Pass work type of dataset as expected by frontend (#13)

.devcontainer/.dev_config.yaml

@@ -14,7 +14,7 @@ db_name: "dev-db"
 service_instance_id: 001
 kafka_servers: ["kafka:9092"]
 
-download_access_url: "http://127.0.0.1:8080/download_access"
+download_access_url: "http://127.0.0.1:8080/download-access"
 
 dataset_overview_event_topic: metadata
 dataset_overview_event_type: metadata_dataset_overview

README.md

@@ -52,21 +52,21 @@ We recommend using the provided Docker container.
 
 A pre-build version is available at [docker hub](https://hub.docker.com/repository/docker/ghga/work-package-service):
 ```bash
-docker pull ghga/work-package-service:0.1.2
+docker pull ghga/work-package-service:0.1.3
 ```
 
 Or you can build the container yourself from the [`./Dockerfile`](./Dockerfile):
 ```bash
 # Execute in the repo's root dir:
-docker build -t ghga/work-package-service:0.1.2 .
+docker build -t ghga/work-package-service:0.1.3 .
 ```
 
 For production-ready deployment, we recommend using Kubernetes, however,
 for simple use cases, you could execute the service using docker
 on a single server:
 ```bash
 # The entrypoint is preconfigured:
-docker run -p 8080:8080 ghga/work-package-service:0.1.2 --help
+docker run -p 8080:8080 ghga/work-package-service:0.1.3 --help
 ```
 
 If you prefer not to use containers, you may install the service from source:

config_schema.json

@@ -112,7 +112,7 @@
     "download_access_url": {
       "title": "Download Access Url",
       "description": "URL pointing to the internal download access API.",
-      "example": "http://127.0.0.1/download_access",
+      "example": "http://127.0.0.1/download-access",
       "env_names": [
         "wps_download_access_url"
       ],

example_config.yaml

@@ -19,7 +19,7 @@ datasets_collection: datasets
 db_connection_str: '**********'
 db_name: dev-db
 docs_url: /docs
-download_access_url: http://127.0.0.1:8080/download_access
+download_access_url: http://127.0.0.1:8080/download-access
 host: 127.0.0.1
 kafka_servers:
 - kafka:9092

openapi.yaml

@@ -18,12 +18,17 @@ components:
           description: ID of the dataset
           title: Id
           type: string
+        stage:
+          allOf:
+          - $ref: '#/components/schemas/WorkType'
+          description: Current stage of this dataset.
         title:
           description: The title of the dataset.
           title: Title
           type: string
       required:
       - id
+      - stage
       - title
       - description
       - files
@@ -133,7 +138,7 @@ components:
 info:
   description: A service managing work packages for the GHGA CLI
   title: Work Package Service
-  version: 0.1.2
+  version: 0.1.3
 openapi: 3.0.2
 paths:
   /health:

setup.cfg

@@ -36,7 +36,7 @@ include_package_data = True
 packages = find:
 install_requires =
     ghga-service-commons[api,auth,crypt]==0.4.1
-    ghga-event-schemas==0.13.1
+    ghga-event-schemas==0.13.2
     hexkit[akafka,mongodb]==0.10.0
     httpx==0.23.3
     typer==0.7.0

tests/fixtures/datasets.py

@@ -16,16 +16,21 @@
 
 """Sample datasets for testing."""
 
-from ghga_event_schemas.pydantic_ import MetadataDatasetFile, MetadataDatasetOverview
+from ghga_event_schemas.pydantic_ import (
+    MetadataDatasetFile,
+    MetadataDatasetOverview,
+    MetadataDatasetStage,
+)
 
-from wps.core.models import Dataset, DatasetFile
+from wps.core.models import Dataset, DatasetFile, WorkType
 
 __all__ = ["DATASET", "DATASET_OVERVIEW_EVENT"]
 
 
 DATASET = Dataset(
     id="some-dataset-id",
     title="Test dataset 1",
+    stage=WorkType.DOWNLOAD,
     description="The first test dataset",
     files=[
         DatasetFile(id="file-id-1", extension=".json"),
@@ -37,6 +42,7 @@
 
