[PRMP-631] Bulk Upload E2e Tests

.gitignore

@@ -108,4 +108,4 @@ lambdas/tests/e2e/apim/*.pdf
 
 tests/bulk-upload/output/**
 tests/bulk-upload/test_patients_data/**
-tests/bulk-upload/scripts/scenario_report.txt
+tests/bulk-upload/scripts/scenario_report.txt

Makefile

@@ -104,11 +104,25 @@ else
 	cd ./lambdas && ./venv/bin/python3 -m pytest tests/e2e/api --ignore=tests/e2e/api/fhir --snapshot-update
 endif
 
+initiate-bulk-upload:
+ifeq ($(CONTAINER), true)
+	cd ./lambdas && PYTHONPATH=. poetry run pytest tests/e2e/bulk_upload/upload -vv
+else
+	cd ./lambdas && ./venv/bin/python3 -m pytest tests/e2e/bulk_upload/upload -vv
+endif
+
 test-bulk-upload-e2e:
 ifeq ($(CONTAINER), true)
-	cd ./lambdas && PYTHONPATH=. poetry run pytest tests/e2e/bulk_upload -vv
+	cd ./lambdas && PYTHONPATH=. poetry run pytest tests/e2e/bulk_upload/check -vv
+else
+	cd ./lambdas && ./venv/bin/python3 -m pytest tests/e2e/bulk_upload/check -vv
+endif
+
+test-bulk-upload-e2e-snapshots:
+ifeq ($(CONTAINER), true)
+	cd ./lambdas && PYTHONPATH=. poetry run pytest tests/e2e/bulk_upload/check --snapshot-update
 else
-	cd ./lambdas && ./venv/bin/python3 -m pytest tests/e2e/bulk_upload -vv
+	cd ./lambdas && ./venv/bin/python3 -m pytest tests/e2e/bulk_upload/check --snapshot-update
 endif
 
 test-unit:

lambdas/tests/e2e/api/fhir/conftest.py

@@ -7,7 +7,7 @@
 import pytest
 import requests
 
-from lambdas.tests.e2e.helpers.data_helper import PdmDataHelper
+from tests.e2e.helpers.data_helper import PdmDataHelper
 
 pdm_data_helper = PdmDataHelper()
 
@@ -27,9 +27,7 @@ def test_data():
         pdm_data_helper.tidyup(record)
 
 
-def fetch_with_retry_mtls(
-    session, url, headers, condition_func=None, max_retries=5, delay=10
-):
+def fetch_with_retry_mtls(session, url, headers, condition_func=None, max_retries=5, delay=10):
     retries = 0
     while retries < max_retries:
         response = session.get(url, headers=headers)
@@ -47,9 +45,7 @@ def fetch_with_retry_mtls(
     raise Exception("Condition not met within retry limit")
 
 
-def create_mtls_session(
-    client_cert_path=CLIENT_CERT_PATH, client_key_path=CLIENT_KEY_PATH
-):
+def create_mtls_session(client_cert_path=CLIENT_CERT_PATH, client_key_path=CLIENT_KEY_PATH):
     session = requests.Session()
     session.cert = (client_cert_path, client_key_path)
     return session
@@ -111,9 +107,7 @@ def create_and_store_pdm_record(
     size: int | None = None,
 ):
     """Helper to create metadata and resource for a record."""
-    record = pdm_data_helper.build_record(
-        nhs_number=nhs_number, doc_status=doc_status, size=size
-    )
+    record = pdm_data_helper.build_record(nhs_number=nhs_number, doc_status=doc_status, size=size)
     test_data.append(record)
     pdm_data_helper.create_metadata(record)
     pdm_data_helper.create_resource(record)

lambdas/tests/e2e/api/fhir/test_mtls_routing.py

@@ -1,17 +1,15 @@
 import os
 import uuid
 
-from lambdas.tests.e2e.api.fhir.conftest import get_pdm_document_reference
+from tests.e2e.api.fhir.conftest import get_pdm_document_reference
 
