only associates datasets with `~CollectionType.RUN`
219 collections. Other collections will be included in the export in the
220 future (once `Registry` provides a way to look up that information).
221 """
222 data_ids = set()
223 refs_to_export = {}
224 for ref in sorted(refs):
225 dataset_id = ref.id
226 # The query interfaces that are often used to generate the refs
227 # passed here often don't remove duplicates, so do that here for
228 # convenience.
229 if dataset_id in self._dataset_ids or dataset_id in refs_to_export:
230 continue
231 # Also convert components to composites.
232 if ref.isComponent():
233 ref = ref.makeCompositeRef()
234 data_ids.add(ref.dataId)
235 refs_to_export[dataset_id] = ref
236 # Do a vectorized datastore export, which might be a lot faster than
237 # one-by-one.
238 exports = self._butler._datastore.export(
239 refs_to_export.values(),
240 directory=self._directory,
241 transfer=self._transfer,
242 )
243 # Export associated data IDs.
244 self.saveDataIds(data_ids, elements=elements)
245 # Rewrite export filenames if desired, and then save them to the
246 # data structure we'll write in `_finish`.
247 # If a single exported FileDataset has multiple DatasetRefs, we save
248 # it with each of them.
249 for file_dataset in exports:
250 if rewrite is not None:
251 file_dataset = rewrite(file_dataset)
252 for ref in file_dataset.refs:
253 assert ref.run is not None
254 self._datasets[ref.datasetType][ref.run].append(file_dataset)
255 self._dataset_ids.update(refs_to_export.keys())
257 def _finish(self) -> None:
258 """Delegate to the backend to finish the export process.
260 For use by `Butler.export` only.
261 """
262 for element in self._butler.dimensions.sorted(self._records.keys()):
263 # To make export deterministic sort the DataCoordinate instances.
264 r = self._records[element]
265 self._backend.saveDimensionData(element, *[r[dataId] for dataId in sorted(r.keys())])
266 for datasetsByRun in self._datasets.values():
267 for run in datasetsByRun:
268 self._collections[run] = self._butler._registry.get_collection_record(run)
269 for collectionName in self._computeSortedCollections():
270 doc = self._butler.registry.getCollectionDocumentation(collectionName)
271 self._backend.saveCollection(self._collections[collectionName], doc)
272 # Sort the dataset types and runs before exporting to ensure
273 # reproducible order in export file.
274 for datasetType in sorted(self._datasets.keys()):
275 for run in sorted(self._datasets[datasetType].keys()):
276 # Sort the FileDataset
277 records = sorted(self._datasets[datasetType][run])
278 self._backend.saveDatasets(datasetType, run, *records)
279 # Export associations between datasets and collections. These need to
280 # be sorted (at two levels; they're dicts) or created more
281 # deterministically, too, which probably involves more data ID sorting.
282 datasetAssociations = self._computeDatasetAssociations()
283 for collection in sorted(datasetAssociations):
284 self._backend.saveDatasetAssociations(
285 collection, self._collections[collection].type, sorted(datasetAssociations[collection])
286 )
287 self._backend.finish()
289 def _computeSortedCollections(self) -> list[str]:
290 """Sort collections in a way that is both deterministic and safe
291 for registering them in a new repo in the presence of nested chains.
293 This method is intended for internal use by `RepoExportContext` only.
295 Returns
296 -------
297 names: `List` [ `str` ]
298 Ordered list of collection names.
299 """
300 # Split collections into CHAINED and everything else, and just
301 # sort "everything else" lexicographically since there are no
302 # dependencies.
303 chains: dict[str, list[str]] = {}
304 result: list[str] = []
305 for record in self._collections.values():
306 if record.type is CollectionType.CHAINED:
307 assert isinstance(record, ChainedCollectionRecord)
308 chains[record.name] = list(record.children)
309 else:
310 result.append(record.name)
311 result.sort()
312 # Sort all chains topologically, breaking ties lexicographically.
313 # Append these to 'result' and remove them from 'chains' as we go.
314 while chains:
315 unblocked = {
316 parent
317 for parent, children in chains.items()
318 if not any(child in chains for child in children)
319 }
320 if not unblocked:
321 raise RuntimeError(
322 f"Apparent cycle in CHAINED collection dependencies involving {unblocked}."
323 )
324 result.extend(sorted(unblocked))
325 for name in unblocked:
326 del chains[name]
327 return result
329 def _computeDatasetAssociations(self) -> dict[str, list[DatasetAssociation]]:
330 """Return datasets-collection associations, grouped by association.
332 This queries for all associations between exported datasets and
333 exported TAGGED or CALIBRATION collections and is intended to be run
334 only by `_finish`, as this ensures all collections and all datasets
335 have already been exported and hence the order in which they are
336 exported does not matter.
338 Returns
339 -------
340 associations : `dict` [ `str`, `list` [ `DatasetAssociation` ] ]
341 Dictionary keyed by collection name, with values lists of structs
342 representing an association between that collection and a dataset.
343 """
344 results = defaultdict(list)
345 for datasetType in self._datasets:
346 # We query for _all_ datasets of each dataset type we export, in
347 # the specific collections we are exporting. The worst-case
348 # efficiency of this is _awful_ (i.e. big repo, exporting a tiny
349 # subset). But we don't have any better options right now; we need
350 # a way to query for a _lot_ of explicitly given dataset_ids, and
351 # the only way to make that scale up is to either upload them to a
352 # temporary table or recognize when they are already in one because
353 # the user passed us a QueryResult object. That's blocked by (at
354 # least) DM-26692.
355 collectionTypes = {CollectionType.TAGGED}
356 if datasetType.isCalibration():
357 collectionTypes.add(CollectionType.CALIBRATION)
358 for association in self._butler.registry.queryDatasetAssociations(
359 datasetType, self._collections.keys(), collectionTypes=collectionTypes, flattenChains=False
360 ):
361 if association.ref.id in self._dataset_ids:
362 results[association.collection].append(association)
363 return results