Implement API endpoints for creating and retrieving JGISequencingProjects

nmdc_runtime/api/endpoints/wf_file_staging.py

@@ -1,7 +1,6 @@
-from fastapi import APIRouter, Depends
+from fastapi import APIRouter, Depends, Query
 from pymongo.database import Database
 from typing import Annotated
-from fastapi import APIRouter, Depends, Query
 from toolz import merge
 import logging
 
@@ -16,8 +15,9 @@
     GlobusTaskStatus,
     JDPFileStatus,
     JGISample,
+    JGISequencingProject,
+    WorkflowFileStagingCollectionName as CollectionName,
 )
-from nmdc_runtime.api.models.user import User
 from nmdc_runtime.api.endpoints.util import check_action_permitted
 
 router = APIRouter()
@@ -44,6 +44,8 @@ def create_globus_tasks(
     mdb: Database = Depends(get_mongo_db),
     user: User = Depends(get_current_active_user),
 ):
+    """Create a `GlobusTask`."""
+
     # check for permissions first
     check_can_run_wf_file_staging_endpoints(user)
     # check if record with same task_id already exists
@@ -72,6 +74,8 @@ def get_globus_tasks(
     mdb: Database = Depends(get_mongo_db),
     user: User = Depends(get_current_active_user),
 ):
+    """Retrieve a `GlobusTask`."""
+
     # check for permissions first
     check_can_run_wf_file_staging_endpoints(user)
     return raise404_if_none(
@@ -86,6 +90,8 @@ def update_globus_tasks(
     mdb: Database = Depends(get_mongo_db),
     user: User = Depends(get_current_active_user),
 ):
+    """Update a `GlobusTask`."""
+
     # check for permissions first
     check_can_run_wf_file_staging_endpoints(user)
 
@@ -116,6 +122,7 @@ def list_globus_tasks(
     user: User = Depends(get_current_active_user),
 ):
     """Get a list of `GlobusTask`s."""
+
     # check for permissions first
     check_can_run_wf_file_staging_endpoints(user)
     rv = list_resources(req, mdb, "wf_file_staging.globus_tasks")
@@ -220,3 +227,68 @@ def update_jgi_samples(
         {"jdp_file_id": jdp_file_id}, doc_jgi_sample_patched
     )
     return doc_jgi_sample_patched
+
+
+@router.get(
+    "/wf_file_staging/jgi_sequencing_projects",
+    response_model=ListResponse[JGISequencingProject],
+    response_model_exclude_unset=True,
+)
+def list_sequencing_project_records(
+    req: Annotated[ListRequest, Query()],
+    mdb: Database = Depends(get_mongo_db),
+    user: User = Depends(get_current_active_user),
+):
+    """Get a list of `JGISequencingProject`s."""
+
+    check_can_run_wf_file_staging_endpoints(user)
+
+    return list_resources(req, mdb, CollectionName.JGI_SEQUENCING_PROJECTS.value)
+
+
+@router.post(
+    "/wf_file_staging/jgi_sequencing_projects",
+    status_code=status.HTTP_201_CREATED,
+    response_model=JGISequencingProject,
+)
+def create_sequencing_record(
+    sequencing_project_in: JGISequencingProject,
+    mdb: Database = Depends(get_mongo_db),
+    user: User = Depends(get_current_active_user),
+):
+    """Create a `JGISequencingProject`."""
+
+    check_can_run_wf_file_staging_endpoints(user)
+    existing = mdb[CollectionName.JGI_SEQUENCING_PROJECTS.value].find_one(
+        {"sequencing_project_name": sequencing_project_in.sequencing_project_name}
+    )
+    if existing is not None:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=f"JGISequencingProject with project name {sequencing_project_in.sequencing_project_name} already exists.",
+        )
+    sequencing_project_dict = sequencing_project_in.model_dump()
+    mdb[CollectionName.JGI_SEQUENCING_PROJECTS.value].insert_one(
+        sequencing_project_dict
+    )
+    return sequencing_project_dict
+
+
+@router.get(
+    "/wf_file_staging/jgi_sequencing_projects/{sequencing_project_name}",
+    response_model=JGISequencingProject,
+)
+def get_sequencing_project(
+    sequencing_project_name: str,
+    mdb: Database = Depends(get_mongo_db),
+    user: User = Depends(get_current_active_user),
+):
+    """Retrieve a `JGISequencingProject`."""
+
+    check_can_run_wf_file_staging_endpoints(user)
+
+    return raise404_if_none(
+        mdb[CollectionName.JGI_SEQUENCING_PROJECTS.value].find_one(
+            {"sequencing_project_name": sequencing_project_name}
+        )
+    )

nmdc_runtime/api/main.py

@@ -17,7 +17,7 @@
 from starlette.responses import RedirectResponse, HTMLResponse, FileResponse
 from refscan.lib.helpers import get_collection_names_from_schema
 from scalar_fastapi import get_scalar_api_reference
-
+from nmdc_runtime.api.models.wfe_file_stages import WorkflowFileStagingCollectionName
 from nmdc_runtime import config
 from nmdc_runtime.api.analytics import Analytics
 from nmdc_runtime.api.middleware import PyinstrumentMiddleware
@@ -202,6 +202,17 @@ def ensure_jgi_samples_id_is_indexed():
     )
 
