lsst.pipe.tasks g4a6547c0d5+6fab381471
getRepositoryData.py
Go to the documentation of this file.
2# LSST Data Management System
3# Copyright 2008, 2009, 2010, 2011, 2012 LSST Corporation.
4#
5# This product includes software developed by the
6# LSST Project (http://www.lsst.org/).
7#
8# This program is free software: you can redistribute it and/or modify
9# it under the terms of the GNU General Public License as published by
10# the Free Software Foundation, either version 3 of the License, or
11# (at your option) any later version.
12#
13# This program is distributed in the hope that it will be useful,
14# but WITHOUT ANY WARRANTY; without even the implied warranty of
15# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16# GNU General Public License for more details.
17#
18# You should have received a copy of the LSST License Statement and
19# the GNU General Public License along with this program. If not,
20# see <http://www.lsstcorp.org/LegalNotices/>.
21#
22"""Retrieve collections of metadata or data based on a set of data references
23
24Use this as a base task for creating graphs and reports for a set of data.
25"""
26import lsst.pex.config as pexConfig
27import lsst.pipe.base as pipeBase
28
29__all__ = ["DataRefListRunner", "GetRepositoryDataTask"]
30
31
32class DataRefListRunner(pipeBase.TaskRunner):
33 """A task runner that calls run with a list of data references
34
35 Differs from the default TaskRunner by providing all data references at once,
36 instead of iterating over them one at a time.
37 """
38 @staticmethod
39 def getTargetList(parsedCmd):
40 """Return a list of targets (arguments for __call__); one entry per invocation
41 """
42 return [parsedCmd.id.refList] # one argument consisting of a list of dataRefs
43
44 def __call__(self, dataRefList):
45 """Run GetRepositoryDataTask.run on a single target
46
47 @param dataRefList: argument dict for run; contains one key: dataRefList
48
49 @return:
50 - None if doReturnResults false
51 - A pipe_base Struct containing these fields if doReturnResults true:
52 - dataRefList: the argument dict sent to runDataRef
53 - metadata: task metadata after execution of runDataRef
54 - result: result returned by task runDataRef
55 """
56 task = self.TaskClass(config=self.config, log=self.log)
57 result = task.runDataRef(dataRefList)
58
59 if self.doReturnResults:
60 return pipeBase.Struct(
61 dataRefList=dataRefList,
62 metadata=task.metadata,
63 result=result,
64 )
65
66
67class GetRepositoryDataTask(pipeBase.CmdLineTask):
68 """Retrieve data from a repository, e.g. for plotting or analysis purposes
69 """
70 ConfigClass = pexConfig.Config # nothing to configure
71 RunnerClass = DataRefListRunner
72 _DefaultName = "getTaskData"
73
74 def __init__(self, *args, **kwargs):
75 pipeBase.CmdLineTask.__init__(self, *args, **kwargs)
76
77 @pipeBase.timeMethod
78 def runDataRef(self, dataRefList):
79 """Get data from a repository for a collection of data references
80
81 @param dataRefList: a list of data references
82 """
83 raise NotImplementedError("subclass must specify a run method")
84
85 def getIdList(self, dataRefList):
86 """Get a list of data IDs in a form that can be used as dictionary keys
87
88 @param dataRefList: a list of data references
89 @return a pipe_base Struct with fields:
90 - idKeyTuple: a tuple of dataRef data ID keys
91 - idValList: a list of data ID value tuples, each tuple contains values in the order in idKeyTuple
92 """
93 if not dataRefList:
94 raise RuntimeError("No data refs")
95 idKeyTuple = tuple(sorted(dataRefList[0].dataId.keys()))
96
97 idValList = []
98 for dataRef in dataRefList:
99 idValTuple = tuple(dataRef.dataId[key] for key in idKeyTuple)
100 idValList.append(idValTuple)
101
102 return pipeBase.Struct(
103 idKeyTuple=idKeyTuple,
104 idValList=idValList,
105 )
106
107 def getDataList(self, dataRefList, datasetType):
108 """Retrieve a list of data
109
110 @param dataRefList: a list of data references
111 @param datasetType: datasetType of data to be retrieved
112 @return a list of data, one entry per dataRef in dataRefList (in order)
113 """
114 return [dataRef.get(datasetType=datasetType) for dataRef in dataRefList]
115
116 def getMetadataItems(self, dataRefList, datasetType, nameList):
117 """Retrieve a list of dictionaries of metadata
118
119 @param dataRefList: a list of data references
120 @param datasetType: datasetType of metadata (or any object that supports get(name))
121 @return a list of dicts of metadata:
122 - each entry in the list corresponds to a dataRef in dataRefList
123 - each dict contains name: item of metadata, for each name in nameList;
124 numeric and string values will be returned as arrays
125 """
126 valList = []
127 for dataRef in dataRefList:
128 metadata = dataRef.get(datasetType=datasetType)
129 valList.append(dict((name, metadata.getArray(name)) for name in nameList))
130 return valList
def getMetadataItems(self, dataRefList, datasetType, nameList)