-
Notifications
You must be signed in to change notification settings - Fork 7
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #403 from bento-platform/feat/data-type-counts
Add data type counts & queryable flag to data types
- Loading branch information
Showing
9 changed files
with
274 additions
and
102 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
106 changes: 106 additions & 0 deletions
106
chord_metadata_service/chord/tests/test_api_data_types.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,106 @@ | ||
| from django.urls import reverse | ||
| from rest_framework import status | ||
| from rest_framework.test import APITestCase | ||
|
|
||
| from ..data_types import ( | ||
| DATA_TYPE_EXPERIMENT, | ||
| DATA_TYPE_EXPERIMENT_RESULT, | ||
| DATA_TYPE_PHENOPACKET, | ||
| DATA_TYPE_READSET, | ||
| DATA_TYPES | ||
| ) | ||
| from ..views_data_types import get_count_for_data_type | ||
|
|
||
| POST_GET = ("POST", "GET") | ||
|
|
||
| DATA_TYPE_NOT_REAL = "not_a_real_data_type" | ||
|
|
||
|
|
||
| class DataTypeTest(APITestCase): | ||
| def test_data_type_list(self): | ||
| r = self.client.get(reverse("data-type-list")) | ||
| self.assertEqual(r.status_code, status.HTTP_200_OK) | ||
| c = r.json() | ||
| self.assertEqual(len(c), len(DATA_TYPES)) | ||
| ids = [dt["id"] for dt in c] | ||
| self.assertIn(DATA_TYPE_EXPERIMENT, ids) | ||
| # self.assertIn(DATA_TYPE_MCODEPACKET, ids) | ||
| self.assertIn(DATA_TYPE_PHENOPACKET, ids) | ||
| self.assertIn(DATA_TYPE_READSET, ids) | ||
| self.assertIn(DATA_TYPE_EXPERIMENT_RESULT, ids) | ||
|
|
||
| def test_data_type_list_non_uuid_project(self): | ||
| # Non-UUID project | ||
| r = self.client.get(reverse("data-type-list"), {"project": "a"}) | ||
| self.assertEqual(r.status_code, status.HTTP_400_BAD_REQUEST) | ||
|
|
||
| def test_data_type_list_non_uuid_dataset(self): | ||
| # Non-UUID dataset | ||
| r = self.client.get(reverse("data-type-list"), {"dataset": "a"}) | ||
| self.assertEqual(r.status_code, status.HTTP_400_BAD_REQUEST) | ||
|
|
||
| def test_data_type_detail(self): | ||
| self.maxDiff = None | ||
| r = self.client.get(reverse("data-type-detail", kwargs={"data_type": DATA_TYPE_PHENOPACKET})) | ||
| self.assertEqual(r.status_code, status.HTTP_200_OK) | ||
| c = r.json() | ||
| self.assertDictEqual(c, { | ||
| "id": DATA_TYPE_PHENOPACKET, | ||
| "label": "Clinical Data", | ||
| **DATA_TYPES[DATA_TYPE_PHENOPACKET], | ||
| "queryable": True, | ||
| "count": 0, | ||
| }) | ||
|
|
||
| def test_data_type_detail_non_uuid_project(self): | ||
| # Non-UUID project | ||
| r = self.client.get(reverse("data-type-detail", kwargs={"data_type": DATA_TYPE_PHENOPACKET}), {"project": "a"}) | ||
| self.assertEqual(r.status_code, status.HTTP_400_BAD_REQUEST) | ||
|
|
||
| r = self.client.get( | ||
| reverse("data-type-detail", kwargs={"data_type": DATA_TYPE_EXPERIMENT_RESULT}), {"project": "a"}) | ||
| self.assertEqual(r.status_code, status.HTTP_400_BAD_REQUEST) | ||
|
|
||
| def test_data_type_detail_non_uuid_dataset(self): | ||
| # Non-UUID dataset | ||
| r = self.client.get(reverse("data-type-detail", kwargs={"data_type": DATA_TYPE_PHENOPACKET}), {"dataset": "a"}) | ||
| self.assertEqual(r.status_code, status.HTTP_400_BAD_REQUEST) | ||
|
|
||
| r = self.client.get(reverse( | ||
| "data-type-detail", kwargs={"data_type": DATA_TYPE_EXPERIMENT_RESULT}), {"dataset": "a"}) | ||
| self.assertEqual(r.status_code, status.HTTP_400_BAD_REQUEST) | ||
|
|
||
| def test_data_type_detail_bad_data_type_for_count(self): | ||
