Test files and documentation

Content

• Creation of data_test directory that contains small dataset to tests different endpoints based on file url:
  • Update README
  • ncbi_taxonomy/taxdump.tar.gz small taxonomy with Escherichia coli and Lactobacillus casei group.
  • No data for KEGG which is quick to create.
  • genes/genes.fa: few genes with random sequences.

backend/app/app/api/endpoints/admin/db.py

@@ -19,6 +19,7 @@ from app.celery.utils import (
     get_task_id,
 )
 from app.db import reinit_db
+from app.core.config import settings
 from app.core.schemas.tasks.base import CreateTask
 from app.core.schemas.tasks.db import TaskDbOperation
 
@@ -51,13 +52,13 @@ def create_kegg_ko():
     response_model=CreateTask,
     status_code=status.HTTP_201_CREATED,
 )
-def create_ncbi_taxonomy():
+def create_ncbi_taxonomy(ncbi_taxdump_tar_url: str = settings.NCBI_TAX_DUMPS_URL):
     task_name = CREATE_NCBI_TAX_TASK_NAME
     if is_running_task(task_name):
         task_id = get_task_id(task_name)
         task_obj = CreateTask(task_status="STARTED", task_id=task_id)
         return JSONResponse(status_code=status.HTTP_200_OK, content=task_obj.dict())
-    task = create_or_update_all_ncbi_tax.delay()
+    task = create_or_update_all_ncbi_tax.delay(ncbi_taxdump_tar_url)
     task_obj = CreateTask(task_status="PENDING", task_id=task.id)
     return task_obj
 
@@ -100,15 +101,16 @@ def create_genes(fasta_url: str, catalog_name: str):
 )
 def get_status(task_id):
     task_result = AsyncResult(task_id)
-    if task_result.failed():
-        result = {
-            "task_id": task_id,
-            "task_status": task_result.status,
-        }
-        return JSONResponse(result)
-    result = TaskDbOperation(
-        task_id=task_id,
-        task_status=task_result.status,
-        task_result=task_result.result,
-    )
+    if task_result.status != "SUCCESS":
+        result = TaskDbOperation(
+            task_id=task_id,
+            task_status=task_result.status,
+            task_result=[],
+        )
+    else:
+        result = TaskDbOperation(
+            task_id=task_id,
+            task_status=task_result.status,
+            task_result=task_result.result,
+        )
     return result