 UNAUTHORISED_CLIENT_CERT_PATH = os.environ.get("UNAUTHORISED_CLIENT_CERT_PATH")
 UNAUTHORISED_CLIENT_KEY_PATH = os.environ.get("UNAUTHORISED_CLIENT_KEY_PATH")
 
 
 def test_mtls_invalid_common_name():
     record_id = str(uuid.uuid4())
-    response = get_pdm_document_reference(
-        record_id, UNAUTHORISED_CLIENT_CERT_PATH, UNAUTHORISED_CLIENT_KEY_PATH
-    )
+    response = get_pdm_document_reference(record_id, UNAUTHORISED_CLIENT_CERT_PATH, UNAUTHORISED_CLIENT_KEY_PATH)
     assert response.status_code == 400
 
     data = response.json()

lambdas/tests/e2e/api/fhir/test_retrieve_document_fhir_api.py

@@ -2,23 +2,21 @@
 import uuid
 
 import pytest
-from tests.e2e.helpers.data_helper import PdmDataHelper
 
-from lambdas.tests.e2e.api.fhir.conftest import (
+from tests.e2e.api.fhir.conftest import (
     PDM_S3_BUCKET,
     create_and_store_pdm_record,
     get_pdm_document_reference,
 )
+from tests.e2e.helpers.data_helper import PdmDataHelper
 
 pdm_data_helper = PdmDataHelper()
 
 
 @pytest.mark.parametrize("file_size", [None, 10 * 1024 * 1024])
 def test_file_retrieval(test_data, file_size):
     """Test retrieval for small and large files."""
-    pdm_record = create_and_store_pdm_record(
-        test_data, size=file_size if file_size else None
-    )
+    pdm_record = create_and_store_pdm_record(test_data, size=file_size if file_size else None)
     response = get_pdm_document_reference(pdm_record["id"])
     assert response.status_code == 200
 
@@ -30,10 +28,7 @@ def test_file_retrieval(test_data, file_size):
         expected_bytes = b"Sample PDF Content"
         assert decoded_data == expected_bytes
     else:
-        expected_presign_uri = (
-            f"https://{PDM_S3_BUCKET}.s3.eu-west-2.amazonaws.com/"
-            f"{pdm_record['nhs_number']}/{pdm_record['id']}"
-        )
+        expected_presign_uri = f"https://{PDM_S3_BUCKET}.s3.eu-west-2.amazonaws.com/{pdm_record['nhs_number']}/{pdm_record['id']}"
         assert expected_presign_uri in json["content"][0]["attachment"]["url"]
 
 
@@ -43,9 +38,7 @@ def test_file_retrieval(test_data, file_size):
         (str(uuid.uuid4()), 404, "RESOURCE_NOT_FOUND", "Document reference not found"),
     ],
 )
-def test_retrieve_edge_cases(
-    record_id, expected_status, expected_code, expected_diagnostics
-):
+def test_retrieve_edge_cases(record_id, expected_status, expected_code, expected_diagnostics):
     response = get_pdm_document_reference(record_id)
     assert response.status_code == expected_status
 
@@ -75,9 +68,7 @@ def test_forbidden_with_invalid_cert(test_data, temp_cert_and_key):
     # Use an invalid cert that is trusted by TLS but fails truststore validation
     cert_path, key_path = temp_cert_and_key
 
-    response = get_pdm_document_reference(
-        pdm_record["id"], client_cert_path=cert_path, client_key_path=key_path
-    )
+    response = get_pdm_document_reference(pdm_record["id"], client_cert_path=cert_path, client_key_path=key_path)
 
     body = response.json()
     assert response.status_code == 403

lambdas/tests/e2e/api/fhir/test_search_patient_fhir_api.py

@@ -1,23 +1,20 @@
 import pytest
 
-from lambdas.tests.e2e.api.fhir.conftest import (
+from tests.e2e.api.fhir.conftest import (
     MTLS_ENDPOINT,
     PDM_SNOMED,
     create_and_store_pdm_record,
     create_mtls_session,
 )
-from lambdas.tests.e2e.conftest import APIM_ENDPOINT
-from lambdas.tests.e2e.helpers.data_helper import PdmDataHelper
+from tests.e2e.conftest import APIM_ENDPOINT
+from tests.e2e.helpers.data_helper import PdmDataHelper
 
 pdm_data_helper = PdmDataHelper()
 
 
 def search_document_reference(nhs_number, client_cert_path=None, client_key_path=None):
     """Helper to perform search by NHS number with optional mTLS certs."""
-    url = (
-        f"https://{MTLS_ENDPOINT}/DocumentReference?"
-        f"subject:identifier=https://fhir.nhs.uk/Id/nhs-number|{nhs_number}"
-    )
+    url = f"https://{MTLS_ENDPOINT}/DocumentReference?subject:identifier=https://fhir.nhs.uk/Id/nhs-number|{nhs_number}"
     headers = {
         "X-Correlation-Id": "1234",
     }
@@ -56,11 +53,7 @@ def test_search_patient_details(test_data):
 
