Merge pull request #1329 from Sage-Bionetworks/SYNPY-1765

[SYNPY-1765] Remove project id arg from create_record_based_curator_task

Author: andrewelamb

synapseclient/extensions/curator/file_based_metadata_task.py

@@ -10,6 +10,7 @@
 from synapseclient import Synapse  # type: ignore
 from synapseclient import Wiki  # type: ignore
 from synapseclient.core.exceptions import SynapseHTTPError  # type: ignore
+from synapseclient.extensions.curator.utils import project_id_from_entity_id
 from synapseclient.models import (  # type: ignore
     Column,
     ColumnType,
@@ -430,27 +431,15 @@ def create_file_based_metadata_task(
     synapse_client.logger.info(
         "Attempting to get the Synapse ID of the provided folders project."
     )
-    try:
-        entity = Folder(folder_id).get(synapse_client=synapse_client)
-        parent = synapse_client.get(entity.parent_id)
-        project = None
-        while not project:
-            if parent.concreteType == "org.sagebionetworks.repo.model.Project":
-                project = parent
-                break
-            parent = synapse_client.get(parent.parentId)
-    except Exception as e:
-        synapse_client.logger.exception(
-            "Error getting the Synapse ID of the provided folders project"
-        )
-        raise e
+
+    project_id = project_id_from_entity_id(folder_id, synapse_client=synapse_client)
     synapse_client.logger.info("Got the Synapse ID of the provided folders project.")
 
     synapse_client.logger.info("Attempting to create the CurationTask.")
     try:
         task = CurationTask(
             data_type=task_datatype,
-            project_id=project.id,
+            project_id=project_id,
             instructions=instructions,
             assignee_principal_id=(
                 str(assignee_principal_id)

synapseclient/extensions/curator/record_based_metadata_task.py

@@ -11,6 +11,7 @@
 from synapseclient import Synapse
 from synapseclient.core.typing_utils import DataFrame as DATA_FRAME_TYPE
 from synapseclient.core.utils import test_import_pandas
+from synapseclient.extensions.curator.utils import project_id_from_entity_id
 from synapseclient.models import (
     CurationTask,
     Grid,
@@ -99,7 +100,6 @@ def extract_schema_properties_from_web(
 
 
 def create_record_based_metadata_task(
-    project_id: str,
     folder_id: str,
     record_set_name: str,
     record_set_description: str,
@@ -112,6 +112,7 @@ def create_record_based_metadata_task(
     assignee_principal_id: Optional[Union[str, int]] = None,
     *,
     synapse_client: Optional[Synapse] = None,
+    project_id: Optional[str] = None,  # Deprecated, will be removed in v5.0.0
 ) -> Tuple[RecordSet, CurationTask, Grid]:
     """
     Generate and upload CSV templates as a RecordSet for record-based metadata,
@@ -142,7 +143,6 @@ def create_record_based_metadata_task(
 
         record_set, task, grid = create_record_based_metadata_task(
             synapse_client=syn,
-            project_id="syn12345678",
             folder_id="syn87654321",
             record_set_name="BiospecimenMetadata_RecordSet",
             record_set_description="RecordSet for biospecimen metadata curation",
@@ -155,9 +155,10 @@ def create_record_based_metadata_task(
         ```
 
     Arguments:
-        project_id: The Synapse ID of the project where the folder exists.
         folder_id: The Synapse ID of the folder to upload RecordSet to.
-        record_set_name: Name for the RecordSet.
+        record_set_name: Name for the RecordSet entity that will be created.
+            A RecordSet entity captures record-based metadata as a special type of CSV and stores contributor
+              provided metadata collected via Curator enabling sharing and download of validated metadata in Synapse.
         record_set_description: Description for the RecordSet.
         curation_task_name: Name for the CurationTask (used as data_type field).
             Must be unique within the project, otherwise if it matches an existing
@@ -177,6 +178,7 @@ def create_record_based_metadata_task(
         synapse_client: If not passed in and caching was not disabled by
                 `Synapse.allow_client_caching(False)` this will use the last created
                 instance from the Synapse class constructor.
+        project_id: Deprecated, will be removed in v5.0.0
 
     Returns:
         Tuple containing the created RecordSet, CurationTask, and Grid objects
@@ -186,8 +188,6 @@ def create_record_based_metadata_task(
         SynapseError: If there are issues with Synapse operations.
     """
     # Validate required parameters
-    if not project_id:
-        raise ValueError("project_id is required")
     if not folder_id:
         raise ValueError("folder_id is required")
     if not record_set_name:
@@ -203,8 +203,18 @@ def create_record_based_metadata_task(
     if not schema_uri:
         raise ValueError("schema_uri is required")
 
