Added some tests and they pass with updated backend

Author: Diego Ardila

nucleus/__init__.py

@@ -387,28 +387,33 @@ def populate_dataset(
 
         agg_response = UploadResponse(json={DATASET_ID_KEY: dataset_id})
 
-        tqdm_local_batches = self.tqdm_bar(local_batches)
-
-        tqdm_remote_batches = self.tqdm_bar(remote_batches)
-
         async_responses: List[Any] = []
 
-        for batch in tqdm_local_batches:
-            payload = construct_append_payload(batch, update)
-            responses = self._process_append_requests_local(
-                dataset_id, payload, update
+        if local_batches:
+            tqdm_local_batches = self.tqdm_bar(
+                local_batches, desc="Local file batches"
             )
-            async_responses.extend(responses)
-
-        for batch in tqdm_remote_batches:
-            payload = construct_append_payload(batch, update)
-            responses = self._process_append_requests(
-                dataset_id=dataset_id,
-                payload=payload,
-                update=update,
-                batch_size=batch_size,
+
+            for batch in tqdm_local_batches:
+                payload = construct_append_payload(batch, update)
+                responses = self._process_append_requests_local(
+                    dataset_id, payload, update
+                )
+                async_responses.extend(responses)
+
+        if remote_batches:
+            tqdm_remote_batches = self.tqdm_bar(
+                remote_batches, desc="Remote file batches"
             )
-            async_responses.extend(responses)
+            for batch in tqdm_remote_batches:
+                payload = construct_append_payload(batch, update)
+                responses = self._process_append_requests(
+                    dataset_id=dataset_id,
+                    payload=payload,
+                    update=update,
+                    batch_size=batch_size,
+                )
+                async_responses.extend(responses)
 
         for response in async_responses:
             agg_response.update_response(response)
@@ -423,6 +428,8 @@ def _process_append_requests_local(
         local_batch_size: int = 10,
     ):
         def get_files(batch):
+            for item in batch:
+                item[UPDATE_KEY] = update
             request_payload = [
                 (
                     ITEMS_KEY,

tests/test_dataset.py

@@ -113,6 +113,56 @@ def test_dataset_create_and_delete(CLIENT):
     assert response == {"message": "Beginning dataset deletion..."}
 
 
+def test_dataset_update_metadata_local(dataset):
+    dataset.append(
+        [
+            DatasetItem(
+                image_location=LOCAL_FILENAME,
+                metadata={"snake_field": 0},
+                reference_id="test_image",
+            )
+        ]
+    )
+    dataset.append(
+        [
+            DatasetItem(
+                image_location=LOCAL_FILENAME,
+                metadata={"snake_field": 1},
+                reference_id="test_image",
+            )
+        ],
+        update=True,
+    )
+    resulting_item = dataset.iloc(0)["item"]
+    print(resulting_item)
+    assert resulting_item.metadata["snake_field"] == 1
+
+
+def test_dataset_update_metadata(dataset):
+    dataset.append(
+        [
+            DatasetItem(
+                image_location=TEST_IMG_URLS[0],
+                metadata={"snake_field": 0},
+                reference_id="test_image",
+            )
+        ]
+    )
+    dataset.append(
+        [
+            DatasetItem(
+                image_location=TEST_IMG_URLS[0],
+                metadata={"snake_field": 1},
+                reference_id="test_image",
+            )
+        ],
+        update=True,
+    )
+    resulting_item = dataset.iloc(0)["item"]
+    print(resulting_item)
+    assert resulting_item.metadata["snake_field"] == 1
+
+
 def test_dataset_append(dataset):
     def check_is_expected_response(response):
         assert isinstance(response, UploadResponse)