Coverage for python/lsst/pipe/base/quantum_graph/aggregator/_structs.py: 98%

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 .._common import DatastoreName 

44from .._predicted import PredictedDatasetModel 

45from .._provenance import ( 

46 ProvenanceLogRecordsModel, 

47 ProvenanceQuantumAttemptModel, 

48 ProvenanceTaskMetadataModel, 

49) 

50 

51 

52class ScanStatus(enum.Enum): 

53 """Status enum for quantum scanning. 

54 

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

56 from the status of the quantum's execution. 

57 """ 

58 

59 INCOMPLETE = enum.auto() 

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

61 conclusively yet. 

62 """ 

63 

64 ABANDONED = enum.auto() 

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

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

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

68 to stop trying for now. 

69 

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

71 required. 

72 """ 

73 

74 SUCCESSFUL = enum.auto() 

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

76 unblocking scans for downstream quanta. 

77 """ 

78 

79 FAILED = enum.auto() 

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

81 scans for downstream quanta. 

82 """ 

83 

84 BLOCKED = enum.auto() 

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

86 

87 INIT = enum.auto() 

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

89 metadata. 

90 """ 

91 

92 

93@dataclasses.dataclass 

94class ScanReport: 

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

96 

97 quantum_id: uuid.UUID 

98 """Unique ID of the quantum.""" 

99 

100 status: ScanStatus 

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

102 

103 

104@dataclasses.dataclass 

105class IngestRequest: 

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

107 

108 producer_id: uuid.UUID 

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

110 

111 datasets: list[PredictedDatasetModel] 

112 """Registry information about the datasets.""" 

113 

114 records: dict[DatastoreName, DatastoreRecordData] 

115 """Datastore information about the datasets.""" 

116 

117 def __bool__(self) -> bool: 

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

119 

120 

121@dataclasses.dataclass 

122class ScanResult: 

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

124 

125 quantum_id: uuid.UUID 

126 """Unique ID for the quantum.""" 

127 

128 status: ScanStatus 

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

130 

131 attempts: list[ProvenanceQuantumAttemptModel] = dataclasses.field(default_factory=list) 

132 """Provenance information about each attempt to run the quantum.""" 

133 

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

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

136 

137 metadata_model: ProvenanceTaskMetadataModel | None = dataclasses.field( 

138 default_factory=ProvenanceTaskMetadataModel 

139 ) 

140 """Task metadata information for each attempt. 

141 

142 This is set to `None` to keep the pickle size small after it is saved 

143 to `metadata_content`. 

144 """ 

145 

146 metadata_content: bytes = b"" 

147 """Serialized form of `metadata_model`.""" 

148 

149 log_model: ProvenanceLogRecordsModel | None = dataclasses.field(default_factory=ProvenanceLogRecordsModel) 

150 """Log records for each attempt. 

151 

152 This is set to `None` to keep the pickle size small after it is saved 

153 to `log_content`. 

154 """ 

155 

156 log_content: bytes = b"" 

157 """Serialized form of `logs_model`.""" 

158 

159 is_compressed: bool = False 

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