+    if project_id:
+        synapse_client.logger.warning(
+            "The 'project_id' parameter is deprecated and will be removed in v5.0.0. "
+            "The project ID will be inferred from the folder ID provided."
+        )
+
     synapse_client = Synapse.get_client(synapse_client=synapse_client)
 
+    project_id = project_id_from_entity_id(
+        entity_id=folder_id, synapse_client=synapse_client
+    )
+
     template_df = extract_schema_properties_from_web(
         syn=synapse_client, schema_uri=schema_uri
     )

synapseclient/extensions/curator/utils.py

@@ -0,0 +1,32 @@
+from synapseclient import Synapse
+from synapseclient.models import Project
+from synapseclient.operations import get
+
+"""This number represents a safeguard against infinite loops when traversing the folder hierarchy to find the project ID."""
+MAX_HIERARCHY_DEPTH = 1000
+
+
+def project_id_from_entity_id(entity_id: str, synapse_client: Synapse) -> str:
+    """
+    Retrieves the project ID from a given entity ID by traversing up the folder hierarchy
+
+    Args:
+        entity_id: The Synapse ID of the entity (e.g., folder, file) to start from.
+        synapse_client: Authenticated Synapse client instance
+
+    Returns:
+        The Synapse ID of the project that the entity belongs to.
+
+    Raises:
+        ValueError: If the project ID cannot be found within 1000 iterations.
+    """
+
+    # Get the project ID from the folder ID
+    current_obj = get(entity_id, synapse_client=synapse_client)
+    iterations = 0
+    while not isinstance(current_obj, Project):
+        current_obj = get(current_obj.parent_id, synapse_client=synapse_client)
+        iterations += 1
+        if iterations > MAX_HIERARCHY_DEPTH:
+            raise ValueError("Could not find project ID in folder hierarchy")
+    return current_obj.id

synapseclient/models/recordset.py

@@ -360,7 +360,12 @@ def get_detailed_validation_results(
 @dataclass()
 @async_to_sync
 class RecordSet(RecordSetSynchronousProtocol, AccessControllable, BaseJSONSchema):
-    """A RecordSet within Synapse.
+    """
+    A RecordSet entity captures record-based metadata as a special type of CSV.
+    The record set content can be curated using the grid services.
+    When a grid is created from a record set, its data can be exported back to a new version of the record set.
+    The export will include the validation summary as well as a validation file handle that
+      contains detailed validation results for each row in the record set.
 
     Attributes:
         id: The unique immutable ID for this file. A new ID will be generated for new

…/synapseclient/test_schema_management.py …nsions/curator/test_schema_management.pytests/integration/synapseclient/test_schema_management.py renamed to tests/integration/synapseclient/extensions/curator/test_schema_management.py tests/integration/synapseclient/test_schema_management.py renamed to tests/integration/synapseclient/extensions/curator/test_schema_management.py

@@ -8,7 +8,10 @@
 
 from synapseclient import Synapse
 from synapseclient.extensions.curator import bind_jsonschema, register_jsonschema
-from synapseclient.models import File, Folder, Project, SchemaOrganization
+from synapseclient.extensions.curator.record_based_metadata_task import (
+    project_id_from_entity_id,
+)
+from synapseclient.models import Folder, Project, SchemaOrganization
 
 
 def create_test_name():
@@ -259,3 +262,37 @@ def test_complete_workflow(
             # Cleanup: unbind schema before deleting folder
             folder.unbind_schema(synapse_client=syn)
             syn.delete(folder.id)
+
+
+class TestProjectIDFromEntityID:
+    @pytest.fixture(scope="module")
+    def temp_hierarchy(self, syn: Synapse, request) -> tuple[str, str, str]:
+        """Creates a Project -> Folder -> Folder hierarchy for testing."""
+        project = Project(name=create_test_name()).store(synapse_client=syn)
+        folder1 = Folder(name=create_test_name(), parent_id=project.id).store(
+            synapse_client=syn
+        )
+        folder2 = Folder(name=create_test_name(), parent_id=folder1.id).store(
+            synapse_client=syn
+        )
+
+        def delete_project():
+            project.delete(synapse_client=syn)
+
+        request.addfinalizer(delete_project)
+        return project.id, folder1.id, folder2.id
+
+    def test_project_id_from_folder(self, syn, temp_hierarchy):
+        """Test finding project id when input id is from a nested folder."""
+        folder_id = temp_hierarchy[2]
+        expected_project_id = temp_hierarchy[0]
+
+        result = project_id_from_entity_id(folder_id, syn)
+        assert result == expected_project_id
+
+    def test_project_id_from_project(self, syn, temp_hierarchy):
+        """Test finding project id when input id is for a project"""
+        project_id = temp_hierarchy[0]
+
+        result = project_id_from_entity_id(project_id, syn)
+        assert result == project_id