[NDR-365] Allow title to be optional

lambdas/models/document_reference.py

@@ -102,7 +102,7 @@ class DocumentReference(BaseModel):
     author: str | None = None
     content_type: str = Field(default=DEFAULT_CONTENT_TYPE)
     created: str = Field(
-        default_factory=lambda: datetime.now(timezone.utc).strftime(DATE_FORMAT)
+        default_factory=lambda: datetime.now(timezone.utc).strftime(DATE_FORMAT),
     )
     document_scan_creation: Optional[str] = Field(
         default_factory=lambda: datetime.date(datetime.now()).isoformat(),
@@ -125,10 +125,10 @@ class DocumentReference(BaseModel):
     ] = Field(default="preliminary")
     doc_type: str = Field(default=None, exclude=True)
     document_snomed_code_type: Optional[str] = Field(
-        default=SnomedCodes.LLOYD_GEORGE.value.code
+        default=SnomedCodes.LLOYD_GEORGE.value.code,
     )
     file_location: str = ""
-    file_name: str
+    file_name: str | None
     file_size: int | None = Field(default=None)
     last_updated: int = Field(
         default_factory=lambda: int(datetime.now(timezone.utc).timestamp()),
@@ -140,11 +140,12 @@ class DocumentReference(BaseModel):
     s3_version_id: Optional[str] = Field(default=None, alias="S3VersionID")
     s3_upload_key: str = Field(default=None, exclude=True)
     status: Literal["current", "superseded", "entered-in-error"] = Field(
-        default="current"
+        default="current",
     )
     sub_folder: str = Field(default=None, exclude=True)
     ttl: Optional[int] = Field(
-        alias=str(DocumentReferenceMetadataFields.TTL.value), default=None
+        alias=str(DocumentReferenceMetadataFields.TTL.value),
+        default=None,
     )
     uploaded: bool = Field(default=None)
     uploading: bool = Field(default=None)
@@ -174,7 +175,8 @@ def set_location_properties(cls, data, *args, **kwargs):
             if "s3_file_key" not in data:
                 data["s3_file_key"] = cls._build_final_s3_key(data)
             data["file_location"] = cls._build_s3_location(
-                data["s3_bucket_name"], current_s3_file_key
+                data["s3_bucket_name"],
+                current_s3_file_key,
             )
         return data
 

lambdas/services/post_fhir_document_reference_service.py

@@ -3,7 +3,9 @@
 from enums.mtls import MtlsCommonNames
 from enums.snomed_codes import SnomedCode, SnomedCodes
 from models.document_reference import DocumentReference
-from models.fhir.R4.fhir_document_reference import SNOMED_URL
+from models.fhir.R4.fhir_document_reference import (
+    SNOMED_URL,
+)
 from models.fhir.R4.fhir_document_reference import (
     DocumentReference as FhirDocumentReference,
 )
@@ -25,7 +27,9 @@ def __init__(self):
         super().__init__()
 
     def process_fhir_document_reference(
-        self, fhir_document: str, api_request_context: dict = {}
+        self,
+        fhir_document: str,
+        api_request_context: dict = {},
     ) -> str:
         """
         Process a FHIR Document Reference request
@@ -40,7 +44,7 @@ def process_fhir_document_reference(
             common_name = validate_common_name_in_mtls(api_request_context)
 
             validated_fhir_doc = FhirDocumentReference.model_validate_json(
-                fhir_document
+                fhir_document,
             )
 
             # Extract NHS number and author from the FHIR document
@@ -72,7 +76,9 @@ def process_fhir_document_reference(
             )
 
             presigned_url = self._handle_document_save(
-                document_reference, validated_fhir_doc, dynamo_table
+                document_reference,
+                validated_fhir_doc,
+                dynamo_table,
             )
 
             return self._create_fhir_response(document_reference, presigned_url)
@@ -107,7 +113,9 @@ def _extract_author_from_fhir(self, fhir_doc: FhirDocumentReference) -> str | No
             raise DocumentRefException(400, LambdaError.DocRefNoParse)
 
