fix(service): dataset import error (#3670)

Author: mohammad-alisafaee

.gitignore

@@ -56,6 +56,7 @@ htmlcov/
 nosetests.xml
 coverage.xml
 *,cover
+.hypothesis
 
 # Translations
 *.mo

renku/core/dataset/providers/zenodo.py

@@ -179,7 +179,7 @@ class ZenodoDatasetSchema(ProviderDatasetSchema):
             """Schema for Zenodo datasets."""
 
             @pre_load
-            def fix_data(self, data, **kwargs):
+            def fix_data(self, data, **_):
                 """Fix data that is received from Zenodo."""
                 # Fix context
                 context = data.get("@context")
@@ -236,7 +236,7 @@ def fix_data(self, data, **kwargs):
 class ZenodoFileSerializer:
     """Zenodo record file."""
 
-    def __init__(self, *, id=None, checksum=None, links=None, key=None, size=None, **kwargs):
+    def __init__(self, *, id=None, checksum=None, links=None, key=None, size=None, **_):
         self.id = id
         self.checksum = checksum
         self.links = links

renku/ui/service/controllers/datasets_import.py

@@ -48,7 +48,7 @@ def renku_op(self):
         """Renku operation for the controller."""
         job = self.cache.make_job(
             self.user,
-            # NOTE: To support operation to be execute on remote project, this behaviour should be updated.
+            # NOTE: To support operation to be executed on remote project, this behaviour should be updated.
             project=self.ctx["project_id"],
             job_data={"renku_op": "dataset_import", "client_extras": self.ctx.get("client_extras")},
         )

renku/ui/service/jobs/datasets.py

@@ -37,7 +37,7 @@ def dataset_import(
     user_job_id,
     project_id,
     dataset_uri,
-    name=None,
+    slug=None,
     extract=False,
     tag=None,
     timeout=None,
@@ -63,7 +63,7 @@ def dataset_import(
             command = import_dataset_command().with_commit_message(commit_message)
             command.with_communicator(communicator).build().execute(
                 uri=dataset_uri,
-                name=name,
+                slug=slug,
                 extract=extract,
                 tag=tag,
                 yes=True,
@@ -98,7 +98,7 @@ def _is_safe_to_pass_gitlab_token(project_git_url, dataset_uri):
 
 
 @requires_cache
-def dataset_add_remote_file(cache, user, user_job_id, project_id, create_dataset, commit_message, name, url):
+def dataset_add_remote_file(cache, user, user_job_id, project_id, create_dataset, commit_message, slug, url):
     """Add a remote file to a specified dataset."""
     user = cache.ensure_user(user)
     worker_log.debug(f"executing dataset add remote file job for {user.user_id}:{user.fullname}")
@@ -113,9 +113,9 @@ def dataset_add_remote_file(cache, user, user_job_id, project_id, create_dataset
         with renku_project_context(project.abs_path):
             urls = url if isinstance(url, list) else [url]
 
-            worker_log.debug(f"adding files {urls} to dataset {name}")
+            worker_log.debug(f"adding files {urls} to dataset {slug}")
             command = add_to_dataset_command().with_commit_message(commit_message).build()
-            result = command.execute(dataset_slug=name, urls=urls, create=create_dataset)
+            result = command.execute(dataset_slug=slug, urls=urls, create=create_dataset)
             if result.error:
                 raise result.error
 

tests/service/jobs/test_datasets.py

@@ -88,8 +88,8 @@ def test_dataset_url_import_job(url, svc_client_with_repo):
 @pytest.mark.service
 @retry_failed
 @pytest.mark.vcr
-def test_dataset_import_job(doi, svc_client_with_repo):
-    """Test dataset import via doi."""
+def test_dataset_import_job_with_slug(doi, svc_client_with_repo):
+    """Test dataset import via doi and give it a slug."""
     svc_client, headers, project_id, url_components = svc_client_with_repo
 
     user_id = encode_b64(secure_filename("9ab2fc80-3a5c-426d-ae78-56de01d214df"))
@@ -118,7 +118,14 @@ def test_dataset_import_job(doi, svc_client_with_repo):
     job_id = response.json["result"]["job_id"]
 
     commit_message = "service: import remote dataset"
-    dataset_import(user, job_id, project_id, doi, commit_message=commit_message)
+    dataset_import(
+        user=user,
+        user_job_id=job_id,
+        project_id=project_id,
+        dataset_uri=doi,
+        slug="dataset-slug",
+        commit_message=commit_message,
+    )
 
     new_commit = Repository(dest).head.commit
     assert old_commit.hexsha != new_commit.hexsha
@@ -279,7 +286,16 @@ def test_dataset_add_remote_file(url, svc_client_with_repo):
     job_id = response.json["result"]["files"][0]["job_id"]
     commit_message = "service: dataset add remote file"
 
-    dataset_add_remote_file(user, job_id, project_id, True, commit_message, payload["slug"], url)
+    # user, user_job_id, project_id, create_dataset, commit_message, slug, url
+    dataset_add_remote_file(
+        user=user,
+        user_job_id=job_id,
+        project_id=project_id,
+        create_dataset=True,
+        commit_message=commit_message,
+        slug=payload["slug"],
+        url=url,
+    )
 
     new_commit = Repository(dest).head.commit