[NDR-183] Bulk upload missing scan_date field in metadata (#700)

* [NDR-183] add logic to handle missing scan data
* [NDR-183] remove default value for scan date

Author: NogaNHS

lambdas/models/document_reference.py

@@ -48,7 +48,7 @@ class DocumentReference(BaseModel):
     created: str = Field(
         default_factory=lambda: datetime.now(timezone.utc).strftime(DATE_FORMAT)
     )
-    document_scan_creation: str = Field(
+    document_scan_creation: Optional[str] = Field(
         default_factory=lambda: datetime.date(datetime.now()).isoformat(),
     )
     current_gp_ods: str = Field(default=None)

lambdas/services/bulk_upload_service.py

@@ -389,9 +389,12 @@ def convert_to_document_reference(
     ) -> DocumentReference:
         s3_bucket_name = self.bulk_upload_s3_repository.lg_bucket_name
         file_name = os.path.basename(file_metadata.file_path)
-        scan_date_formatted = datetime.strptime(
-            file_metadata.scan_date, "%d/%m/%Y"
-        ).strftime("%Y-%m-%d")
+        if file_metadata.scan_date:
+            scan_date_formatted = datetime.strptime(
+                file_metadata.scan_date, "%d/%m/%Y"
+            ).strftime("%Y-%m-%d")
+        else:
+            scan_date_formatted = None
         document_reference = DocumentReference(
             id=str(uuid.uuid4()),
             nhs_number=nhs_number,

lambdas/tests/unit/services/test_bulk_upload_service.py

@@ -887,6 +887,28 @@ def test_convert_to_document_reference(set_env, mock_uuid, repo_under_test):
     assert actual == expected
 
 
+@freeze_time("2024-01-01 12:00:00")
+def test_convert_to_document_reference_missing_scan_date(
+    set_env, mock_uuid, repo_under_test
+):
+    TEST_STAGING_METADATA.retries = 0
+    repo_under_test.bulk_upload_s3_repository.lg_bucket_name = "test_lg_s3_bucket"
+    expected = TEST_DOCUMENT_REFERENCE
+    expected.document_scan_creation = None
+    TEST_FILE_METADATA.scan_date = ""
+
+    actual = repo_under_test.convert_to_document_reference(
+        file_metadata=TEST_FILE_METADATA,
+        nhs_number=TEST_STAGING_METADATA.nhs_number,
+        current_gp_ods=TEST_CURRENT_GP_ODS,
+    )
+
+    assert actual == expected
+
+    TEST_FILE_METADATA.scan_date = "03/09/2022"
+    TEST_DOCUMENT_REFERENCE.document_scan_creation = "2022-09-03"
+
+
 def test_raise_client_error_from_ssm_with_pds_service(
     mock_ods_validation,
     repo_under_test,