Coverage for python / lsst / daf / butler / script / removeRuns.py: 38%

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 

29from collections import defaultdict 

30from collections.abc import Callable, Mapping, Sequence 

31from dataclasses import dataclass 

32from functools import partial 

33 

34from .._butler import Butler 

35from .._collection_type import CollectionType 

36from ..registry import MissingCollectionError 

37 

38 

39@dataclass 

40class RemoveRun: 

41 """Represents a RUN collection to remove.""" 

42 

43 # the name of the run: 

44 name: str 

45 # parent CHAINED collections the RUN belongs to: 

46 parents: list[str] 

47 

48 

49@dataclass 

50class RemoveRunsResult: 

51 """Container to return to the cli command. 

52 

53 Contains the names of runs that will be deleted, and a map of dataset type 

54 to how many of that dataset will be deleted. Also contains the callback 

55 function to execute the remove upon user confirmation. 

56 """ 

57 

58 # the callback function to do the removal 

59 onConfirmation: Callable[[], None] 

60 # list of the run collections that will be removed 

61 runs: Sequence[RemoveRun] 

62 # mapping of dataset type name to how many will be removed. 

63 datasets: Mapping[str, int] 

64 

65 

66def _getCollectionInfo( 

67 repo: str, 

68 collection: str, 

69) -> tuple[list[RemoveRun], Mapping[str, int]]: 

70 """Get the names and types of collections that match the collection 

71 string. 

72 

73 Parameters 

74 ---------- 

75 repo : `str` 

76 The URI to the repository. 

77 collection : `str` 

78 The collection string to search for. Same as the `expression` 

79 argument to `registry.queryCollections`. 

80 

81 Returns 

82 ------- 

83 runs : `list` of `RemoveRun` 

84 Describes the runs that will be removed. 

85 datasets : `dict` [`str`, `int`] 

86 The dataset types and and how many will be removed. 

87 """ 

88 with Butler.from_config(repo) as butler, butler.registry.caching_context(): 

89 try: 

90 collections = butler.collections.query_info( 

91 collection, 

92 CollectionType.RUN, 

93 include_chains=False, 

94 include_parents=True, 

95 include_summary=True, 

96 ) 

97 except MissingCollectionError: 

98 # Act as if no collections matched. 

99 collections = [] 

100 dataset_types = [dt.name for dt in butler.registry.queryDatasetTypes(...)] 

101 dataset_types = list(butler.collections._filter_dataset_types(dataset_types, collections)) 

102 

103 runs = [] 

104 datasets: dict[str, int] = defaultdict(int) 

105 for collection_info in collections: 

106 assert collection_info.type == CollectionType.RUN and collection_info.parents is not None 

107 runs.append(RemoveRun(collection_info.name, list(collection_info.parents))) 

108 with butler.query() as query: 

109 for dt in dataset_types: 

110 results = query.datasets(dt, collections=collection_info.name) 

111 count = results.count(exact=False) 

112 if count: 

113 datasets[dt] += count 

114 

115 return runs, {k: datasets[k] for k in sorted(datasets.keys())} 

116 

117 

118def removeRuns( 

119 repo: str, 

120 collection: str, 

121) -> RemoveRunsResult: 

122 """Remove collections. 

123 

124 Parameters 

125 ---------- 

126 repo : `str` 

127 Same as the ``config`` argument to ``Butler.__init__``. 

128 collection : `str` 

129 Same as the ``name`` argument to ``Butler.removeRuns``. 

130 

131 Returns 

132 ------- 

133 collections : `RemoveRunsResult` 

134 Contains information describing what will be removed. 

135 """ 

136 runs, datasets = _getCollectionInfo(repo, collection) 

137 

138 def _doRemove(runs: Sequence[RemoveRun]) -> None: 

139 """Perform the remove step.""" 

140 with Butler.from_config(repo, writeable=True) as butler: 

141 butler.removeRuns([r.name for r in runs], unlink_from_chains=True) 

142 

143 result = RemoveRunsResult( 

144 onConfirmation=partial(_doRemove, runs), 

145 runs=runs, 

146 datasets=datasets, 

147 ) 

148 return result