     def _determine_document_type(
-        self, fhir_doc: FhirDocumentReference, common_name: MtlsCommonNames | None
+        self,
+        fhir_doc: FhirDocumentReference,
+        common_name: MtlsCommonNames | None,
     ) -> SnomedCode:
         if not common_name:
             """Determine the document type based on SNOMED code in the FHIR document"""
@@ -119,7 +127,7 @@ def _determine_document_type(
                             return snomed_code
                     else:
                         logger.error(
-                            f"SNOMED code {coding.code} - {coding.display} is not supported"
+                            f"SNOMED code {coding.code} - {coding.display} is not supported",
                         )
                         raise DocumentRefException(400, LambdaError.DocRefInvalidType)
             logger.error("SNOMED code not found in FHIR document")
@@ -147,6 +155,12 @@ def _create_document_reference(
         if not custodian:
             custodian = current_gp_ods
 
+        title = fhir_doc.content[0].attachment.title or None
+
+        if doc_type != SnomedCodes.PATIENT_DATA.value and title is None:
+            logger.error("FHIR document validation error: attachment.title missing")
+            raise DocumentRefException(400, LambdaError.DocRefNoParse)
+
         sub_folder, raw_request = (
             ("user_upload", None)
             if doc_type != SnomedCodes.PATIENT_DATA.value
@@ -161,7 +175,7 @@ def _create_document_reference(
             s3_bucket_name=self.staging_bucket_name,
             author=author,
             content_type=fhir_doc.content[0].attachment.contentType,
-            file_name=fhir_doc.content[0].attachment.title,
+            file_name=title,
             document_snomed_code_type=doc_type.code,
             doc_status="preliminary",
             status="current",

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

@@ -1,4 +1,5 @@
 import base64
+import json
 import logging
 import os
 
@@ -42,7 +43,8 @@ def condition(response_json):
         return response_json["content"][0]["attachment"].get("data", False)
 
     raw_retrieve_response = retrieve_document_with_retry(
-        upload_response["id"], condition
+        upload_response["id"],
+        condition,
     )
     retrieve_response = raw_retrieve_response.json()
 
@@ -85,7 +87,8 @@ def test_create_document_without_author_or_type(test_data):
     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"]
+        record=record,
+        exclude=["type", "author"],
     )
 
     for field in ["type", "author"]:
@@ -103,3 +106,32 @@ def test_create_document_without_author_or_type(test_data):
     assert doc_ref["Item"]["RawRequest"] == payload
     for field in ["type", "author"]:
         assert field not in doc_ref["Item"]["RawRequest"]
+
+
+def test_create_document_without_title(test_data):
+    record = {
+        "ods": "H81109",
+        "nhs_number": "9912003071",
+    }
+
+    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=["title"])
+    assert "title" not in payload
+
+    raw_upload_response = upload_document(payload)
+    assert raw_upload_response.status_code == 201
+    record["id"] = raw_upload_response.json()["id"].split("~")[1]
+    test_data.append(record)
+
+    doc_ref = pdm_data_helper.retrieve_document_reference(record=record)
+    assert "Item" in doc_ref
+    assert "RawRequest" in doc_ref["Item"]
+    assert doc_ref["Item"]["RawRequest"] == payload
+    raw_request = json.loads(doc_ref["Item"]["RawRequest"])
+    assert "content" in raw_request
+    content = raw_request["content"]
+    assert "attachment" in content[0]
+    attachment = raw_request["content"][0]["attachment"]
+    assert "title" not in attachment

lambdas/tests/e2e/api/test_upload_document_api.py

@@ -18,7 +18,7 @@
 data_helper = LloydGeorgeDataHelper()
 
