more fixes

evadb/binder/binder_utils.py

@@ -242,9 +242,7 @@ def resolve_alias_table_value_expression(node: FunctionExpression):
         if not len(node.alias.col_names):
             node.alias = Alias(node.alias.alias_name, default_output_col_aliases)
         else:
-            output_aliases = [
-                str(col_name) for col_name in node.alias.col_names
-            ]
+            output_aliases = [str(col_name) for col_name in node.alias.col_names]
             node.alias = Alias(node.alias.alias_name, output_aliases)
 
     assert len(node.alias.col_names) == len(

evadb/binder/statement_binder_context.py

@@ -171,7 +171,7 @@ def _check_table_alias_map(self, alias, col_name) -> ColumnCatalogEntry:
         if table_obj is not None:
             if table_obj.table_type == TableType.NATIVE_DATA:
                 for column_catalog_entry in table_obj.columns:
-                    if column_catalog_entry.name == col_name:
+                    if column_catalog_entry.name.lower() == col_name.lower():
                         return column_catalog_entry
             else:
                 return self._catalog().get_column_catalog_entry(table_obj, col_name)
@@ -191,7 +191,7 @@ def _check_derived_table_alias_map(self, alias, col_name) -> CatalogColumnType:
             return None
 
         for name, obj in col_objs_map.items():
-            if name == col_name:
+            if name.lower() == col_name.lower():
                 return obj
 
     def _get_all_alias_and_col_name(self) -> List[Tuple[str, str]]:

test/integration_tests/long/test_huggingface_functions.py

@@ -113,19 +113,13 @@ def test_object_detection(self):
         # Test that there exists a column with function_name.score and each entry is a list of floats
         self.assertTrue(function_name + ".score" in output_frames.columns)
         self.assertTrue(
-            all(
-                isinstance(x, list)
-                for x in output.frames[function_name + ".score"]
-            )
+            all(isinstance(x, list) for x in output.frames[function_name + ".score"])
         )
 
         # Test that there exists a column with function_name.label and each entry is a list of strings
         self.assertTrue(function_name + ".label" in output_frames.columns)
         self.assertTrue(
-            all(
-                isinstance(x, list)
-                for x in output.frames[function_name + ".label"]
-            )
+            all(isinstance(x, list) for x in output.frames[function_name + ".label"])
         )
 
         # Test that there exists a column with function_name.box and each entry is a dictionary with 4 keys
@@ -160,19 +154,13 @@ def test_image_classification(self):
         # Test that there exists a column with function_name.score and each entry is a list of floats
         self.assertTrue(function_name + ".score" in output.frames.columns)
         self.assertTrue(
-            all(
-                isinstance(x, list)
-                for x in output.frames[function_name + ".score"]
-            )
+            all(isinstance(x, list) for x in output.frames[function_name + ".score"])
         )
 
         # Test that there exists a column with function_name.label and each entry is a list of strings
         self.assertTrue(function_name + ".label" in output.frames.columns)
         self.assertTrue(
-            all(
-                isinstance(x, list)
-                for x in output.frames[function_name + ".label"]
-            )
+            all(isinstance(x, list) for x in output.frames[function_name + ".label"])
         )
 
         drop_function_query = f"DROP FUNCTION {function_name};"
@@ -214,10 +202,7 @@ def test_text_classification(self):
         # Test that there exists a column with function_name.score and each entry is a float
         self.assertTrue(function_name + ".score" in output.frames.columns)
         self.assertTrue(
-            all(
-                isinstance(x, float)
-                for x in output.frames[function_name + ".score"]
-            )
+            all(isinstance(x, float) for x in output.frames[function_name + ".score"])
         )
 
         drop_function_query = f"DROP FUNCTION {function_name};"
@@ -326,10 +311,7 @@ def test_toxicity_classification(self):
         # and each entry is a float
         self.assertTrue(function_name + ".score" in output.frames.columns)
         self.assertTrue(
-            all(
-                isinstance(x, float)
-                for x in output.frames[function_name + ".score"]
-            )
+            all(isinstance(x, float) for x in output.frames[function_name + ".score"])
         )
 
         drop_function_query = f"DROP FUNCTION {function_name};"
@@ -375,10 +357,7 @@ def test_multilingual_toxicity_classification(self):
         # Test that there exists a column with function_name.score and each entry is a float
         self.assertTrue(function_name + ".score" in output.frames.columns)
         self.assertTrue(
-            all(
-                isinstance(x, float)
-                for x in output.frames[function_name + ".score"]
-            )
+            all(isinstance(x, float) for x in output.frames[function_name + ".score"])
         )
 
         drop_function_query = f"DROP FUNCTION {function_name};"

test/integration_tests/short/test_insert_executor.py

@@ -97,7 +97,7 @@ def test_should_insert_tuples_in_table(self):
 
         self.assertIsNone(
             np.testing.assert_array_equal(
-                batch.frames["csvtable.name"].array,
+                batch.frames["CSVTable.name"].array,
                 np.array(
                     [
                         "test_evadb/similarity/data/sad.jpg",

test/integration_tests/short/test_load_executor.py

@@ -110,7 +110,7 @@ def test_should_load_csv_in_table(self):
 
         # assert the batches are equal
         expected_batch = next(create_dummy_csv_batches())
-        expected_batch.modify_column_alias("myvideocsv")
+        expected_batch.modify_column_alias("MyVideoCSV")
         self.assertEqual(actual_batch, expected_batch)
 
