Addressing Sonar-found bugs and code smells. (#2487)

* Addressing sonar-found bugs and bad code smells.
Primarily:
- Unused variables
- Missing "Optional" in type definitions
- Use https for test download to avoid sonar complaints

---------

Co-authored-by: Tatevik Hakobyan <83741606+tatevikh@users.noreply.github.com>
Co-authored-by: Fayaz Rahman <fayazrahman4u@gmail.com>

deeplake/api/dataset.py

@@ -687,7 +687,7 @@ def _reset_and_load(storage, access_method, dataset_kwargs, address, err):
         if storage.read_only:
             msg = "Cannot reset when loading dataset in read-only mode."
             if parent_commit_id:
-                msg += f" However, you can try loading the previous commit using "
+                msg += " However, you can try loading the previous commit using "
                 msg += f"`deeplake.load('{dataset_kwargs.get('path')}@{parent_commit_id}')`."
             raise ReadOnlyModeError(msg)
         if parent_commit_id is None:
@@ -1175,7 +1175,7 @@ def deepcopy(
         else:
             if not isinstance(src, Dataset):
                 raise TypeError(
-                    f"The specified ``src`` is not an allowed type. Please specify a dataset or a materialized dataset view."
+                    "The specified ``src`` is not an allowed type. Please specify a dataset or a materialized dataset view."
                 )
 
             if not src.index.is_trivial():

deeplake/api/tests/test_api.py

@@ -1714,7 +1714,7 @@ def test_hub_remote_read_videos(storage, memory_ds):
     memory_ds.create_tensor("videos", htype="video", sample_compression="mp4")
 
     video = deeplake.read(
-        "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4",
+        "https://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4",
     )
     memory_ds.videos.append(video)
     assert memory_ds.videos[0].shape == (361, 720, 1280, 3)

deeplake/api/tests/test_link.py

@@ -332,7 +332,7 @@ def test_video(request, local_ds_generator, create_shape_tensor, verify):
         )
         for _ in range(3):
             sample = deeplake.link(
-                "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4"
+                "https://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4"
             )
             ds.linked_videos.append(sample)
 

deeplake/api/tests/test_video.py

@@ -192,7 +192,7 @@ def test_linked_video_timestamps(local_ds):
         ds.create_tensor("videos", htype="link[video]", sample_compression="mp4")
         ds.videos.append(
             deeplake.link(
-                "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4",
+                "https://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4",
                 creds_key="ENV",
             )
         )

deeplake/core/chunk_engine.py

@@ -2279,7 +2279,7 @@ def _sequence_length(self):
         return
 
     @property
-    def sequence_encoder(self) -> SequenceEncoder:
+    def sequence_encoder(self) -> Optional[SequenceEncoder]:
         """Gets the shape encoder from cache, if one is not found it creates a blank encoder.
 
         Raises:
@@ -2676,7 +2676,7 @@ def shapes(
         convert_bad_to_list: bool = True,
     ):
         if len(index) > 1:
-            raise IndexError(f"`.shapes` only accepts indexing on the primary axis.")
+            raise IndexError("`.shapes` only accepts indexing on the primary axis.")
 
         index_0 = index.values[0]
         num_samples, sample_ndim = self._get_total_samples_and_sample_ndim(index_0)

deeplake/core/dataset/dataset.py

@@ -3116,7 +3116,7 @@ def get_sample_from_engine(
                         self[k] = v
                     except Exception as e2:
                         raise Exception(
-                            f"Error while attempting to rollback updates"
+                            "Error while attempting to rollback updates"
                         ) from e2
                 raise e
             finally:

deeplake/core/vectorstore/test_deeplake_vectorstore.py

@@ -285,7 +285,7 @@ def test_search_basic(local_path, hub_cloud_dev_token):
     assert len(data_ce.keys()) == 3  # One for each return_tensors + score
 
     with pytest.raises(ValueError):
-        data_ce = vector_store_cloud.search(
+        vector_store_cloud.search(
             query=f"SELECT * WHERE id=='{vector_store_cloud.dataset.id[0].numpy()[0]}'",
             embedding=query_embedding,
             k=2,
@@ -514,7 +514,7 @@ def test_search_quantitative(distance_metric, hub_cloud_dev_token):
 
     with pytest.raises(ValueError):
         # use indra implementation to search the data
-        data_ce = vector_store.search(
+        vector_store.search(
             query="select * where metadata == {'abcdefg': 28}",
             exec_option="compute_engine",
             distance_metric=distance_metric,

deeplake/core/vectorstore/vector_search/dataset/dataset.py

@@ -313,8 +313,8 @@ def get_not_none_tensors(tensors, embedding_data):
 
 def populate_id_tensor_if_needed(ids_tensor, tensors, not_none_tensors, num_items):
     if "id" not in not_none_tensors and "ids" not in not_none_tensors:
-        id = [str(uuid.uuid1()) for _ in range(num_items)]
-        tensors[ids_tensor] = id
+        found_id = [str(uuid.uuid1()) for _ in range(num_items)]
+        tensors[ids_tensor] = found_id
     else:
         for tensor in not_none_tensors:
             if tensor in ("id", "ids"):
@@ -364,14 +364,14 @@ def update_embedding_info(logger, dataset, embedding_function):
 
