Cleanup source tests (#1912)

* Move test to base for broader coverage (#1848)

* Remove duplicate line (#1848)

* FUDS needed an extra mock (#1848)

data/data-pipeline/data_pipeline/etl/base.py

@@ -164,9 +164,6 @@ def yaml_config_load(cls) -> dict:
         for field in dataset_config["load_fields"]:
             cls.COLUMNS_TO_KEEP.append(field["long_name"])
             setattr(cls, field["df_field_name"], field["long_name"])
-
-            # set the constants for the class
-            setattr(cls, field["df_field_name"], field["long_name"])
         return dataset_config
 
     # This is a classmethod so it can be used by `get_data_frame` without

data/data-pipeline/data_pipeline/tests/sources/doe_energy_burden/test_etl.py

@@ -59,13 +59,3 @@ def test_get_output_file_path(self, mock_etl, mock_paths):
             data_path / "dataset" / "doe_energy_burden" / "usa.csv"
         )
         assert output_file_path == expected_output_file_path
-
-    def test_tract_id_lengths(self, mock_etl, mock_paths):
-        etl = self._setup_etl_instance_and_run_extract(
-            mock_etl=mock_etl, mock_paths=mock_paths
-        )
-        etl.transform()
-        etl.validate()
-        etl.load()
-        df = etl.get_data_frame()
-        assert (df[etl.GEOID_TRACT_FIELD_NAME].str.len() == 11).all()

data/data-pipeline/data_pipeline/tests/sources/eamlis/test_etl.py

@@ -150,3 +150,10 @@ def test_tracts_without_fuds_not_in_results(self, mock_etl, mock_paths):
             assert len(df[etl.GEOID_TRACT_FIELD_NAME]) == len(
                 self._FIXTURES_SHARED_TRACT_IDS
             )
+
+    def test_tract_id_lengths(self, mock_etl, mock_paths):
+        with mock.patch(
+            "data_pipeline.etl.sources.eamlis.etl.add_tracts_for_geometries",
+            new=_fake_add_tracts_for_geometries,
+        ):
+            super().test_tract_id_lengths(mock_etl, mock_paths)

data/data-pipeline/data_pipeline/tests/sources/example/test_etl.py

@@ -209,6 +209,16 @@ def test_get_output_file_path_base(self, mock_etl, mock_paths):
 
         assert actual_file_path == expected_file_path
 
+    def test_tract_id_lengths(self, mock_etl, mock_paths):
+        etl = self._setup_etl_instance_and_run_extract(
+            mock_etl=mock_etl, mock_paths=mock_paths
+        )
+        etl.transform()
+        etl.validate()
+        etl.load()
+        df = etl.get_data_frame()
+        assert (df[etl.GEOID_TRACT_FIELD_NAME].str.len() == 11).all()
+
     def test_fixtures_contain_shared_tract_ids_base(self, mock_etl, mock_paths):
         """Check presence of necessary shared tract IDs.
         Note: We used shared census tract IDs so that later our tests can join all the

data/data-pipeline/data_pipeline/tests/sources/us_army_fuds/test_etl.py

@@ -185,3 +185,10 @@ def test_tracts_without_fuds_not_in_results(self, mock_etl, mock_paths):
             assert len(df[etl.GEOID_TRACT_FIELD_NAME]) == len(
                 self._FIXTURES_SHARED_TRACT_IDS
             )
+
+    def test_tract_id_lengths(self, mock_etl, mock_paths):
+        with mock.patch(
+            "data_pipeline.etl.sources.us_army_fuds.etl.add_tracts_for_geometries",
+            new=_fake_add_tracts_for_geometries,
+        ):
+            return super().test_tract_id_lengths(mock_etl, mock_paths)