Coverage for python/lsst/ctrl/mpexec/cli/script/cleanup.py: 34%

64 statements  

« prev     ^ index     » next       coverage.py v6.4.4, created at 2022-08-18 11:55 -0700

1# This file is part of ctrl_mpexec. 

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/>. 

21 

22 

23import re 

24from typing import Any 

25 

26from lsst.daf.butler import Butler, CollectionType 

27from lsst.daf.butler.registry import CollectionTypeError, MissingCollectionError 

28 

29from .confirmable import ConfirmableResult 

30 

31 

32class NoSuchCollectionFailure: 

33 def __init__(self, collection: str): 

34 self.collection = collection 

35 

36 def __str__(self) -> str: 

37 return f'Did not find a collection named "{self.collection}"' 

38 

39 

40class NotChainedCollectionFailure: 

41 def __init__(self, collection: str, type: str): 

42 self.collection = collection 

43 self.type = type 

44 

45 def __str__(self) -> str: 

46 return f'COLLECTION must be a CHAINED collection, "{self.collection}" is a "{self.type}" collection.' 

47 

48 

49class CleanupResult(ConfirmableResult): 

50 def __init__(self, butler_config: str): 

51 self.butler_config = butler_config 

52 self.runs_to_remove: list[str] = [] 

53 self.others_to_remove: list[str] = [] 

54 self.failure: Any = None 

55 

56 def describe(self, will: bool) -> str: 

57 if self.can_continue: 

58 msg = "Will remove:" if will else "Removed:" 

59 msg += "\n" 

60 msg += f" runs: {', '.join(self.runs_to_remove)}\n" 

61 msg += f" others: {', '.join(self.others_to_remove)}" 

62 else: 

63 msg = "Did not find any collections to remove." 

64 return msg 

65 

66 def on_confirmation(self) -> None: 

67 butler = Butler(self.butler_config, writeable=True) 

68 with butler.transaction(): 

69 for collection in self.others_to_remove: 

70 butler.registry.removeCollection(collection) 

71 butler.removeRuns(self.runs_to_remove) 

72 

73 @property 

74 def failed(self) -> bool: 

75 return self.failure is not None 

76 

77 @property 

78 def describe_failure(self) -> str: 

79 return str(self.failure) 

80 

81 @property 

82 def can_continue(self) -> bool: 

83 return bool(self.runs_to_remove) or bool(self.others_to_remove) 

84 

85 

86def cleanup( 

87 butler_config: str, 

88 collection: str, 

89) -> CleanupResult: 

90 """Remove collections that start with the same name as a CHAINED 

91 collection but are not members of that collection. 

92 

93 Parameters 

94 ---------- 

95 butler_config : str 

96 The path location of the gen3 butler/registry config file. 

97 collection : str 

98 The name of the chained collection. 

99 """ 

100 butler = Butler(butler_config) 

101 result = CleanupResult(butler_config) 

102 try: 

103 to_keep = set(butler.registry.getCollectionChain(collection)) 

104 except MissingCollectionError: 

105 result.failure = NoSuchCollectionFailure(collection) 

106 return result 

107 except CollectionTypeError: 

108 result.failure = NotChainedCollectionFailure( 

109 collection, butler.registry.getCollectionType(collection).name 

110 ) 

111 return result 

112 regex = re.compile(collection + ".+") 

113 to_consider = set(butler.registry.queryCollections(regex)) 

114 to_remove = to_consider - to_keep 

115 for r in to_remove: 

116 if butler.registry.getCollectionType(r) == CollectionType.RUN: 

117 result.runs_to_remove.append(r) 

118 else: 

119 result.others_to_remove.append(r) 

120 return result