NRL-1165 reject whitespace-only strings in model, update tests for pydantic validation of codeable concept fields

Author: katebobyn-nhs

api/producer/createDocumentReference/tests/test_create_document_reference.py

@@ -239,6 +239,36 @@ def test_create_document_reference_invalid_body():
                 "diagnostics": "Request body could not be parsed (status: Field required)",
                 "expression": ["status"],
             },
+            {
+                "severity": "error",
+                "code": "invalid",
+                "details": {
+                    "coding": [
+                        {
+                            "code": "MESSAGE_NOT_WELL_FORMED",
+                            "display": "Message not well formed",
+                            "system": "https://fhir.nhs.uk/ValueSet/Spine-ErrorOrWarningCode-1",
+                        }
+                    ],
+                },
+                "diagnostics": "Request body could not be parsed (type: Field required)",
+                "expression": ["type"],
+            },
+            {
+                "severity": "error",
+                "code": "invalid",
+                "details": {
+                    "coding": [
+                        {
+                            "code": "MESSAGE_NOT_WELL_FORMED",
+                            "display": "Message not well formed",
+                            "system": "https://fhir.nhs.uk/ValueSet/Spine-ErrorOrWarningCode-1",
+                        }
+                    ],
+                },
+                "diagnostics": "Request body could not be parsed (category: Field required)",
+                "expression": ["category"],
+            },
             {
                 "severity": "error",
                 "code": "invalid",