| r = self.client.get(reverse("data-type-detail", kwargs={"data_type": DATA_TYPE_READSET})) | ||
| self.assertIsNone(r.json()["count"]) | ||
|
|
||
| async def test_data_type_count_bad_data_type(self): | ||
| with self.assertRaises(ValueError): | ||
| await get_count_for_data_type(DATA_TYPE_NOT_REAL) | ||
|
|
||
| def test_data_type_detail_404(self): | ||
| r = self.client.get(reverse("data-type-detail", kwargs={"data_type": DATA_TYPE_NOT_REAL})) | ||
| self.assertEqual(r.status_code, status.HTTP_404_NOT_FOUND) | ||
| r.json() # assert json response | ||
|
|
||
| def test_data_type_schema(self): | ||
| r = self.client.get(reverse("data-type-schema", kwargs={"data_type": DATA_TYPE_PHENOPACKET})) | ||
| self.assertEqual(r.status_code, status.HTTP_200_OK) | ||
| c = r.json() | ||
| self.assertDictEqual(c, DATA_TYPES[DATA_TYPE_PHENOPACKET]["schema"]) | ||
|
|
||
| def test_data_type_schema_404(self): | ||
| r = self.client.get(reverse("data-type-schema", kwargs={"data_type": DATA_TYPE_NOT_REAL})) | ||
| self.assertEqual(r.status_code, status.HTTP_404_NOT_FOUND) | ||
| r.json() # assert json response | ||
|
|
||
| def test_data_type_metadata_schema(self): | ||
| r = self.client.get(reverse("data-type-metadata-schema", kwargs={"data_type": DATA_TYPE_PHENOPACKET})) | ||
| self.assertEqual(r.status_code, status.HTTP_200_OK) | ||
| c = r.json() | ||
| self.assertDictEqual(c, DATA_TYPES[DATA_TYPE_PHENOPACKET]["metadata_schema"]) | ||
|
|
||
| def test_data_type_metadata_schema_404(self): | ||
| r = self.client.get(reverse("data-type-metadata-schema", kwargs={"data_type": DATA_TYPE_NOT_REAL})) | ||
| self.assertEqual(r.status_code, status.HTTP_404_NOT_FOUND) | ||
| r.json() # assert json response |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,132 @@ | ||
| from bento_lib.responses import errors | ||
| from django.core.exceptions import ValidationError | ||
| from django.db.models import QuerySet | ||
| from django.http import HttpRequest | ||
|
|
||
| from adrf.decorators import api_view | ||
| from rest_framework import status | ||
| from rest_framework.decorators import permission_classes | ||
| from rest_framework.permissions import AllowAny | ||
| from rest_framework.response import Response | ||
|
|
||
| from typing import Optional | ||
|
|
||
| from chord_metadata_service.phenopackets.models import Phenopacket | ||
| from chord_metadata_service.experiments.models import Experiment, ExperimentResult | ||
|
|
||
| from . import data_types as dt | ||
|
|
||
|
|
||
| async def get_count_for_data_type( | ||
| data_type: str, | ||
| project: Optional[str] = None, | ||
| dataset: Optional[str] = None, | ||
| ) -> Optional[int]: | ||
| """ | ||
| Returns the count for a particular data type. If dataset is provided, project will be ignored. If neither are | ||
| provided, the count will be for the whole node. | ||
| """ | ||
|
|
||
| if data_type == dt.DATA_TYPE_READSET: | ||
| # No counts for readset, it's a fake data type inside Katsu... | ||
| return None | ||
|
|
||
| q: Optional[QuerySet] = None | ||
|
|
||
| if data_type in (dt.DATA_TYPE_PHENOPACKET, dt.DATA_TYPE_EXPERIMENT): | ||
| q = (Phenopacket if data_type == dt.DATA_TYPE_PHENOPACKET else Experiment).objects.all() | ||
| if dataset: | ||
| try: | ||
| q = q.filter(table__ownership_record__dataset_id=dataset) | ||
| except ValidationError: | ||
| raise ValueError("Dataset ID must be a UUID") | ||
| elif project: | ||
| try: | ||
| q = q.filter(table__ownership_record__dataset__project_id=project) | ||