         # clean up

test/integration_tests/short/test_select_executor.py

@@ -68,8 +68,8 @@ def test_should_load_and_sort_in_table(self):
         actual_batch = execute_query_fetch_all(self.evadb, select_query)
         expected_rows = [
             {
-                "myvideo.id": i,
-                "myvideo.data": np.array(np.ones((32, 32, 3)) * i, dtype=np.uint8),
+                "MyVideo.id": i,
+                "MyVideo.data": np.array(np.ones((32, 32, 3)) * i, dtype=np.uint8),
             }
             for i in range(NUM_FRAMES)
         ]
@@ -85,7 +85,7 @@ def test_should_load_and_select_in_table(self):
         select_query = "SELECT id FROM MyVideo;"
         actual_batch = execute_query_fetch_all(self.evadb, select_query)
         actual_batch.sort()
-        expected_rows = [{"myvideo.id": i} for i in range(NUM_FRAMES)]
+        expected_rows = [{"MyVideo.id": i} for i in range(NUM_FRAMES)]
         expected_batch = Batch(frames=pd.DataFrame(expected_rows))
         self.assertEqual(actual_batch, expected_batch)
 
@@ -121,7 +121,7 @@ def test_select_star_in_lateral_join(self):
         select_query = """SELECT * FROM MyVideo JOIN LATERAL
                           Yolo(data);"""
         actual_batch = execute_query_fetch_all(self.evadb, select_query)
-        self.assertEqual(actual_batch.frames.columns, ["myvideo.id"])
+        self.assertEqual(actual_batch.frames.columns, ["MyVideo.id"])
 
     def test_should_throw_error_when_both_audio_and_video_selected(self):
         query = """LOAD VIDEO 'data/sample_videos/touchdown.mp4'
@@ -159,7 +159,7 @@ def test_select_and_iframe_sample(self):
         actual_batch.sort()
 
         expected_batch = list(create_dummy_batches(filters=range(0, NUM_FRAMES, 7)))
-        expected_batch[0] = expected_batch[0].project(["myvideo.id"])
+        expected_batch[0] = expected_batch[0].project(["MyVideo.id"])
 
         self.assertEqual(len(actual_batch), len(expected_batch[0]))
         self.assertEqual(actual_batch, expected_batch[0])
@@ -170,7 +170,7 @@ def test_select_and_iframe_sample_without_sampling_rate(self):
         actual_batch.sort()
 
         expected_batch = list(create_dummy_batches(filters=range(0, NUM_FRAMES, 1)))
-        expected_batch[0] = expected_batch[0].project(["myvideo.id"])
+        expected_batch[0] = expected_batch[0].project(["MyVideo.id"])
 
         self.assertEqual(len(actual_batch), len(expected_batch[0]))
         self.assertEqual(actual_batch, expected_batch[0])
@@ -193,7 +193,7 @@ def test_select_and_groupby_first(self):
         self.assertEqual(len(actual_batch), len(expected_batch))
 
         expected_batch.rename(
-            columns={"myvideo.id": "FIRST.id", "myvideo.data": "SEGMENT.data"}
+            columns={"MyVideo.id": "FIRST.id", "MyVideo.data": "SEGMENT.data"}
         )
         self.assertEqual(
             actual_batch,
@@ -220,7 +220,7 @@ def test_select_and_groupby_with_last(self):
         self.assertEqual(len(actual_batch), len(expected_batch))
 
         expected_batch.rename(
-            columns={"myvideo.id": "LAST.id", "myvideo.data": "SEGMENT.data"}
+            columns={"MyVideo.id": "LAST.id", "MyVideo.data": "SEGMENT.data"}
         )
         self.assertEqual(
             actual_batch,
@@ -274,7 +274,7 @@ def test_select_and_groupby_with_sample(self):
         self.assertEqual(len(actual_batch), len(expected_batch))
 
         expected_batch.rename(
-            columns={"myvideo.id": "FIRST.id", "myvideo.data": "SEGMENT.data"}
+            columns={"MyVideo.id": "FIRST.id", "MyVideo.data": "SEGMENT.data"}
         )
 
         self.assertEqual(
@@ -286,12 +286,12 @@ def test_lateral_join_with_unnest_and_sample(self):
         query = """SELECT id, label
                   FROM MyVideo SAMPLE 2 JOIN LATERAL
                     UNNEST(DummyMultiObjectDetector(data).labels) AS T(label)
-                  WHERE id < 10 ORDER BY id;"""
+                  WHERE iD < 10 ORDER BY id;"""
         unnest_batch = execute_query_fetch_all(self.evadb, query)
         expected = Batch(
             pd.DataFrame(
                 {
-                    "myvideo.id": np.array(
+                    "MyVideo.id": np.array(
                         [0, 0, 2, 2, 4, 4, 6, 6, 8, 8], dtype=np.intp
                     ),
                     "T.label": np.array(

test/unit_tests/optimizer/test_cascade_optimizer.py

@@ -58,7 +58,7 @@ def test_logical_to_physical_function(self):
         actual_batch = execute_query_fetch_all(self.evadb, select_query)
         actual_batch.sort()
         expected = [
-            {"myvideo.id": i * 2, "dummyobjectdetector.label": ["person"]}
+            {"MyVideo.id": i * 2, "DummyObjectDetector.label": ["person"]}
             for i in range(NUM_FRAMES // 2)
         ]
         expected_batch = Batch(frames=pd.DataFrame(expected))