Python Job.inputdata方法代码示例

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
def create_gaudi_subjob(job, inputdata):
    j = Job()
    j.name = job.name
    j.application = copy_app(job.application)
    j.backend = job.backend # no need to deepcopy
    if inputdata:
        j.inputdata = inputdata
        if hasattr(j.application,'extra'):
            j.application.extra.inputdata = j.inputdata
    else:
        j.inputdata = None
        if hasattr(j.application,'extra'):
            j.application.extra.inputdata = BesDataset()
    j.outputsandbox = job.outputsandbox[:]
    j.outputdata = job.outputdata
    return j

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def __make_subjob__(self, mj, guids, names, sjob_evnts=-1, sites=None):
        
        """
        private method to create subjob object
        """
        
        logger.debug('generating subjob to run %d events in-total on files: %s' % (sjob_evnts, repr(guids)))
        j = Job()

        j.name            = mj.name
        j.inputdata       = mj.inputdata

        if j.inputdata.type in ['','DQ2']:
            j.inputdata.guids = guids

        j.inputdata.names = names

        j.outputdata    = mj.outputdata
        j.application   = mj.application
        if sjob_evnts != -1:
            j.application.max_events = sjob_evnts
        j.backend       = mj.backend
        
        if j.backend._name in ['LCG'] and j.backend.requirements._name == 'AtlasLCGRequirements':
            if sites:
                j.backend.requirements.sites = sites
        
        j.inputsandbox  = mj.inputsandbox
        j.outputsandbox = mj.outputsandbox

        return j

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def split(self,job):
        from Ganga.GPIDev.Lib.Job import Job
        logger.debug("AnaTaskSplitterJob split called")
        sjl = []
        transform = stripProxy(job.application.getTransform())
        transform.setAppStatus(job.application, "removed")
        # Do the splitting
        for sj in self.subjobs:
            j = Job()
            j.inputdata = transform.partitions_data[sj-1]
            j.outputdata = job.outputdata
            j.application = job.application
            j.application.atlas_environment.append("OUTPUT_FILE_NUMBER=%i" % sj)
            j.backend = job.backend
            if transform.partitions_sites:
                if hasattr(j.backend.requirements, 'sites'):                
                    j.backend.requirements.sites = transform.partitions_sites[sj-1]                    
                else:
                    j.backend.site = transform.partitions_sites[sj-1]

            j.inputsandbox = job.inputsandbox
            j.outputsandbox = job.outputsandbox
            sjl.append(j)
            # Task handling
            j.application.tasks_id = job.application.tasks_id
            j.application.id = transform.getNewAppID(sj)
             #transform.setAppStatus(j.application, "submitting")
        if not job.application.tasks_id.startswith("00"):
            job.application.tasks_id = "00:%s" % job.application.tasks_id
        return sjl

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def _create_subjob(self, job, dataset):
        logger.debug("_create_subjob")
        datatmp = []

        logger.debug("dataset size: %s" % str(len(dataset)))
        #logger.debug( "dataset: %s" % str(dataset) )

        if isinstance(dataset, LHCbDataset):
            for i in dataset:
                if isType(i, DiracFile):
                    datatmp.append(i)
                else:
                    logger.error(
                        "Unkown file-type %s, cannot perform split with file %s" % (type(i), str(i)))
                    from Ganga.Core.exceptions import GangaException
                    raise GangaException(
                        "Unkown file-type %s, cannot perform split with file %s" % (type(i), str(i)))
        elif type(dataset) == type([]) or isType(dataset, GangaList()):
            for file in dataset:
                if type(file) == type(''):
                    datatmp.append(
                        allComponentFilters['gangafiles'](file, None))
                elif isType(file, IGangaFile):
                    datatmp.append(file)
                else:
                    logger.error("Unexpected type: %s" % str(type(file)))
                    logger.error(
                        "Wanted object to inherit from type: %s: %s" % (str(type(IGangaFile()))))
                    from Ganga.Core.exceptions import GangaException
                    x = GangaException(
                        "Unknown(unexpected) file object: %s" % file)
                    raise x
        elif type(dataset) == type(''):
            datatmp.append(DiracFile(lfn=dataset))
        else:
            logger.error("Unkown dataset type, cannot perform split here")
            from Ganga.Core.exceptions import GangaException
            logger.error("Dataset found: " + str(dataset))
            raise GangaException(
                "Unkown dataset type, cannot perform split here")

        logger.debug("Creating new Job in Splitter")
        j = Job()
        logger.debug("Copying From Job")
        j.copyFrom(
            stripProxy(job), ['inputdata', 'inputsandbox', 'inputfiles'])
        logger.debug("Unsetting Splitter")
        j.splitter = None
        logger.debug("Unsetting Merger")
        j.merger = None
        # j.inputsandbox = [] ## master added automatically
        #j.inputfiles = []
        logger.debug("Setting InputData")
        j.inputdata = LHCbDataset(files=datatmp[:],
                                  persistency=self.persistency,
                                  depth=self.depth)
        #j.inputdata.XMLCatalogueSlice = self.XMLCatalogueSlice
        logger.debug("Returning new subjob")
        return j

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def _create_subjob(self, job, inputdata):
        j = Job()
        j.copyFrom(job)
        j.splitter = None
        j.merger = None
        j.inputsandbox = []  # master added automatically
        j.inputfiles = []
        j.inputdata = inputdata

        return j

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def _create_subjob(self, job, dataset):
        logger.debug("_create_subjob")
        j = Job()
        j.copyFrom(job)
        j.splitter = None
        j.merger = None
        j.inputsandbox = []  # master added automatically
        j.inputdata = GaudiDataset(files=dataset)
##         if not j.inputdata: j.inputdata = GaudiDataset(files=dataset)
# else:               j.inputdata.files = dataset
        return j