     # Find the entry with the matching record_id
     matching_entry = next(
-        (
-            e
-            for e in entries
-            if e["resource"].get("id") == f"{PDM_SNOMED}~{expected_record_id}"
-        ),
+        (e for e in entries if e["resource"].get("id") == f"{PDM_SNOMED}~{expected_record_id}"),
         None,
     )
     assert matching_entry
@@ -73,10 +66,7 @@ def test_search_patient_details(test_data):
 
 
 def test_multiple_cancelled_search_patient_details(test_data):
-    record_ids = [
-        create_and_store_pdm_record(test_data, doc_status="cancelled")["id"]
-        for _ in range(2)
-    ]
+    record_ids = [create_and_store_pdm_record(test_data, doc_status="cancelled")["id"] for _ in range(2)]
 
     response = search_document_reference("9912003071")
     assert response.status_code == 200
@@ -88,11 +78,7 @@ def test_multiple_cancelled_search_patient_details(test_data):
     # Validate all created records exist and have status cancelled
     for record_id in record_ids:
         entry = next(
-            (
-                e
-                for e in entries
-                if e["resource"].get("id") == f"{PDM_SNOMED}~{record_id}"
-            ),
+            (e for e in entries if e["resource"].get("id") == f"{PDM_SNOMED}~{record_id}"),
             None,
         )
         assert entry
@@ -106,9 +92,7 @@ def test_multiple_cancelled_search_patient_details(test_data):
         ("123", 400, "INVALID_SEARCH_DATA", "Invalid patient number 123"),
     ],
 )
-def test_search_edge_cases(
-    nhs_number, expected_status, expected_code, expected_diagnostics
-):
+def test_search_edge_cases(nhs_number, expected_status, expected_code, expected_diagnostics):
     response = search_document_reference(nhs_number)
     assert response.status_code == expected_status
 
@@ -127,9 +111,7 @@ def test_search_patient_unauthorized_mtls(test_data, temp_cert_and_key):
     # Use an invalid cert that is trusted by TLS but fails truststore validation
     cert_path, key_path = temp_cert_and_key
 
-    response = search_document_reference(
-        "9912003071", client_cert_path=cert_path, client_key_path=key_path
-    )
+    response = search_document_reference("9912003071", client_cert_path=cert_path, client_key_path=key_path)
 
     body = response.json()
     assert response.status_code == 403

lambdas/tests/e2e/api/fhir/test_upload_document_fhir_api_failure.py

@@ -6,12 +6,12 @@
 import pytest
 import requests
 
-from lambdas.tests.e2e.api.fhir.conftest import (
+from tests.e2e.api.fhir.conftest import (
     MTLS_ENDPOINT,
     create_mtls_session,
     fetch_with_retry_mtls,
 )
-from lambdas.tests.e2e.helpers.data_helper import PdmDataHelper
+from tests.e2e.helpers.data_helper import PdmDataHelper
 
 pdm_data_helper = PdmDataHelper()
 
@@ -59,9 +59,7 @@ def test_create_document_virus(test_data):
     }
 
     # Attach EICAR data
-    eicar_string = (
-        r"X5O!P%@AP[4\PZX54(P^)7CC)7}$EICAR-STANDARD-ANTIVIRUS-TEST-FILE!$H+H*"
-    )
+    eicar_string = r"X5O!P%@AP[4\PZX54(P^)7CC)7}$EICAR-STANDARD-ANTIVIRUS-TEST-FILE!$H+H*"
     record["data"] = base64.b64encode(eicar_string.encode()).decode()
     payload = pdm_data_helper.create_upload_payload(record)
 
@@ -79,9 +77,7 @@ def condition(response_json):
             "final",
         )
 
-    raw_retrieve_response = retrieve_document_with_retry(
-        upload_response["id"], condition
-    )
+    raw_retrieve_response = retrieve_document_with_retry(upload_response["id"], condition)
     retrieve_response = raw_retrieve_response.json()
 
     assert retrieve_response["docStatus"] == "cancelled"
@@ -104,9 +100,7 @@ def condition(response_json):
         ),
     ],
 )
-def test_search_edge_cases(
-    nhs_number, expected_status, expected_code, expected_diagnostics
-):
+def test_search_edge_cases(nhs_number, expected_status, expected_code, expected_diagnostics):
     record = {
         "ods": "H81109",
         "nhs_number": f"{nhs_number}",
@@ -143,9 +137,7 @@ def test_forbidden_with_invalid_cert(temp_cert_and_key):
     url = f"https://{MTLS_ENDPOINT}/DocumentReference"
     headers = {"Authorization": "Bearer 123", "X-Correlation-Id": "1234"}
 