     if num_embedding_tensors == 0:
         logger.warning(
-            f"No embedding tensors were found, so the embedding function metadata will not be added to any tensor. "
+            "No embedding tensors were found, so the embedding function metadata will not be added to any tensor. "
             "Consider doing that manually using `vector_store.dataset.tensor_name.info. = <embedding_function_info_dictionary>`"
         )
         return
     if num_embedding_tensors > 1:
         logger.warning(
             f"{num_embedding_tensors} embedding tensors were found. "
-            f"It is not clear to which tensor the embedding function information should be added, so the embedding function metadata will not be added to any tensor. "
+            "It is not clear to which tensor the embedding function information should be added, so the embedding function metadata will not be added to any tensor. "
             "Consider doing that manually using `vector_store.dataset.tensor_name.info = <embedding_function_info_dictionary>`"
         )
         return

deeplake/core/vectorstore/vector_search/dataset/test_dataset.py

@@ -86,7 +86,7 @@ def test_create(caplog, hub_cloud_path, hub_cloud_dev_token):
 
     # Test whether not specifiying runtime with exec_option tensor_db raises error
     with pytest.raises(ValueError):
-        dataset = dataset_utils.create_or_load_dataset(
+        dataset_utils.create_or_load_dataset(
             tensor_params=DEFAULT_VECTORSTORE_TENSORS,
             dataset_path="hub://testingacc2/vectorstore_test_create_dbengine",
             token=hub_cloud_dev_token,
@@ -123,7 +123,7 @@ def test_load(caplog, hub_cloud_dev_token):
     test_logger = logging.getLogger("test_logger")
     with caplog.at_level(logging.WARNING, logger="test_logger"):
         # dataset loading
-        dataset = dataset_utils.create_or_load_dataset(
+        dataset_utils.create_or_load_dataset(
             tensor_params=DEFAULT_VECTORSTORE_TENSORS,
             dataset_path=DEFAULT_VECTORSTORE_DEEPLAKE_PATH,
             token=None,
@@ -142,7 +142,7 @@ def test_load(caplog, hub_cloud_dev_token):
         )
 
     with pytest.raises(ValueError):
-        dataset = dataset_utils.create_or_load_dataset(
+        dataset_utils.create_or_load_dataset(
             tensor_params={"name": "image", "htype": "image"},
             dataset_path=DEFAULT_VECTORSTORE_DEEPLAKE_PATH,
             token=None,
@@ -193,7 +193,7 @@ def test_delete_and_commit():
     dataset.ids.extend([1, 2, 3, 4, 5, 6, 7, 8, 9])
 
     dataset_utils.delete_and_commit(dataset, ids=[1, 2, 3])
-    len(dataset) == 6
+    assert len(dataset) == 6
 
 
 def test_delete_all():
@@ -229,7 +229,7 @@ def test_fetch_embeddings():
 def test_embeding_data():
     query = "tql query"
     with pytest.raises(Exception):
-        embedding = dataset_utils.get_embedding(
+        dataset_utils.get_embedding(
             embedding=None, query=query, embedding_function=None
         )
 

deeplake/core/vectorstore/vector_search/indra/query.py

@@ -1,15 +1,15 @@
 import numpy as np
 
-from typing import List
+from typing import List, Optional
 
 from deeplake.core.vectorstore.vector_search.indra import tql_distance_metrics
 
 
 def create_query_string(
-    distance_metric: str,
+    distance_metric: Optional[str],
     tql_filter: str,
     limit: int,
-    order: str,
+    order: Optional[str],
     tensor_list: List[str],
 ):
     """Function for creating a query string from a distance metric, limit and order.

deeplake/enterprise/test_tensorflow.py

@@ -628,7 +628,7 @@ def test_indexes_tensors(hub_cloud_ds, num_workers):
             ds.xyz.append(i * np.ones((2, 2)))
 
     with pytest.raises(ValueError):
-        ptds = (
+        (
             hub_cloud_ds.dataloader()
             .batch(4)
             .tensorflow(

deeplake/util/connect_dataset.py

@@ -21,7 +21,7 @@ def is_path_connectable(path: str, allow_local: bool) -> bool:
 
 def connect_dataset_entry(
     src_path: str,
-    creds_key: str,
+    creds_key: Optional[str],
     dest_path: Optional[str] = None,
     org_id: Optional[str] = None,
     ds_name: Optional[str] = None,

deeplake/visualizer/tests/test_playback.py

@@ -37,7 +37,7 @@ def test_linked_video_playback(local_ds_generator, gcs_path):
         ds.populate_creds("ENV", from_environment=True)
         ds.video_links.append(
             deeplake.link(
-                "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4",
+                "https://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4",
                 creds_key="ENV",
             )
         )
@@ -49,7 +49,7 @@ def test_linked_video_playback(local_ds_generator, gcs_path):
         url = ds.video_links[0]._get_video_stream_url()
         assert (
             url
-            == "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4"
+            == "https://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerJoyrides.mp4"
         )
         http_data = urlopen(url).read()