api/producer/swagger.yaml

@@ -1386,7 +1386,7 @@ components:
             description: Relationships that this document has with other document references that already exist.
         description:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: Human–readable description of the source document.
         securityLabel:
           type: array
@@ -1408,6 +1408,8 @@ components:
         - content
         - author
         - context
+        - type
+        - category
     Bundle:
       type: object
       properties:
@@ -1693,7 +1695,7 @@ components:
           description: The calculated hash of the data using SHA–1. Represented using base64.
         title:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A label or set of text to display in place of the data.
         creation:
           type: string
@@ -1716,7 +1718,7 @@ components:
             description: A reference to a code defined by a terminology system.
         text:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A human language representation of the concept as seen/selected/uttered by the user who entered the data and/or which represents the intended meaning of the user.
     NRLCodeableConcept:
       type: object
@@ -1734,7 +1736,7 @@ components:
           maxItems: 1
         text:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A human language representation of the concept as seen/selected/uttered by the user who entered the data and/or which represents the intended meaning of the user.
       required:
         - coding
@@ -1752,15 +1754,15 @@ components:
           description: The identification of the code system that defines the meaning of the symbol in the code.
         version:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: The version of the code system which was used when choosing this code. Note that a well–maintained code system does not need the version reported, because the meaning of codes is consistent across versions. However this cannot consistently be assured, and when the meaning is not guaranteed to be consistent, the version SHOULD be exchanged.
         code:
           type: string
           pattern: "[^\\s]+(\\s[^\\s]+)*"
           description: A symbol in syntax defined by the system. The symbol may be a predefined code or an expression in a syntax defined by the coding system (e.g. post–coordination).
         display:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A representation of the meaning of the code in the system, following the rules of the system.
         userSelected:
           type: boolean
@@ -1778,15 +1780,15 @@ components:
           description: The identification of the code system that defines the meaning of the symbol in the code.
         version:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: The version of the code system which was used when choosing this code. Note that a well–maintained code system does not need the version reported, because the meaning of codes is consistent across versions. However this cannot consistently be assured, and when the meaning is not guaranteed to be consistent, the version SHOULD be exchanged.
         code:
           type: string
           pattern: "[^\\s]+(\\s[^\\s]+)*"
           description: A symbol in syntax defined by the system. The symbol may be a predefined code or an expression in a syntax defined by the coding system (e.g. post–coordination).
         display:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A representation of the meaning of the code in the system, following the rules of the system.
         userSelected:
           type: boolean
@@ -1893,11 +1895,11 @@ components:
           description: A coded type for the identifier that can be used to determine which identifier to use for a specific purpose.
         system:
           type: string
-          pattern: \S*
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: Establishes the namespace for the value – that is, a URL that describes a set values that are unique.
         value:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: The portion of the identifier typically relevant to the user and which is unique within the context of the system.
         period:
           $ref: "#/components/schemas/Period"
@@ -1936,11 +1938,11 @@ components:
           description: How the value should be understood and represented &ndash; whether the actual value is greater or less than the stated value due to measurement issues; e.g. if the comparator is "<" , then the real value is < stated value.
         unit:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A human&ndash;readable form of the unit.
         system:
           type: string
-          pattern: \S*
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: The identification of the system that provides the coded form of the unit.
         code:
           type: string
@@ -1955,11 +1957,11 @@ components:
           description: Unique id for the element within a resource (for internal references). This may be any string value that does not contain spaces.
         reference:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A reference to a location at which the other resource is found. The reference may be a relative reference, in which case it is relative to the service base URL, or an absolute URL that resolves to the location where the resource is found. The reference may be version specific or not. If the reference is not to a FHIR RESTful server, then it should be assumed to be version specific. Internal fragment references (start with '#') refer to contained resources.
         type:
           type: string
-          pattern: \S*
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: |-
             The expected type of the target of the reference. If both Reference.type and Reference.reference are populated and Reference.reference is a FHIR URL, both SHALL be consistent.
             The type is the Canonical URL of Resource Definition that is the type this reference refers to. References are URLs that are relative to http://hl7.org/fhir/StructureDefinition/ e.g. "Patient" is a reference to http://hl7.org/fhir/StructureDefinition/Patient. Absolute URLs are only allowed for logical models (and can only be used in references in logical models, not resources).
@@ -1968,7 +1970,7 @@ components:
           description: An identifier for the target resource. This is used when there is no way to reference the other resource directly, either because the entity it represents is not available through a FHIR server, or because there is no way for the author of the resource to convert a known identifier to an actual location. There is no requirement that a Reference.identifier point to something that is actually exposed as a FHIR instance, but it SHALL point to a business concept that would be expected to be exposed as a FHIR instance, and that instance would need to be of a FHIR resource type allowed by the reference.
         display:
           type: string
-          pattern: "[ \\r\\n\\t\\S]+"
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: Plain text narrative that identifies the resource in addition to the resource reference.
     Signature:
       type: object
@@ -2026,13 +2028,13 @@ components:
           description: When the resource last changed &ndash; e.g. when the version changed.
         source:
           type: string
-          pattern: \S*
+          pattern: "[\\S]+[ \\r\\n\\t\\S]*"
           description: A uri that identifies the source system of the resource. This provides a minimal amount of [Provenance](provenance.html#) information that can be used to track or differentiate the source of information in the resource. The source may identify another FHIR server, document, message, database, etc.
         profile:
           type: array
           items:
             type: string
-            pattern: \S*
+            pattern: "[\\S]+[ \\r\\n\\t\\S]*"
             description: A list of profiles (references to [StructureDefinition](structuredefinition.html#) resources) that this resource claims to conform to. The URL is a reference to [StructureDefinition.url](structuredefinition&ndash;definitions.html#StructureDefinition.url).
         security:
           type: array

