refactor(Document): initialising a Document now requires a DocumentUR…

…IString, not a str

This previously accepted a str and would attempt to strip it and remove slashes. It now only accepts a DocumentURIString object.

BREAKING CHANGE: Document can now no longer be initialised with a string as the `uri`, it must be a `DocumentURIString`.

CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog 1.0.0].
 
+## Unreleased
+
+### BREAKING CHANGE
+
+- Document can now no longer be initialised with a string as the `uri`, it must be a `DocumentURIString`.
+
 ## v27.4.0 (2024-11-07)
 
 ### Change of behaviour

src/caselawclient/factories.py

@@ -5,7 +5,7 @@
 from typing_extensions import TypeAlias
 
 from caselawclient.Client import MarklogicApiClient
-from caselawclient.models.documents import Document
+from caselawclient.models.documents import Document, DocumentURIString
 from caselawclient.models.documents.body import DocumentBody
 from caselawclient.models.judgments import Judgment
 from caselawclient.models.press_summaries import PressSummary
@@ -54,7 +54,7 @@ class DocumentFactory:
     @classmethod
     def build(
         cls,
-        uri: str = "test/2023/123",
+        uri: DocumentURIString = DocumentURIString("test/2023/123"),
         html: str = "<p>This is a judgment.</p>",
         api_client: Optional[MarklogicApiClient] = None,
         **kwargs: Any,

src/caselawclient/models/documents/__init__.py

@@ -105,13 +105,15 @@ class Document:
     Individual document classes should extend this list where necessary to validate document type-specific attributes.
     """
 
-    def __init__(self, uri: str, api_client: "MarklogicApiClient", search_query: Optional[str] = None):
+    def __init__(self, uri: DocumentURIString, api_client: "MarklogicApiClient", search_query: Optional[str] = None):
         """
-        :param uri: For historical reasons this accepts a pseudo-URI which may include leading or trailing slashes.
+        :param uri: The URI of the document to retrieve from MarkLogic.
+        :param api_client: An instance of the API client object to handle communication with the MarkLogic server.
+        :param search_query: Optionally, a search string which should be highlighted if it appears in the document body.
 
         :raises DocumentNotFoundError: The document does not exist within MarkLogic
         """
-        self.uri: DocumentURIString = DocumentURIString(uri.strip("/"))
+        self.uri: DocumentURIString = uri
         self.api_client: MarklogicApiClient = api_client
         if not self.document_exists():
             raise DocumentNotFoundError(f"Document {self.uri} does not exist")
@@ -123,7 +125,7 @@ def __init__(self, uri: str, api_client: "MarklogicApiClient", search_query: Opt
                 search_query=search_query,
             ),
         )
-        """ `Document.body` represents the XML of the document itself, without any information such as version tracking or properties. """
+        """ `Document.body` represents the body of the document itself, without any information such as version tracking or properties. """
 
     def __repr__(self) -> str:
         name = self.body.name or "un-named"