Coverage for python/lsst/daf/butler/registry/bridge/ephemeral.py: 81%

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/>. 

27from __future__ import annotations 

28 

29__all__ = ("EphemeralDatastoreRegistryBridge",) 

30 

31from collections.abc import Collection, Iterable, Iterator 

32from contextlib import contextmanager 

33from typing import TYPE_CHECKING 

34 

35from ..._dataset_ref import DatasetId 

36from .._exceptions import ConflictingDefinitionError 

37from ..interfaces import DatasetIdRef, DatastoreRegistryBridge, FakeDatasetRef, OpaqueTableStorage 

38 

39if TYPE_CHECKING: 

40 from ...datastore import DatastoreTransaction 

41 from ...datastore.stored_file_info import StoredDatastoreItemInfo 

42 

43 

44class EphemeralDatastoreRegistryBridge(DatastoreRegistryBridge): 

45 """An implementation of `DatastoreRegistryBridge` for ephemeral datastores 

46 - those whose artifacts never outlive the current process. 

47 

48 Parameters 

49 ---------- 

50 datastoreName : `str` 

51 Name of the `Datastore` as it should appear in `Registry` tables 

52 referencing it. 

53 

54 Notes 

55 ----- 

56 The current implementation just uses a Python set to remember the dataset 

57 IDs associated with the datastore. This will probably need to be converted 

58 to use in-database temporary tables instead in the future to support 

59 "in-datastore" constraints in `Registry.queryDatasets`. 

60 """ 

61 

62 def __init__(self, datastoreName: str): 

63 super().__init__(datastoreName) 

64 self._datasetIds: set[DatasetId] = set() 

65 self._trashedIds: set[DatasetId] = set() 

66 

67 def insert(self, refs: Iterable[DatasetIdRef]) -> None: 

68 # Docstring inherited from DatastoreRegistryBridge 

69 new_ids = {ref.id for ref in refs} 

70 if known_ids := new_ids & self._datasetIds: 70 ↛ 71line 70 didn't jump to line 71 because the condition on line 70 was never true

71 raise ConflictingDefinitionError(f"Some datasets are already in registry: {known_ids}") 

72 self._datasetIds.update(new_ids) 

73 

74 def ensure(self, refs: Iterable[DatasetIdRef]) -> None: 

75 # Docstring inherited from DatastoreRegistryBridge 

76 self._datasetIds.update(ref.id for ref in refs) 

77 

78 def forget(self, refs: Iterable[DatasetIdRef]) -> None: 

79 self._datasetIds.difference_update(ref.id for ref in refs) 

80 

81 def _rollbackMoveToTrash(self, refs: Iterable[DatasetIdRef]) -> None: 

82 """Rollback a moveToTrash call.""" 

83 for ref in refs: 

84 self._trashedIds.remove(ref.id) 

85 

86 def moveToTrash(self, refs: Iterable[DatasetIdRef], transaction: DatastoreTransaction | None) -> None: 

87 # Docstring inherited from DatastoreRegistryBridge 

88 if transaction is None: 88 ↛ 89line 88 didn't jump to line 89 because the condition on line 88 was never true

89 raise RuntimeError("Must be called with a defined transaction.") 

90 ref_list = list(refs) 

91 with transaction.undoWith(f"Trash {len(ref_list)} datasets", self._rollbackMoveToTrash, ref_list): 

92 self._trashedIds.update(ref.id for ref in ref_list) 

93 

94 def check(self, datasets: Iterable[DatasetId]) -> set[DatasetId]: 

95 # Docstring inherited from DatastoreRegistryBridge 

96 return {id for id in datasets if FakeDatasetRef(id) in self} 

97 

98 def __contains__(self, ref: DatasetIdRef) -> bool: 

99 return ref.id in self._datasetIds and ref.id not in self._trashedIds 

100 

101 @contextmanager 

102 def emptyTrash( 

103 self, 

104 records_table: OpaqueTableStorage | None = None, 

105 record_class: type[StoredDatastoreItemInfo] | None = None, 

106 record_column: str | None = None, 

107 selected_ids: Collection[DatasetId] | None = None, 

108 dry_run: bool = False, 

109 ) -> Iterator[tuple[Iterable[tuple[DatasetIdRef, StoredDatastoreItemInfo | None]], set[str] | None]]: 

110 # Docstring inherited from DatastoreRegistryBridge 

111 matches: Iterable[tuple[FakeDatasetRef, StoredDatastoreItemInfo | None]] = () 

112 trashed_ids = self._trashedIds 

113 

114 if selected_ids is not None: 

115 trashed_ids = {tid for tid in trashed_ids if tid in selected_ids} 

116 

117 if isinstance(records_table, OpaqueTableStorage): 117 ↛ 126line 117 didn't jump to line 126 because the condition on line 117 was always true

118 if record_class is None: 118 ↛ 119line 118 didn't jump to line 119 because the condition on line 118 was never true

119 raise ValueError("Record class must be provided if records table is given.") 

120 matches = ( 

121 (FakeDatasetRef(id), record_class.from_record(record)) 

122 for id in trashed_ids 

123 for record in records_table.fetch(dataset_id=id) 

124 ) 

125 else: 

126 matches = ((FakeDatasetRef(id), None) for id in trashed_ids) 

127 

128 # Indicate to caller that we do not know about artifacts that 

129 # should be retained. 

130 yield ((matches, None)) 

131 

132 if dry_run: 

133 return 

134 

135 if isinstance(records_table, OpaqueTableStorage): 135 ↛ 140line 135 didn't jump to line 140 because the condition on line 135 was always true

136 # Remove the records entries 

137 records_table.delete(["dataset_id"], *[{"dataset_id": id} for id in trashed_ids]) 

138 

139 # Empty the trash table 

140 self._datasetIds.difference_update(trashed_ids) 

141 self._trashedIds = self._trashedIds - trashed_ids