Coverage for python/lsst/ctrl/mpexec/cli/script/run.py: 38%

11 statements  

« prev     ^ index     » next       coverage.py v7.2.7, created at 2023-06-09 02:48 -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 

22import logging 

23from types import SimpleNamespace 

24 

25from ... import CmdLineFwk, TaskFactory 

26 

27_log = logging.getLogger(__name__) 

28 

29 

30def run( # type: ignore 

31 pdb, 

32 graph_fixup, 

33 init_only, 

34 no_versions, 

35 processes, 

36 start_method, 

37 profile, 

38 qgraphObj, 

39 register_dataset_types, 

40 skip_init_writes, 

41 timeout, 

42 butler_config, 

43 input, 

44 output, 

45 output_run, 

46 extend_run, 

47 replace_run, 

48 prune_replaced, 

49 data_query, 

50 skip_existing_in, 

51 skip_existing, 

52 debug, 

53 fail_fast, 

54 clobber_outputs, 

55 summary, 

56 mock, 

57 unmocked_dataset_types, 

58 enable_implicit_threading, 

59 **kwargs, 

60): 

61 """Implements the command line interface `pipetask run` subcommand, should 

62 only be called by command line tools and unit test code that test this 

63 function. 

64 

65 Parameters 

66 ---------- 

67 pdb : `bool` 

68 Drop into pdb on exception? 

69 graph_fixup : `str` 

70 The name of the class or factory method which makes an instance used 

71 for execution graph fixup. 

72 init_only : `bool` 

73 If true, do not actually run; just register dataset types and/or save 

74 init outputs. 

75 no_versions : `bool` 

76 If true, do not save or check package versions. 

77 processes : `int` 

78 The number of processes to use. 

79 start_method : `str` or `None` 

80 Start method from `multiprocessing` module, `None` selects the best 

81 one for current platform. 

82 profile : `str` 

83 File name to dump cProfile information to. 

84 qgraphObj : `lsst.pipe.base.QuantumGraph` 

85 A QuantumGraph generated by a previous subcommand. 

86 register_dataset_types : `bool` 

87 If true, register DatasetTypes that do not already exist in the 

88 Registry. 

89 skip_init_writes : `bool` 

90 If true, do not write collection-wide 'init output' datasets (e.g. 

91 schemas). 

92 timeout : `int` 

93 Timeout for multiprocessing; maximum wall time (sec). 

94 butler_config : `str`, `dict`, or `lsst.daf.butler.Config` 

95 If `str`, `butler_config` is the path location of the gen3 

96 butler/registry config file. If `dict`, `butler_config` is key value 

97 pairs used to init or update the `lsst.daf.butler.Config` instance. If 

98 `Config`, it is the object used to configure a Butler. 

99 input : `list` [ `str` ] 

100 List of names of the input collection(s). 

101 output : `str` 

102 Name of the output CHAINED collection. This may either be an existing 

103 CHAINED collection to use as both input and output (if `input` is 

104 `None`), or a new CHAINED collection created to include all inputs 

105 (if `input` is not `None`). In both cases, the collection's children 

106 will start with an output RUN collection that directly holds all new 

107 datasets (see `output_run`). 

108 output_run : `str` 

109 Name of the new output RUN collection. If not provided then `output` 

110 must be provided and a new RUN collection will be created by appending 

111 a timestamp to the value passed with `output`. If this collection 

112 already exists then `extend_run` must be passed. 

113 extend_run : `bool` 

114 Instead of creating a new RUN collection, insert datasets into either 

115 the one given by `output_run` (if provided) or the first child 

116 collection of `output` (which must be of type RUN). 

117 replace_run : `bool` 

118 Before creating a new RUN collection in an existing CHAINED collection, 

119 remove the first child collection (which must be of type RUN). This can 

120 be used to repeatedly write to the same (parent) collection during 

121 development, but it does not delete the datasets associated with the 

122 replaced run unless `prune-replaced` is also True. Requires `output`, 

123 and `extend_run` must be `None`. 

124 prune_replaced : "unstore", "purge", or `None`. 

125 If not `None`, delete the datasets in the collection replaced by 

126 `replace_run`, either just from the datastore ("unstore") or by 

127 removing them and the RUN completely ("purge"). Requires `replace_run`. 

128 data_query : `str` 

129 User query selection expression. 

130 skip_existing_in : `list` [ `str` ] 

131 Accepts list of collections, if all Quantum outputs already exist in 

132 the specified list of collections then that Quantum will be excluded 

133 from the QuantumGraph. 

134 skip_existing : `bool` 

135 Appends output RUN collection to the ``skip_existing_in`` list. 

136 debug : `bool` 

137 If true, enable debugging output using lsstDebug facility (imports 

138 debug.py). 

139 fail_fast : `bool` 

140 If true then stop processing at first error, otherwise process as many 

141 tasks as possible. 

142 clobber_outputs : `bool` 

143 Remove outputs from previous execution of the same quantum before new 

144 execution. Only applies to failed quanta if skip_existing is also 

145 given. 

146 summary : `str` 

147 File path to store job report in JSON format. 

148 mock : `bool`, optional 

149 If `True` then run mock pipeline instead of real one. Ignored if an 

150 existing QuantumGraph is provided. 

151 unmocked_dataset_types : `collections.abc.Sequence` [ `str` ] 

152 List of overall-input dataset types that should not be mocked. 

153 Ignored if an existing QuantumGraph is provided. 

154 enable_implicit_threading : `bool`, optional 

155 If `True`, do not disable implicit threading by third-party libraries. 

156 Implicit threading is always disabled during actual quantum execution 

157 if ``processes > 1``. 

158 kwargs : `dict` [`str`, `str`] 

159 Ignored; click commands may accept options for more than one script 

160 function and pass all the option kwargs to each of the script functions 

161 which ignore these unused kwargs. 

162 """ 

163 args = SimpleNamespace( 

164 pdb=pdb, 

165 graph_fixup=graph_fixup, 

166 init_only=init_only, 

167 no_versions=no_versions, 

168 processes=processes, 

169 start_method=start_method, 

170 profile=profile, 

171 skip_init_writes=skip_init_writes, 

172 timeout=timeout, 

173 register_dataset_types=register_dataset_types, 

174 butler_config=butler_config, 

175 input=input, 

176 output=output, 

177 output_run=output_run, 

178 extend_run=extend_run, 

179 replace_run=replace_run, 

180 prune_replaced=prune_replaced, 

181 data_query=data_query, 

182 skip_existing_in=skip_existing_in, 

183 skip_existing=skip_existing, 

184 enableLsstDebug=debug, 

185 fail_fast=fail_fast, 

186 clobber_outputs=clobber_outputs, 

187 summary=summary, 

188 mock=mock, 

189 unmocked_dataset_types=unmocked_dataset_types, 

190 enable_implicit_threading=enable_implicit_threading, 

191 ) 

192 

193 f = CmdLineFwk() 

194 taskFactory = TaskFactory() 

195 

196 # If we have no output run specified, use the one from the graph rather 

197 # than letting a new timestamped run be created. 

198 if not args.output_run and qgraphObj.metadata and (output_run := qgraphObj.metadata.get("output_run")): 

199 args.output_run = output_run 

200 

201 f.runPipeline(qgraphObj, taskFactory, args)