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def createSubjob(self, job, additional_skip_args=None):
        """ Create a new subjob by copying the master job and setting all fields correctly.
        """
        from Ganga.GPIDev.Lib.Job import Job
        if additional_skip_args is None:
            additional_skip_args = []

        j = Job()
        skipping_args = ['splitter', 'inputsandbox', 'inputfiles', 'inputdata', 'subjobs']
        for arg in additional_skip_args:
            skipping_args.append(arg)
        j.copyFrom(job, skipping_args)
        j.splitter = None
        j.inputsandbox = []
        j.inputfiles = []
        j.inputdata = []
        return j

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def _create_subjob(self, job, dataset):
        logger.debug("_create_subjob")

        datatmp = []
        if isinstance(dataset, LHCbDataset):
            for i in dataset:
                if isinstance(i, DiracFile):
                    datatmp.extend(i)
                else:
                    logger.error(
                        "Unkown file-type %s, cannot perform split with file %s" % (type(i), str(i)))
                    from Ganga.Core.exceptions import GangaException
                    raise GangaException(
                        "Unkown file-type %s, cannot perform split with file %s" % (type(i), str(i)))
        elif isinstance(dataset, list):
            from Ganga.GPIDev.Base.Proxy import isType
            for i in dataset:
                if type(i) is str:
                    datatmp.append(DiracFile(lfn=i))
                elif isType(i, DiracFile()):
                    datatmp.extend(i)
                else:
                    x = GangaException(
                        "Unknown(unexpected) file object: %s" % i)
                    raise x
        else:
            logger.error("Unkown dataset type, cannot perform split here")
            from Ganga.Core.exceptions import GangaException
            raise GangaException(
                "Unkown dataset type, cannot perform split here")

        logger.debug("Creating new Job in Splitter")
        j = Job()
        j.copyFrom(stripProxy(job))
        j.splitter = None
        j.merger = None
        j.inputsandbox = []  # master added automatically
        j.inputfiles = []
        j.inputdata = LHCbDataset(files=datatmp[:],
                                  persistency=self.persistency,
                                  depth=self.depth)
        j.inputdata.XMLCatalogueSlice = self.XMLCatalogueSlice

        return j

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
    def split(self,job):
        from Ganga.GPIDev.Lib.Job import Job
        subjobs = []
        primeTables = job.inputdata.get_dataset()

        ## avoid creating jobs with nothing to do
        if self.numsubjobs > len(primeTables):
            self.numsubjobs = len(primeTables)

        ## create subjobs
        for i in range(self.numsubjobs):
            j = Job()
            j.application   = job.application
            j.inputdata     = job.inputdata 
            j.inputdata.table_id_lower = 1 
            j.inputdata.table_id_upper = 1
            j.outputdata    = job.outputdata 
            j.inputsandbox  = job.inputsandbox
            j.outputsandbox = job.outputsandbox
            j.backend       = job.backend
            subjobs.append(j)

        ## chunksize of each subjob
        chunksize = len(primeTables) / self.numsubjobs

        offset = 0
        for i in range(len(subjobs)):
            my_chunksize = chunksize
            if len(primeTables) % self.numsubjobs >= i+1: my_chunksize+=1

            ## set lower bound id (inclusive)
            subjobs[i].inputdata.table_id_lower = offset+1
            ## fill subjob with prime tables 
            #for j in range(my_chunksize):
            #    subjobs[i].application.addPrimeTable(primeTables[offset+j])
            offset += my_chunksize
            ## set upper  bound id (inclusive)
            subjobs[i].inputdata.table_id_upper = offset

        return subjobs

# 需要导入模块: from Ganga.GPIDev.Lib.Job import Job [as 别名]
# 或者: from Ganga.GPIDev.Lib.Job.Job import inputdata [as 别名]
def test__setup_bulk_subjobs(tmpdir, db):
    from Ganga.Core import BackendError
    from Ganga.GPIDev.Lib.Dataset.Dataset import Dataset
    from GangaDirac.Lib.Backends import Dirac

    name = str(tmpdir.join('submit_script'))
    with open(name, 'w') as fd:
        fd.write(script_template.replace('###PARAMETRIC_INPUTDATA###', str([['a'], ['b']])))

    with pytest.raises(BackendError):
        db._setup_bulk_subjobs([], name)

    d = Dirac()
    j = Job()
    j.id = 0  # This would normally be set by the registry if this was a proxy job
    j.application = Executable()
    j.splitter = ArgSplitter()
    j.splitter.args = [['a'], ['b'], ['c'], ['d'], ['e']]
    j.inputdata = Dataset()
    j.backend = d
    d._parent = j

    dirac_ids = [123, 456]

    def fake_setup_subjob_dataset(dataset):
        assert dataset in [['a'], ['b']], 'dataset not passed properly'

    with patch.object(d, '_setup_subjob_dataset', fake_setup_subjob_dataset):
        assert d._setup_bulk_subjobs(dirac_ids, name), 'didnt run'

    assert len(j.subjobs) == len(dirac_ids), 'didnt work'
    for id_, backend_id, subjob in zip(range(len(dirac_ids)), dirac_ids, j.subjobs):
        assert id_ == subjob.id, 'ids dont match'
        assert backend_id == subjob.backend.id, 'backend.ids dont match'
        assert isinstance(subjob.application, j.application.__class__), 'apps dont match'
        assert subjob.splitter is None, 'splitter not done'
        assert isinstance(subjob.backend, j.backend.__class__), 'backend dont match'