 
-def create_upload_payload(lloyd_george_record):
+def create_upload_payload(lloyd_george_record, exclude: list[str] | None = None):
     sample_payload = {
         "resourceType": "DocumentReference",
         "type": {
@@ -27,28 +27,28 @@ def create_upload_payload(lloyd_george_record):
                     "system": "http://snomed.info/sct",
                     "code": f"{LLOYD_GEORGE_SNOMED}",
                     "display": "Lloyd George record folder",
-                }
-            ]
+                },
+            ],
         },
         "subject": {
             "identifier": {
                 "system": "https://fhir.nhs.uk/Id/nhs-number",
                 "value": lloyd_george_record["nhs_number"],
-            }
+            },
         },
         "author": [
             {
                 "identifier": {
                     "system": "https://fhir.nhs.uk/Id/ods-organization-code",
                     "value": lloyd_george_record["ods"],
-                }
-            }
+                },
+            },
         ],
         "custodian": {
             "identifier": {
                 "system": "https://fhir.nhs.uk/Id/ods-organization-code",
                 "value": lloyd_george_record["ods"],
-            }
+            },
         },
         "content": [
             {
@@ -57,11 +57,18 @@ def create_upload_payload(lloyd_george_record):
                     "contentType": "application/pdf",
                     "language": "en-GB",
                     "title": "1of1_Lloyd_George_Record_[Paula Esme VESEY]_[9730153973]_[22-01-1960].pdf",
-                }
-            }
+                },
+            },
         ],
     }
 
+    if exclude:
+        for field in exclude:
+            if field == "title":
+                sample_payload["content"][0]["attachment"].pop(field, None)
+            else:
+                sample_payload.pop(field, None)
+
     if "data" in lloyd_george_record:
         sample_payload["content"][0]["attachment"]["data"] = lloyd_george_record["data"]
     return json.dumps(sample_payload)
@@ -105,10 +112,10 @@ def condition(response_json):
     assert base64.b64decode(base64_data, validate=True)
 
     assert upload_response == snapshot_json(
-        exclude=paths("id", "date", "content.0.attachment.url")
+        exclude=paths("id", "date", "content.0.attachment.url"),
     )
     assert retrieve_response == snapshot_json(
-        exclude=paths("id", "date", "content.0.attachment.data")
+        exclude=paths("id", "date", "content.0.attachment.data"),
     )
 
 
@@ -153,8 +160,11 @@ def condition(response_json):
     assert upload_response == snapshot_json(exclude=paths("id", "date"))
     assert retrieve_response == snapshot_json(
         exclude=paths(
-            "id", "date", "content.0.attachment.url", "content.0.attachment.size"
-        )
+            "id",
+            "date",
+            "content.0.attachment.url",
+            "content.0.attachment.size",
+        ),
     )
 
 
@@ -195,7 +205,7 @@ def condition(response_json):
     retrieve_response = raw_retrieve_response.json()
 
     assert upload_response == snapshot_json(
-        exclude=paths("id", "date", "content.0.attachment.url")
+        exclude=paths("id", "date", "content.0.attachment.url"),
     )
     assert retrieve_response == snapshot_json(exclude=paths("id", "date"))
 
@@ -221,3 +231,29 @@ def test_create_document_does_not_save_raw(test_data):
     doc_ref = data_helper.retrieve_document_reference(record=lloyd_george_record)
     assert "Item" in doc_ref
     assert "RawRequest" not in doc_ref["Item"]
+
+
+def test_create_document_without_title_raises_error(test_data):
+    lloyd_george_record = {}
+    lloyd_george_record["ods"] = "H81109"
+    lloyd_george_record["nhs_number"] = "9449303304"
+
+    sample_pdf_path = os.path.join(os.path.dirname(__file__), "files", "dummy.pdf")
+    with open(sample_pdf_path, "rb") as f:
+        lloyd_george_record["data"] = base64.b64encode(f.read()).decode("utf-8")
+    payload = create_upload_payload(lloyd_george_record, exclude=["title"])
+
+    url = f"https://{API_ENDPOINT}/FhirDocumentReference"
+    headers = {"Authorization": "Bearer 123", "X-Api-Key": API_KEY}
+
+    retrieve_response = requests.post(url, headers=headers, data=payload)
+    assert retrieve_response.status_code == 400
+
+    json_response = retrieve_response.json()
+    assert (
+        json_response["issue"][0]["details"]["coding"][0]["code"] == "VALIDATION_ERROR"
+    )
+    assert (
+        json_response["issue"][0]["diagnostics"]
+        == "Failed to parse document upload request data"
+    )