Issue 9656 Raise an error when check_cols has duplicated values

.changes/unreleased/Features-20240228-192518.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Validation to detect duplicate column names in the check_cols configuration of a snapshot.
+time: 2024-02-28T19:25:18.00447-03:00
+custom:
+  Author: ariosramirez
+  Issue: "9656"

core/dbt/artifacts/resources/v1/snapshot.py

@@ -52,6 +52,10 @@ def validate(cls, data):
         if data.get("materialized") and data.get("materialized") != "snapshot":
             raise ValidationError("A snapshot must have a materialized value of 'snapshot'")
 
+        # Validate if there are duplicate column names in check_cols.
+        if len(data.get("check_cols")) != len(set(data.get("check_cols"))):
+            raise ValidationError(f"Duplicate column names in 'check_cols': {data['check_cols']}.")
+
     # Called by "calculate_node_config_dict" in ContextConfigGenerator
     def finalize_and_validate(self):
         data = self.to_dict(omit_none=True)

tests/unit/test_contracts_graph_parsed.py

@@ -1474,6 +1474,14 @@ def test_missing_snapshot_configs(basic_check_snapshot_config_dict):
         SnapshotConfig.validate(wrong_fields)
 
 
+def test_duplicate_check_cols(basic_check_snapshot_config_dict):
+    duplicate_cols = basic_check_snapshot_config_dict
+    # Introducing duplicate column names
+    duplicate_cols["check_cols"] = ["col1", "col2", "col2"]
+    with pytest.raises(ValidationError, match=r"Duplicate column names in 'check_cols'"):
+        SnapshotConfig.validate(duplicate_cols)
+
+
 def test_invalid_check_value(basic_check_snapshot_config_dict):
     invalid_check_type = basic_check_snapshot_config_dict
     invalid_check_type["check_cols"] = "some"