| except ValidationError: | ||
| raise ValueError("Project ID must be a UUID") | ||
|
|
||
| elif data_type == dt.DATA_TYPE_EXPERIMENT_RESULT: | ||
| q = ExperimentResult.objects.all() | ||
| if dataset: | ||
| try: | ||
| q = q.filter(experiment__table__ownership_record__dataset_id=dataset) | ||
| except ValidationError: | ||
| raise ValueError("Dataset ID must be a UUID") | ||
| elif project: | ||
| try: | ||
| q = q.filter(experiment__table__ownership_record__dataset__project_id=project) | ||
| except ValidationError: | ||
| raise ValueError("Project ID must be a UUID") | ||
|
|
||
| if q is None: | ||
| raise ValueError(f"Unsupported data type for count function: {data_type}") | ||
|
|
||
| return await q.acount() | ||
|
|
||
|
|
||
| async def make_data_type_response_object( | ||
| data_type_id: str, | ||
| data_type_details: dict, | ||
| project: Optional[str], | ||
| dataset: Optional[str], | ||
| ) -> dict: | ||
| return { | ||
| **data_type_details, | ||
| "id": data_type_id, | ||
| "count": await get_count_for_data_type(data_type_id, project, dataset), | ||
| } | ||
|
|
||
|
|
||
| @api_view(["GET"]) | ||
| @permission_classes([AllowAny]) | ||
| async def data_type_list(request: HttpRequest): | ||
| # TODO: Permissions: only return counts when we are authenticated/have access to counts or full data. | ||
|
|
||
| project = request.GET.get("project", "").strip() or None | ||
| dataset = request.GET.get("dataset", "").strip() or None | ||
|
|
||
| dt_response = [] | ||
| for dt_id, dt_d in dt.DATA_TYPES.items(): | ||
| try: | ||
| dt_response.append(await make_data_type_response_object(dt_id, dt_d, project, dataset)) | ||
| except ValueError as e: | ||
| return Response(errors.bad_request_error(str(e)), status=status.HTTP_400_BAD_REQUEST) | ||
|
|
||
| dt_response.sort(key=lambda d: d["id"]) | ||
| return Response(dt_response) | ||
|
|
||
|
|
||
| @api_view(["GET"]) | ||
| @permission_classes([AllowAny]) | ||
| async def data_type_detail(request: HttpRequest, data_type: str): | ||
| # TODO: Permissions: only return counts when we are authenticated/have access to counts or full data. | ||
|
|
||
| if data_type not in dt.DATA_TYPES: | ||
| return Response(errors.not_found_error(f"Date type {data_type} not found"), status=status.HTTP_404_NOT_FOUND) | ||
|
|
||
| project = request.GET.get("project", "").strip() or None | ||
| dataset = request.GET.get("dataset", "").strip() or None | ||
|
|
||
| try: | ||
| return Response(await make_data_type_response_object(data_type, dt.DATA_TYPES[data_type], project, dataset)) | ||
| except ValueError as e: | ||
| return Response(errors.bad_request_error(str(e)), status=status.HTTP_400_BAD_REQUEST) | ||
|
|
||
|
|
||
| @api_view(["GET"]) | ||
| @permission_classes([AllowAny]) | ||
| async def data_type_schema(_request: HttpRequest, data_type: str): | ||
| if data_type not in dt.DATA_TYPES: | ||
| return Response(errors.not_found_error(f"Date type {data_type} not found"), status=status.HTTP_404_NOT_FOUND) | ||
|
|
||
| return Response(dt.DATA_TYPES[data_type]["schema"]) | ||
|
|
||
|
|
||
| @api_view(["GET"]) | ||
| @permission_classes([AllowAny]) | ||
| async def data_type_metadata_schema(_request: HttpRequest, data_type: str): | ||
| if data_type not in dt.DATA_TYPES: | ||
| return Response(errors.not_found_error(f"Date type {data_type} not found"), status=status.HTTP_404_NOT_FOUND) | ||
|
|
||
| return Response(dt.DATA_TYPES[data_type]["metadata_schema"]) |
Oops, something went wrong.