api/producer/updateDocumentReference/tests/test_update_document_reference.py

@@ -195,7 +195,7 @@ def test_create_document_reference_no_body():
     }
 
 
-def test_create_document_reference_invalid_body():
+def test_update_document_reference_invalid_body():
     event = create_test_api_gateway_event(
         headers=create_headers(),
         path_parameters={"id": "Y05868-99999-99999-999999"},
@@ -246,6 +246,36 @@ def test_create_document_reference_invalid_body():
                 "diagnostics": "Request body could not be parsed (status: Field required)",
                 "expression": ["status"],
             },
+            {
+                "severity": "error",
+                "code": "invalid",
+                "details": {
+                    "coding": [
+                        {
+                            "code": "MESSAGE_NOT_WELL_FORMED",
+                            "display": "Message not well formed",
+                            "system": "https://fhir.nhs.uk/ValueSet/Spine-ErrorOrWarningCode-1",
+                        }
+                    ],
+                },
+                "diagnostics": "Request body could not be parsed (type: Field required)",
+                "expression": ["type"],
+            },
+            {
+                "severity": "error",
+                "code": "invalid",
+                "details": {
+                    "coding": [
+                        {
+                            "code": "MESSAGE_NOT_WELL_FORMED",
+                            "display": "Message not well formed",
+                            "system": "https://fhir.nhs.uk/ValueSet/Spine-ErrorOrWarningCode-1",
+                        }
+                    ],
+                },
+                "diagnostics": "Request body could not be parsed (category: Field required)",
+                "expression": ["category"],
+            },
             {
                 "severity": "error",
                 "code": "invalid",

api/producer/upsertDocumentReference/tests/test_upsert_document_reference.py

@@ -324,6 +324,36 @@ def test_upsert_document_reference_invalid_body():
                 "diagnostics": "Request body could not be parsed (status: Field required)",
                 "expression": ["status"],
             },
+            {
+                "severity": "error",
+                "code": "invalid",
+                "details": {
+                    "coding": [
+                        {
+                            "code": "MESSAGE_NOT_WELL_FORMED",
+                            "display": "Message not well formed",
+                            "system": "https://fhir.nhs.uk/ValueSet/Spine-ErrorOrWarningCode-1",
+                        }
+                    ],
+                },
+                "diagnostics": "Request body could not be parsed (type: Field required)",
+                "expression": ["type"],
+            },
+            {
+                "severity": "error",
+                "code": "invalid",
+                "details": {
+                    "coding": [
+                        {
+                            "code": "MESSAGE_NOT_WELL_FORMED",
+                            "display": "Message not well formed",
+                            "system": "https://fhir.nhs.uk/ValueSet/Spine-ErrorOrWarningCode-1",
+                        }
+                    ],
+                },
+                "diagnostics": "Request body could not be parsed (category: Field required)",
+                "expression": ["category"],
+            },
             {
                 "severity": "error",
                 "code": "invalid",

layer/nrlf/consumer/fhir/r4/model.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  swagger.yaml
-#   timestamp: 2024-12-13T11:19:30+00:00
+#   timestamp: 2025-01-27T09:26:33+00:00
 
 from __future__ import annotations
 

layer/nrlf/core/dynamodb/tests/test_model.py

@@ -6,8 +6,7 @@
 from nrlf.core.constants import PointerTypes
 from nrlf.core.dynamodb.model import DocumentPointer, DynamoDBModel
 from nrlf.core.utils import create_fhir_instant
-from nrlf.producer.fhir.r4.model import DocumentReference
-from nrlf.tests.data import load_document_reference, load_document_reference_json
+from nrlf.tests.data import load_document_reference
 
 
 def test_dynamodb_model_init():
@@ -159,28 +158,6 @@ def test_document_pointer_from_document_reference_invalid():
     assert str(error.value) == "'NoneType' object has no attribute 'coding'"
 
 
-def test_document_pointer_from_document_reference_multiple_types():
-    doc_ref_data = load_document_reference_json("Y05868-736253002-Valid")
-    doc_ref = DocumentReference.model_validate(
-        {
-            **doc_ref_data,
-            "type": {
-                "coding": [
-                    {"system": "http://snomed.info/sct", "code": "123456789"},
-                    {"system": "http://snomed.info/sct", "code": "987654321"},
-                ]
-            },
-        }
-    )
-
-    with pytest.raises(ValueError) as error:
-        DocumentPointer.from_document_reference(doc_ref)
-
-    assert (
-        str(error.value) == "DocumentReference.type.coding must have exactly one item"
-    )
-
-
 def test_document_pointer_extract_custodian_suffix_no_suffix():
     values = {"custodian": "X26", "custodian_suffix": None}