Coverage for python / lsst / daf / butler / registry / bridge / ephemeral.py: 29%

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 ..interfaces import DatasetIdRef, DatastoreRegistryBridge, FakeDatasetRef, OpaqueTableStorage 

37 

38if TYPE_CHECKING: 

39 from ...datastore import DatastoreTransaction 

40 from ...datastore.stored_file_info import StoredDatastoreItemInfo 

41 

42 

43class EphemeralDatastoreRegistryBridge(DatastoreRegistryBridge): 

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

45 - those whose artifacts never outlive the current process. 

46 

47 Parameters 

48 ---------- 

49 datastoreName : `str` 

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

51 referencing it. 

52 

53 Notes 

54 ----- 

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

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

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

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

59 """ 

60 

61 def __init__(self, datastoreName: str): 

62 super().__init__(datastoreName) 

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

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

65 

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

67 # Docstring inherited from DatastoreRegistryBridge 

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

69 

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

71 # Docstring inherited from DatastoreRegistryBridge 

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

73 

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

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

76 

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

78 """Rollback a moveToTrash call.""" 

79 for ref in refs: 

80 self._trashedIds.remove(ref.id) 

81 

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

83 # Docstring inherited from DatastoreRegistryBridge 

84 if transaction is None: 

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

86 ref_list = list(refs) 

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

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

89 

90 def check(self, refs: Iterable[DatasetIdRef]) -> Iterable[DatasetIdRef]: 

91 # Docstring inherited from DatastoreRegistryBridge 

92 yield from (ref for ref in refs if ref in self) 

93 

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

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

96 

97 @contextmanager 

98 def emptyTrash( 

99 self, 

100 records_table: OpaqueTableStorage | None = None, 

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

102 record_column: str | None = None, 

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

104 dry_run: bool = False, 

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

106 # Docstring inherited from DatastoreRegistryBridge 

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

108 trashed_ids = self._trashedIds 

109 

110 if selected_ids is not None: 

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

112 

113 if isinstance(records_table, OpaqueTableStorage): 

114 if record_class is None: 

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

116 matches = ( 

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

118 for id in trashed_ids 

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

120 ) 

121 else: 

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

123 

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

125 # should be retained. 

126 yield ((matches, None)) 

127 

128 if dry_run: 

129 return 

130 

131 if isinstance(records_table, OpaqueTableStorage): 

132 # Remove the records entries 

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

134 

135 # Empty the trash table 

136 self._datasetIds.difference_update(trashed_ids) 

137 self._trashedIds = self._trashedIds - trashed_ids