-    response = requests.post(
-        url, headers=headers, cert=(cert_path, key_path), data=payload
-    )
+    response = requests.post(url, headers=headers, cert=(cert_path, key_path), data=payload)
     body = response.json()
     assert response.status_code == 403
     assert body["message"] == "Forbidden"
@@ -172,6 +164,4 @@ def test_create_document_with_invalid_author_returns_error(test_data, author_pay
     response_json = raw_upload_response.json()
     assert raw_upload_response.status_code == 400
     assert response_json["resourceType"] == "OperationOutcome"
-    assert (
-        response_json["issue"][0]["details"]["coding"][0]["code"] == "VALIDATION_ERROR"
-    )
+    assert response_json["issue"][0]["details"]["coding"][0]["code"] == "VALIDATION_ERROR"

lambdas/tests/e2e/api/fhir/test_upload_document_fhir_api_success.py

@@ -2,14 +2,14 @@
 import logging
 import os
 
-from lambdas.tests.e2e.api.fhir.conftest import (
+from tests.e2e.api.fhir.conftest import (
     MTLS_ENDPOINT,
     PDM_SNOMED,
     create_mtls_session,
     fetch_with_retry_mtls,
 )
-from lambdas.tests.e2e.conftest import APIM_ENDPOINT
-from lambdas.tests.e2e.helpers.data_helper import PdmDataHelper
+from tests.e2e.conftest import APIM_ENDPOINT
+from tests.e2e.helpers.data_helper import PdmDataHelper
 
 pdm_data_helper = PdmDataHelper()
 
@@ -53,18 +53,13 @@ def test_create_document_base64(test_data):
     # Validate attachment URL
     upload_response = raw_upload_response.json()
     attachment_url = upload_response["content"][0]["attachment"]["url"]
-    assert (
-        f"https://{APIM_ENDPOINT}/national-document-repository/FHIR/R4/DocumentReference/{PDM_SNOMED}~"
-        in attachment_url
-    )
+    assert f"https://{APIM_ENDPOINT}/national-document-repository/FHIR/R4/DocumentReference/{PDM_SNOMED}~" in attachment_url
 
     def condition(response_json):
         logging.info(response_json)
         return response_json["content"][0]["attachment"].get("data", False)
 
-    raw_retrieve_response = retrieve_document_with_retry(
-        upload_response["id"], condition
-    )
+    raw_retrieve_response = retrieve_document_with_retry(upload_response["id"], condition)
     retrieve_response = raw_retrieve_response.json()
 
     # Validate base64 data
@@ -105,9 +100,7 @@ def test_create_document_without_author_or_type(test_data):
     sample_pdf_path = os.path.join(os.path.dirname(__file__), "files", "dummy.pdf")
     with open(sample_pdf_path, "rb") as f:
         record["data"] = base64.b64encode(f.read()).decode("utf-8")
-    payload = pdm_data_helper.create_upload_payload(
-        record=record, exclude=["type", "author"]
-    )
+    payload = pdm_data_helper.create_upload_payload(record=record, exclude=["type", "author"])
 
     for field in ["type", "author"]:
         assert field not in payload

lambdas/tests/e2e/api/test_login_api.py

@@ -1,15 +1,14 @@
 import pytest
+
 from tests.e2e.helpers.data_helper import LloydGeorgeDataHelper
-from tests.e2e.helpers.lloyd_george_mockcis2_helper import LloydGeorgeMockcis2Helper
+from tests.e2e.helpers.mockcis2_helper import MockCis2Helper
 
 # Note this is testing a mock, but this test is valuable to ensure the login code is working for other tests
 
 data_helper = LloydGeorgeDataHelper()
 
 
-@pytest.mark.skipif(
-    data_helper.workspace == "pre-prod", reason="CIS2 login is not mocked in pre-prod"
-)
+@pytest.mark.skipif(data_helper.workspace == "pre-prod", reason="CIS2 login is not mocked in pre-prod")
 @pytest.mark.parametrize(
     "ods_code, role_to_assume, expected_granted_role",
     [
@@ -19,9 +18,7 @@
     ],
 )
 def test_login(ods_code, role_to_assume, expected_granted_role):
-    login_helper = LloydGeorgeMockcis2Helper(
-        ods=ods_code, repository_role=role_to_assume
-    )
+    login_helper = MockCis2Helper(ods=ods_code, repository_role=role_to_assume)
     login_helper.generate_mockcis2_token()
     assert login_helper.user_role == expected_granted_role
     assert login_helper.user_token is not None