[df][NFC] Adapt unittest to changes

Author: vepadulano

Diff for: bindings/experimental/distrdf/test/test_ranges.py

@@ -6,6 +6,10 @@
 
 import ROOT
 
+from collections import namedtuple
+
+# Use a dummy execution identifier to test for TTree-based clustered ranges
+Dummy = namedtuple("Dummy", ["rdf_uuid"])
 
 def emptysourceranges_to_tuples(ranges):
     """Convert EmptySourceRange objects to tuples with the shape (start, end)"""
@@ -34,11 +38,11 @@ def test_nentries_multipleOf_npartitions(self):
         npartitions_large = 10
 
         # First case
-        rng = Ranges.get_balanced_ranges(nentries_small, npartitions_small, exec_id=None)
+        rng = Ranges.get_balanced_ranges(nentries_small, npartitions_small, exec_id=Dummy("dummy"))
         ranges_small = emptysourceranges_to_tuples(rng)
 
         # Second case
-        rng = Ranges.get_balanced_ranges(nentries_large, npartitions_large, exec_id=None)
+        rng = Ranges.get_balanced_ranges(nentries_large, npartitions_large, exec_id=Dummy("dummy"))
         ranges_large = emptysourceranges_to_tuples(rng)
 
         ranges_small_reqd = [(0, 2), (2, 4), (4, 6), (6, 8), (8, 10)]
@@ -70,12 +74,12 @@ def test_nentries_not_multipleOf_npartitions(self):
 
         # Example in which fractional part of
         # (nentries/npartitions) >= 0.5
-        rng = Ranges.get_balanced_ranges(nentries_1, npartitions, exec_id=None)
+        rng = Ranges.get_balanced_ranges(nentries_1, npartitions, exec_id=Dummy("dummy"))
         ranges_1 = emptysourceranges_to_tuples(rng)
 
         # Example in which fractional part of
         # (nentries/npartitions) < 0.5
-        rng = Ranges.get_balanced_ranges(nentries_2, npartitions, exec_id=None)
+        rng = Ranges.get_balanced_ranges(nentries_2, npartitions, exec_id=Dummy("dummy"))
         ranges_2 = emptysourceranges_to_tuples(rng)
 
         # Required output pairs
@@ -94,7 +98,7 @@ def test_nentries_greater_than_npartitions(self):
         nentries = 5
         npartitions = 7
 
-        rng = Ranges.get_balanced_ranges(nentries, npartitions, exec_id=None)
+        rng = Ranges.get_balanced_ranges(nentries, npartitions, exec_id=Dummy("dummy"))
         ranges = emptysourceranges_to_tuples(rng)
 
         ranges_reqd = [(0, 1), (1, 2), (2, 3), (3, 4), (4, 5)]
@@ -157,7 +161,7 @@ def test_clustered_ranges_with_one_cluster(self):
         filenames = ["backend/Slimmed_ntuple.root"]
         npartitions = 1
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -180,7 +184,7 @@ def test_npartitions_greater_than_clusters(self):
         filenames = ["backend/Slimmed_ntuple.root"]
         npartitions = 2
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         # We return one task per partition
@@ -204,7 +208,7 @@ def test_clustered_ranges_with_two_clusters_two_partitions(self):
         filenames = ["backend/2clusters.root"]
         npartitions = 2
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
         ranges = treeranges_to_tuples(clusteredranges)
 
@@ -227,7 +231,7 @@ def test_rdataframe_with_treename_and_filename_with_globbing(self):
         expected_inputfiles = ["backend/2clusters.root"]
         extracted_inputfiles = rdf.inputfiles
 
-        percranges = Ranges.get_percentage_ranges([treename], extracted_inputfiles, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges([treename], extracted_inputfiles, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
         ranges = treeranges_to_tuples(clusteredranges)
 
@@ -258,7 +262,7 @@ def test_rdataframe_with_notreename_and_chain_with_subtrees(self):
         extracted_filenames = rdf.inputfiles
 
         percranges = Ranges.get_percentage_ranges(
-            extracted_subtreenames, extracted_filenames, npartitions, friendinfo=None, exec_id=None)
+            extracted_subtreenames, extracted_filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
         ranges = treeranges_to_tuples(clusteredranges)
 
@@ -281,7 +285,7 @@ def test_clustered_ranges_with_four_clusters_four_partitions(self):
         filenames = ["backend/4clusters.root"]
         npartitions = 4
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -304,7 +308,7 @@ def test_clustered_ranges_with_many_clusters_four_partitions(self):
         filenames = ["backend/1000clusters.root"]
         npartitions = 4
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -327,7 +331,7 @@ def test_clustered_ranges_with_many_clusters_many_partitions(self):
         filenames = ["backend/1000clusters.root"]
         npartitions = 1000
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -349,7 +353,7 @@ def test_clustered_ranges_with_two_files(self):
         filenames = ["backend/2clusters.root", "backend/4clusters.root"]
         npartitions = 2
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -366,7 +370,7 @@ def test_three_files_one_partition(self):
         filenames = [f"distrdf_unittests_file_{i}.root" for i in range(nfiles)]
         npartitions = 1
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -382,7 +386,7 @@ def test_three_files_one_partition_per_file(self):
         filenames = [f"distrdf_unittests_file_{i}.root" for i in range(nfiles)]
         npartitions = nfiles
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -398,7 +402,7 @@ def test_three_files_two_partitions_per_file(self):
         treenames = [f"tree_{i}" for i in range(nfiles)]
         filenames = [f"distrdf_unittests_file_{i}.root" for i in range(nfiles)]
         npartitions = nfiles * 2
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -425,7 +429,7 @@ def test_three_files_partitions_equal_clusters(self):
         filenames = [f"distrdf_unittests_file_{i}.root" for i in range(nfiles)]
         npartitions = nfiles * 10  # trees have 10 clusters
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         ranges = treeranges_to_tuples(clusteredranges)
@@ -473,7 +477,7 @@ def test_three_files_partitions_greater_than_clusters(self):
         filenames = [f"distrdf_unittests_file_{i}.root" for i in range(nfiles)]
         npartitions = 42
 
-        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=None)
+        percranges = Ranges.get_percentage_ranges(treenames, filenames, npartitions, friendinfo=None, exec_id=Dummy("dummy"))
         clusteredranges = [Ranges.get_clustered_range_from_percs(percrange)[0] for percrange in percranges]
 
         # We return one task per partition