ds-caselaw-marklogic-api-client 34.0.0__tar.gz → 34.0.2__tar.gz

{ds_caselaw_marklogic_api_client-34.0.0 → ds_caselaw_marklogic_api_client-34.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 34.0.0
+Version: 34.0.2
 Summary: An API client for interacting with the underlying data in Find Caselaw.
 Home-page: https://github.com/nationalarchives/ds-caselaw-custom-api-client
 Keywords: national archives,caselaw

{ds_caselaw_marklogic_api_client-34.0.0 → ds_caselaw_marklogic_api_client-34.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "34.0.0"
+version = "34.0.2"
 description = "An API client for interacting with the underlying data in Find Caselaw."
 authors = ["The National Archives"]
 homepage = "https://github.com/nationalarchives/ds-caselaw-custom-api-client"

{ds_caselaw_marklogic_api_client-34.0.0 → ds_caselaw_marklogic_api_client-34.0.2}/src/caselawclient/client_helpers/__init__.py

@@ -5,6 +5,8 @@ from typing import Any, Optional, TypedDict
 from lxml import etree
 from typing_extensions import NotRequired
 
+from caselawclient.xml_helpers import DEFAULT_NAMESPACES
+
 from ..models.documents import Document
 from ..models.judgments import Judgment
 from ..models.press_summaries import PressSummary
@@ -124,19 +126,23 @@ class VersionAnnotation:
 
 
 def get_document_type_class(xml: bytes) -> type[Document]:
-    """Attempt to get the type of the document based on the XML root node."""
+    """Attempt to get the type of the document based on the top-level structure of the XML document."""
 
     node = etree.fromstring(xml)
 
-    # If the document's root element is `judgment` it's a `Judgment`, regardless of the presence of a `name`.
-    if node.tag == "judgment":
+    # If the main node is `<judgment>`, it's a judgment
+    if node.xpath("/akn:akomaNtoso/akn:judgment", namespaces=DEFAULT_NAMESPACES):
         return Judgment
 
-    # If the document's root element has a `name` attribute with a value of `pressSummary` we can assume it's a `PressSummary`
-    if node.tag == "doc" and node.attrib.get("name") == "pressSummary":
+    # If the main node is `<doc name='pressSummary'>`, it's a press summary
+    if node.xpath("/akn:akomaNtoso/akn:doc[@name='pressSummary']", namespaces=DEFAULT_NAMESPACES):
         return PressSummary
 
+    # If the document is a parser error with a root element of `error`, it's not of a special type.
+    if node.xpath("/error", namespaces=DEFAULT_NAMESPACES):
+        return Document
+
     # Otherwise, we don't know for sure. Fail out.
     raise CannotDetermineDocumentType(
-        "Unable to accurately determine the type of document based on the root XML node.",
+        "Unable to determine the Document type by its XML",
     )

{ds_caselaw_marklogic_api_client-34.0.0 → ds_caselaw_marklogic_api_client-34.0.2}/src/caselawclient/responses/search_result.py

@@ -173,7 +173,7 @@ class SearchResult:
 
     @property
     def identifiers(self) -> Identifiers:
-        identifiers_etrees = self._get_xpath("//identifiers")
+        identifiers_etrees = self._get_xpath(".//identifiers")
         if count := len(identifiers_etrees) != 1:
             logging.warning(f"{count} //identifiers nodes found in search result, expected 1.")
         identifiers_etree = None if not identifiers_etrees else identifiers_etrees[0]

{ds_caselaw_marklogic_api_client-34.0.0 → ds_caselaw_marklogic_api_client-34.0.2}/src/caselawclient/xml_helpers.py

@@ -2,6 +2,11 @@ from typing import Dict, Optional
 
 from lxml import etree
 
+DEFAULT_NAMESPACES = {
+    "uk": "https://caselaw.nationalarchives.gov.uk/akn",
+    "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
+}
+
 
 def get_xpath_match_string(
     node: etree._Element,