 DATASET_OVERVIEW_EVENT = MetadataDatasetOverview(
     accession="some-dataset-id",
+    stage=MetadataDatasetStage.DOWNLOAD,
     title="Test dataset 1",
     description="The first test dataset",
     files=[

wps/__init__.py

@@ -15,4 +15,4 @@
 
 """Work Package Service"""
 
-__version__ = "0.1.2"
+__version__ = "0.1.3"

wps/adapters/inbound/event_sub.py

@@ -22,7 +22,7 @@
 from hexkit.protocols.eventsub import EventSubscriberProtocol
 from pydantic import BaseSettings, Field
 
-from wps.core.models import Dataset, DatasetFile
+from wps.core.models import Dataset, DatasetFile, WorkType
 from wps.ports.inbound.repository import WorkPackageRepositoryPort
 
 __all__ = ["EventSubTranslatorConfig", "EventSubTranslator"]
@@ -77,6 +77,11 @@ async def _consume_validated(  # pylint: disable=unused-argument
             payload=payload,
             schema=event_schemas.MetadataDatasetOverview,
         )
+        try:
+            stage = WorkType[validated_payload.stage.name]
+        except KeyError:
+            # stage does not correspond to a work type, ignore event
+            return
 
         files = [
             DatasetFile(
@@ -89,6 +94,7 @@ async def _consume_validated(  # pylint: disable=unused-argument
         dataset = Dataset(
             id=validated_payload.accession,
             title=validated_payload.title,
+            stage=stage,
             description=validated_payload.description,
             files=files,
         )

wps/adapters/outbound/http.py

@@ -34,7 +34,7 @@ class AccessCheckConfig(BaseSettings):
 
     download_access_url: str = Field(
         ...,
-        example="http://127.0.0.1/download_access",
+        example="http://127.0.0.1/download-access",
         description="URL pointing to the internal download access API.",
     )
 

wps/core/models.py

@@ -42,6 +42,13 @@ class Config:  # pylint: disable=missing-class-docstring
         frozen = True
 
 
+class WorkType(str, Enum):
+    """The type of work that a work package describes."""
+
+    DOWNLOAD = "download"
+    UPLOAD = "upload"
+
+
 class DatasetFile(BaseDto):
     """A file as that is part of a dataset."""
 
@@ -53,20 +60,14 @@ class Dataset(BaseDto):
     """A model describing a dataset."""
 
     id: str = Field(default=..., description="ID of the dataset")
+    stage: WorkType = Field(default=..., description="Current stage of this dataset.")
     title: str = Field(default=..., description="The title of the dataset.")
     description: Optional[str] = Field(
         ..., description="The description of the dataset."
     )
     files: list[DatasetFile] = Field(..., description="Files contained in the dataset.")
 
 
-class WorkType(str, Enum):
-    """The type of work that a work package describes."""
-
-    DOWNLOAD = "download"
-    UPLOAD = "upload"
-
-
 class WorkOrderToken(BaseDto):
     """A model describing the payload of a work order token."""
 

wps/core/repository.py

@@ -237,16 +237,13 @@ async def work_order_token(
 
     async def register_dataset(self, dataset: Dataset) -> None:
         """Register a dataset with all of its files."""
-        # write the dataset to the database
-        await self._dataset_dao.insert(dataset)
-        # await self._dataset_dao.upsert(dataset)
+        await self._dataset_dao.upsert(dataset)
 
     async def get_dataset(self, dataset_id: str) -> Dataset:
         """Get a registered dataset using the given ID.
 
         If the dataset does not exist, a DatasetNotFoundError will be raised.
         """
-        # get the dataset from the database
         try:
             return await self._dataset_dao.get_by_id(dataset_id)
         except ResourceNotFoundError as error: