Coverage for python/lsst/pipe/base/quantum_graph/aggregator/_structs.py: 73%

1# This file is part of pipe_base. 

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/>. 

27 

28from __future__ import annotations 

29 

30__all__ = ( 

31 "IngestRequest", 

32 "ScanReport", 

33 "ScanResult", 

34 "ScanStatus", 

35) 

36 

37import dataclasses 

38import enum 

39import uuid 

40 

41from lsst.daf.butler.datastore.record_data import DatastoreRecordData 

42 

43from ..._status import QuantumSuccessCaveats 

44from ...quantum_provenance_graph import ExceptionInfo, QuantumRunStatus 

45from ...resource_usage import QuantumResourceUsage 

46from .._common import DatastoreName 

47from .._predicted import PredictedDatasetModel 

48 

49 

50class ScanStatus(enum.Enum): 

51 """Status enum for quantum scanning. 

52 

53 Note that this records the status for the *scanning* which is distinct 

54 from the status of the quantum's execution. 

55 """ 

56 

57 INCOMPLETE = enum.auto() 

58 """The quantum is not necessarily done running, and cannot be scanned 

59 conclusively yet. 

60 """ 

61 

62 ABANDONED = enum.auto() 

63 """The quantum's execution appears to have failed but we cannot rule out 

64 the possibility that it could be recovered, but we've also waited long 

65 enough (according to `ScannerTimeConfigDict.retry_timeout`) that it's time 

66 to stop trying for now. 

67 

68 This state means a later run with `ScannerConfig.assume_complete` is 

69 required. 

70 """ 

71 

72 SUCCESSFUL = enum.auto() 

73 """The quantum was conclusively scanned and was executed successfully, 

74 unblocking scans for downstream quanta. 

75 """ 

76 

77 FAILED = enum.auto() 

78 """The quantum was conclusively scanned and failed execution, blocking 

79 scans for downstream quanta. 

80 """ 

81 

82 BLOCKED = enum.auto() 

83 """A quantum upstream of this one failed.""" 

84 

85 INIT = enum.auto() 

86 """Init quanta need special handling, because they don't have logs and 

87 metadata. 

88 """ 

89 

90 

91@dataclasses.dataclass 

92class ScanReport: 

93 """Minimal information needed about a completed scan by the supervisor.""" 

94 

95 quantum_id: uuid.UUID 

96 """Unique ID of the quantum.""" 

97 

98 status: ScanStatus 

99 """Combined status of the scan and the execution of the quantum.""" 

100 

101 

102@dataclasses.dataclass 

103class IngestRequest: 

104 """A request to ingest datasets produced by a single quantum.""" 

105 

106 producer_id: uuid.UUID 

107 """ID of the quantum that produced these datasets.""" 

108 

109 datasets: list[PredictedDatasetModel] 

110 """Registry information about the datasets.""" 

111 

112 records: dict[DatastoreName, DatastoreRecordData] 

113 """Datastore information about the datasets.""" 

114 

115 def __bool__(self) -> bool: 

116 return bool(self.datasets or self.records) 

117 

118 

119@dataclasses.dataclass 

120class ScanResult: 

121 """A struct that represents the result of scanning a quantum.""" 

122 

123 quantum_id: uuid.UUID 

124 """Unique ID for the quantum.""" 

125 

126 status: ScanStatus 

127 """Combined status for the scan and the execution of the quantum.""" 

128 

129 caveats: QuantumSuccessCaveats | None = None 

130 """Flags indicating caveats on successful quanta.""" 

131 

132 exception: ExceptionInfo | None = None 

133 """Information about an exception raised when the quantum was executing.""" 

134 

135 resource_usage: QuantumResourceUsage | None = None 

136 """Resource usage information (timing, memory use) for this quantum.""" 

137 

138 existing_outputs: set[uuid.UUID] = dataclasses.field(default_factory=set) 

139 """Unique IDs of the output datasets that were actually written.""" 

140 

141 metadata: bytes = b"" 

142 """Raw content of the metadata dataset.""" 

143 

144 log: bytes = b"" 

145 """Raw content of the log dataset.""" 

146 

147 is_compressed: bool = False 

148 """Whether the `metadata` and `log` attributes are compressed.""" 

149 

150 def get_run_status(self) -> QuantumRunStatus: 

151 """Translate the scan status and metadata/log presence into a run 

152 status. 

153 """ 

154 if self.status is ScanStatus.BLOCKED: 

155 return QuantumRunStatus.BLOCKED 

156 if self.status is ScanStatus.INIT: 

157 return QuantumRunStatus.SUCCESSFUL 

158 if self.log: 

159 if self.metadata: 

160 return QuantumRunStatus.SUCCESSFUL 

161 else: 

162 return QuantumRunStatus.FAILED 

163 else: 

164 if self.metadata: 

165 return QuantumRunStatus.LOGS_MISSING 

166 else: 

167 return QuantumRunStatus.METADATA_MISSING