Add S3 path check.

Author: igorborgest

awswrangler/_utils.py

@@ -90,6 +90,8 @@ def parse_path(path: str) -> Tuple[str, str]:
     >>> bucket, key = parse_path('s3://bucket/key')
 
     """
+    if path.startswith("s3://") is False:
+        raise exceptions.InvalidArgumentValue(f"'{path}' is not a valid path. It MUST start with 's3://'")
     parts = path.replace("s3://", "").split("/", 1)
     bucket: str = parts[0]
     key: str = ""

awswrangler/s3.py

@@ -188,11 +188,11 @@ def _list_objects(
     suffix: Optional[str] = None,
     boto3_session: Optional[boto3.Session] = None,
 ) -> List[str]:
-    client_s3: boto3.client = _utils.client(service_name="s3", session=boto3_session)
-    paginator = client_s3.get_paginator("list_objects_v2")
     bucket: str
     prefix: str
     bucket, prefix = _utils.parse_path(path=path)
+    client_s3: boto3.client = _utils.client(service_name="s3", session=boto3_session)
+    paginator = client_s3.get_paginator("list_objects_v2")
     args: Dict[str, Any] = {"Bucket": bucket, "Prefix": prefix, "PaginationConfig": {"PageSize": 1000}}
     if delimiter is not None:
         args["Delimiter"] = delimiter

testing/test_awswrangler/test_data_lake2.py

@@ -457,3 +457,9 @@ def test_glue_database():
 
     assert test_database_name == ""
     assert test_database_description == ""
+
+
+def test_list_wrong_path(path):
+    wrong_path = path.replace("s3://", "")
+    with pytest.raises(wr.exceptions.InvalidArgumentValue):
+        wr.s3.list_objects(wrong_path)