 
+def ensure_sequencing_project_name_is_indexed():
+    """
+    Ensures that the `wf_file_staging.sequencing_projects` collection has an index on its `sequencing_project_name` field and that the index is unique.
+    """
+
+    mdb = get_mongo_db()
+    mdb[WorkflowFileStagingCollectionName.JGI_SEQUENCING_PROJECTS.value].create_index(
+        "sequencing_project_name", background=True, unique=True
+    )
+
+
 def ensure_default_api_perms():
     """
     Ensures that specific users (currently only "admin") are allowed to perform
@@ -255,6 +266,7 @@ async def lifespan(app: FastAPI):
     ensure_type_field_is_indexed()
     ensure_default_api_perms()
     ensure_globus_tasks_id_is_indexed()
+    ensure_sequencing_project_name_is_indexed()
     # Invoke a function—thereby priming its memoization cache—in order to speed up all future invocations.
     get_allowed_references()  # we ignore the return value here
 

nmdc_runtime/api/models/wfe_file_stages.py

@@ -4,6 +4,12 @@
 import datetime
 
 
+class WorkflowFileStagingCollectionName(str, Enum):
+    """The name of a MongoDB collection related to workflow file staging."""
+
+    JGI_SEQUENCING_PROJECTS = "wf_file_staging.jgi_sequencing_projects"
+
+
 class GlobusTaskStatus(str, Enum):
     ACTIVE = "ACTIVE"
     INACTIVE = "INACTIVE"
@@ -91,3 +97,26 @@ class JGISample(BaseModel):
         description="Request ID from the JGI data portal after a request to have the files restored from tape is submitted.",
         examples=[1],
     )
+
+
+class JGISequencingProject(BaseModel):
+    """
+    A representation of a JGI sequencing project and its associated metadata.
+    """
+
+    sequencing_project_name: str = Field(
+        ...,
+        description="Name of the sequencing project that we can refer to while staging files.",
+        examples=["Human Genome Project"],
+    )
+    sequencing_project_description: str = Field(
+        ...,
+        description="Detailed description of the sequencing project",
+        examples=["A project to sequence the human genome."],
+    )
+    jgi_proposal_id: str = Field(
+        ..., description="JGI proposal ID", examples=["503568"]
+    )
+    nmdc_study_id: str = Field(
+        ..., description="NMDC study ID", examples=["nmdc:sty-11-28tm5d36"]
+    )

tests/lib/faker.py

@@ -20,7 +20,7 @@
 )
 
 from nmdc_runtime.api.models.job import Job
-from nmdc_runtime.api.models.wfe_file_stages import GlobusTask, GlobusTaskStatus, JGISample
+from nmdc_runtime.api.models.wfe_file_stages import GlobusTask, GlobusTaskStatus, JGISample, JGISequencingProject
 
 class Faker:
     r"""
@@ -342,6 +342,7 @@ def generate_nucleotide_sequencings(self, quantity: int, associated_studies: Lis
 
         return documents
 
+
     def generate_data_objects(self, quantity: int, **overrides) -> List[dict]:
         """
         Generates the specified number of documents representing `DataObject` instances,
@@ -399,6 +400,7 @@ def generate_data_objects(self, quantity: int, **overrides) -> List[dict]:
 
         return documents
 
+
     def generate_workflow_executions(self, quantity: int, workflow_type: str, was_informed_by: List[str], has_input: List[str], **overrides) -> List[dict]:
         """
         Generates the specified number of documents representing generic workflow execution instances,
@@ -478,7 +480,8 @@ def generate_workflow_executions(self, quantity: int, workflow_type: str, was_in
             documents.append(document)
 
         return documents
-
+
+
     def generate_globus_tasks(self, quantity: int, **overrides) -> List[dict]:
         """
         Generates the specified number of documents representing `GlobusTask` instances,
@@ -515,6 +518,7 @@ class defined locally, in the `nmdc_runtime.api.models` module.
 
         return documents
 
+
     def generate_jgi_samples(self, quantity: int, **overrides) -> List[dict]:
         """
         Generates the specified number of documents representing `JGISample` instances,
@@ -563,7 +567,47 @@ class defined locally, in the `nmdc_runtime.api.models` module.
             documents.append(document)
 
         return documents
-
+
+
+    def generate_sequencing_projects(self, quantity: int, **overrides) -> List[dict]:
+        """
+        Generates the specified number of documents representing `SequencingProject` instances,
+        which can be stored in the `sequencing_project` collection.
+
+        Note: The `SequencingProject` class is NOT defined in the NMDC Schema. It is an ad hoc
+              class defined locally, in the `nmdc_runtime.api.models` module.
+
+        :param quantity: Number of documents to create
+        :param overrides: Fields, if any, to add or override in each document
+        :return: The generated documents
+
+        >>> f = Faker()
+        >>> sequencing_projects = f.generate_sequencing_projects(1)
+        >>> len(sequencing_projects)
+        1
+        >>> isinstance(sequencing_projects[0]['sequencing_project_name'], str)
+        True
+        """
+        documents = []
+        for i in range(quantity):
+            # Apply any overrides passed in.
+            params = {
+                "sequencing_project_name": f"arbitrary_string-{i+1}",
+                "sequencing_project_description": "arbitrary_string",
+                "jgi_proposal_id": "arbitrary_string",
+                "nmdc_study_id": "arbitrary_string",
+                **overrides,
+            }
+            # Validate the parameters by attempting to instantiate a `SequencingProject`.
+            instance = JGISequencingProject(**params)
+
+            # Dump the instance to a `dict`
+            document = instance.model_dump()
+            documents.append(document)
+
+        return documents
+
+
     def generate_jobs(self, quantity: int, **overrides) -> List[dict]:
         """
         Generates the specified number of documents representing `Job` instances,