Merge pull request #12 from Waltham-Data-Science/claude/align-python-api-response-fUucA

Claude/align python api response f uuc a

Author: stevevanhooser

src/ndi/cloud/api/datasets.py

@@ -21,6 +21,20 @@
 _Client = Annotated[CloudClient | None, SkipValidation()]
 
 
+def _resolve_org_id(org_id: str | None, client: CloudClient) -> str:
+    """Return *org_id* if given, otherwise pull it from client config."""
+    if org_id:
+        return org_id
+    resolved = getattr(client, "config", None)
+    if resolved and getattr(resolved, "org_id", ""):
+        return resolved.org_id
+    raise ValueError(
+        "org_id is required but was not provided and could not be "
+        "resolved from the client config.  Either pass org_id explicitly "
+        "or set NDI_CLOUD_ORGANIZATION_ID in the environment."
+    )
+
+
 @_auto_client
 @validate_call(config=VALIDATE_CONFIG)
 def getDataset(dataset_id: CloudId, *, client: _Client = None) -> dict[str, Any]:
@@ -29,16 +43,22 @@ def getDataset(dataset_id: CloudId, *, client: _Client = None) -> dict[str, Any]
 
 
 @_auto_client
-@validate_call(config=VALIDATE_CONFIG)
 def createDataset(
-    org_id: NonEmptyStr,
-    name: NonEmptyStr,
+    org_id: str | None = None,
+    name: str = "",
     description: str = "",
     *,
     client: _Client = None,
     **kwargs: Any,
 ) -> dict[str, Any]:
-    """POST /organizations/{organizationId}/datasets"""
+    """POST /organizations/{organizationId}/datasets
+
+    If *org_id* is omitted it is resolved from the client's config
+    (populated automatically during login), matching MATLAB behaviour.
+    """
+    org_id = _resolve_org_id(org_id, client)
+    if not name:
+        raise ValueError("name is required")
     body: dict[str, Any] = {"name": name}
     if description:
         body["description"] = description
@@ -92,15 +112,19 @@ def deleteDataset(
 
 
 @_auto_client
-@validate_call(config=VALIDATE_CONFIG)
 def listDatasets(
-    org_id: NonEmptyStr,
-    page: PageNumber = 1,
-    page_size: PageSize = 1000,
+    org_id: str | None = None,
+    page: int = 1,
+    page_size: int = 1000,
     *,
     client: _Client = None,
 ) -> dict[str, Any]:
-    """GET /organizations/{organizationId}/datasets?page=&pageSize="""
+    """GET /organizations/{organizationId}/datasets?page=&pageSize=
+
+    If *org_id* is omitted it is resolved from the client's config
+    (populated automatically during login), matching MATLAB behaviour.
+    """
+    org_id = _resolve_org_id(org_id, client)
     return client.get(
         "/organizations/{organizationId}/datasets",
         params={"page": page, "pageSize": page_size},
@@ -112,9 +136,13 @@ def listDatasets(
 
 
 @_auto_client
-@validate_call(config=VALIDATE_CONFIG)
-def listAllDatasets(org_id: NonEmptyStr, *, client: _Client = None) -> APIResponse:
-    """Auto-paginate through all datasets for an organisation."""
+def listAllDatasets(org_id: str | None = None, *, client: _Client = None) -> APIResponse:
+    """Auto-paginate through all datasets for an organisation.
+
+    If *org_id* is omitted it is resolved from the client's config
+    (populated automatically during login), matching MATLAB behaviour.
+    """
+    org_id = _resolve_org_id(org_id, client)
     all_datasets: list[dict[str, Any]] = []
     page = 1
     while page <= _MAX_PAGES:

src/ndi/cloud/download.py

@@ -567,7 +567,9 @@ def downloadGenericFiles(
         all_docs = []
         for doc_id in ndi_document_ids:
             q = Query("base.id", "exact_string", doc_id, "")
-            results = ndi_dataset.database_search(q) if hasattr(ndi_dataset, "database_search") else []
+            results = (
+                ndi_dataset.database_search(q) if hasattr(ndi_dataset, "database_search") else []
+            )
             all_docs.extend(results)
 
         if not all_docs:

src/ndi/cloud/internal.py

@@ -288,7 +288,9 @@ def duplicateDocuments(
         for i in range(0, len(doc_ids_to_delete), maximum_delete_batch_size):
             batch = doc_ids_to_delete[i : i + maximum_delete_batch_size]
             batch_num = i // maximum_delete_batch_size + 1
-            total_batches = (len(doc_ids_to_delete) + maximum_delete_batch_size - 1) // maximum_delete_batch_size
+            total_batches = (
+                len(doc_ids_to_delete) + maximum_delete_batch_size - 1
+            ) // maximum_delete_batch_size
             if verbose:
                 print(f"Deleting batch {batch_num} of {total_batches}...")
             try:

src/ndi/cloud/orchestration.py

@@ -377,7 +377,6 @@ def newDataset(
 # Re-export from upload module (MATLAB: ndi.cloud.upload.scanForUpload)
 from .upload import scanForUpload  # noqa: F401
 
-
 # ---------------------------------------------------------------------------
 # Private sync helpers
 # ---------------------------------------------------------------------------

src/ndi/cloud/sync/operations.py

@@ -477,9 +477,7 @@ def twoWaySync(
             failed.append(doc_id)
 
     # 4. Download remote-only docs
-    docs, dl_failed = downloadNdiDocuments(
-        cloud_dataset_id, remote_ids, to_download, client=client
-    )
+    docs, dl_failed = downloadNdiDocuments(cloud_dataset_id, remote_ids, to_download, client=client)
     saved = _save_downloaded_docs(ds_path, docs)
     report["downloaded"] = saved
     failed.extend(dl_failed)

tests/test_cloud_live.py

@@ -207,7 +207,8 @@ def _cleanup_stale_pytest_datasets(client, cloud_config):
         result = listDatasets(cloud_config.org_id, client=client)
         datasets = result.get("datasets", [])
         stale = [
-            ds for ds in datasets
+            ds
+            for ds in datasets
             if ds.get("name", "").startswith("NDI_PYTEST") and ds.get("_id", ds.get("id", ""))
         ]
         if stale: