def get_mergeable_values(starting_node: ROOT.RDF.RNode, range_id: int,
computation_graph_callable: Callable[[ROOT.RDF.RNode, int], List], optimized: bool) -> List:
"""
Triggers the computation graph and returns a list of mergeable values.
"""
if optimized:
# Create the RDF computation graph and execute it on this ranged
# dataset. The results of the actions of the graph and their types
# are returned
results, res_types = computation_graph_callable(starting_node, range_id)
# Get RResultPtrs out of the type-erased RResultHandles by
# instantiating with the type of the value
mergeables = [
ROOT.ROOT.Detail.RDF.GetMergeableValue(res.GetResultPtr[res_type]())
if isinstance(res, ROOT.RDF.RResultHandle)
else res
for res, res_type in zip(results, res_types)
]
else:
# Output of the callable
resultptr_list = computation_graph_callable(starting_node, range_id)
mergeables = [Utils.get_mergeablevalue(resultptr) for resultptr in resultptr_list]
return mergeables
def mapper(current_range):
"""
Triggers the event-loop and executes all
nodes in the computational graph using the
callable.
Args:
current_range (Range): A Range named tuple, representing the
range of entries to be processed, their input files and
information about friend trees.
Returns:
list: This respresents the list of (mergeable)values of all
action nodes in the computational graph.
"""
# Disable graphics functionality in ROOT. It is not needed inside a
# distributed task
ROOT.gROOT.SetBatch(True)
# Enable thread safety for the whole mapper function. We need to do
# this since two tasks could be invoking the C++ interpreter
# simultaneously, given that this function will release the GIL
# before calling into C++ to run the event loop. Dask multi-threaded
# or even multi-process workers could trigger such a scenario.
ROOT.EnableThreadSafety()
# We have to decide whether to do this in Dist or in subclasses
# Utils.declare_headers(worker_includes) # Declare headers if any
# Run initialization method to prepare the worker runtime
# environment
initialization()
# Build an RDataFrame instance for the current mapper task, based
# on the type of the head node.
rdf = build_rdf_from_range(current_range)
if optimized:
# Create the RDF computation graph and execute it on this ranged
# dataset. The results of the actions of the graph and their types
# are returned
results, res_types = computation_graph_callable(
rdf, current_range.id)
# Get RResultPtrs out of the type-erased RResultHandles by
# instantiating with the type of the value
mergeables = [
ROOT.ROOT.Detail.RDF.GetMergeableValue(
res.GetResultPtr[res_type]()) if isinstance(
res, ROOT.RDF.RResultHandle) else res
for res, res_type in zip(results, res_types)
]
else:
# Output of the callable
resultptr_list = computation_graph_callable(
rdf, current_range.id)
mergeables = [
Utils.get_mergeablevalue(resultptr)
for resultptr in resultptr_list
]
return mergeables