Add failure scenario for calculate_levenshtein_distance

Author: aditya-balachander

cumulusci/tasks/bulkdata/load.py

@@ -342,6 +342,7 @@ def configure_step(self, mapping):
             api_options["update_key"] = mapping.update_key[0]
             action = DataOperationType.UPSERT
         elif mapping.action == DataOperationType.SELECT:
+            # Bulk process expects DataOpertionType to be QUERY
             action = DataOperationType.QUERY
         else:
             action = mapping.action

cumulusci/tasks/bulkdata/tests/test_select_utils.py

@@ -1,3 +1,5 @@
+import pytest
+
 from cumulusci.tasks.bulkdata.select_utils import (
     SelectOperationExecutor,
     SelectStrategy,
@@ -215,6 +217,20 @@ def test_calculate_levenshtein_distance():
     assert calculate_levenshtein_distance(record1, record2) == 0  # Distance should be 0
 
 
+def test_calculate_levenshtein_distance_error():
+    # Identical records
+    record1 = ["Tom Cruise", "24", "Actor"]
+    record2 = [
+        "Tom Cruise",
+        "24",
+        "Actor",
+        "SomethingElse",
+    ]  # Record Length does not match
+    with pytest.raises(ValueError) as e:
+        calculate_levenshtein_distance(record1, record2)
+    assert "Records must have the same number of fields" in str(e.value)
+
+
 def test_find_closest_record():
     # Test case 1: Exact match
     load_record = ["Tom Cruise", "62", "Actor"]