ds-caselaw-marklogic-api-client 33.0.0__tar.gz → 34.0.1__tar.gz

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/PKG-INFO

@@ -1,13 +1,12 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 33.0.0
+Version: 34.0.1
 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
 Author: The National Archives
-Requires-Python: >=3.9,<4.0
+Requires-Python: >=3.10.0,<4.0.0
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: boto3 (>=1.26.112,<2.0.0)

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "33.0.0"
+version = "34.0.1"
 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"
@@ -11,7 +11,7 @@ packages = [
 ]
 
 [tool.poetry.dependencies]
-python = "^3.9"
+python = "^3.10.0"
 certifi = ">=2025.1.31,<2025.2.0"
 charset-normalizer = "^3.0.0"
 django-environ = ">=0.12.0"

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/Client.py

@@ -572,6 +572,7 @@ class MarklogicApiClient:
         self,
         document_uri: DocumentURIString,
         document_xml: Element,
+        document_type: type[Document],
         annotation: VersionAnnotation,
     ) -> requests.Response:
         """
@@ -579,6 +580,7 @@ class MarklogicApiClient:
 
         :param document_uri: The URI to insert the document at
         :param document_xml: The XML of the document to insert
+        :param document_type: The type class of the document
         :param annotation: Annotations to record alongside this version
 
         :return: The response object from MarkLogic
@@ -592,6 +594,7 @@ class MarklogicApiClient:
 
         vars: query_dicts.InsertDocumentDict = {
             "uri": uri,
+            "type_collection": document_type.type_collection_name,
             "document": xml.decode("utf-8"),
             "annotation": annotation.as_json,
         }
@@ -1068,14 +1071,14 @@ class MarklogicApiClient:
         response = self._send_to_eval(vars, "get_properties_for_search_results.xqy")
         return get_single_string_from_marklogic_response(response)
 
-    def search_and_decode_response(self, search_parameters: SearchParameters) -> str:
+    def search_and_decode_response(self, search_parameters: SearchParameters) -> bytes:
         response = self.advanced_search(search_parameters)
-        return get_single_string_from_marklogic_response(response)
+        return get_single_bytestring_from_marklogic_response(response)
 
     def search_judgments_and_decode_response(
         self,
         search_parameters: SearchParameters,
-    ) -> str:
+    ) -> bytes:
         search_parameters.collections = [DOCUMENT_COLLECTION_URI_JUDGMENT]
         return self.search_and_decode_response(search_parameters)
 

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/client_helpers/__init__.py

@@ -2,8 +2,19 @@ import json
 from enum import Enum
 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
+
+
+class CannotDetermineDocumentType(Exception):
+    pass
+
 
 class AnnotationDataDict(TypedDict):
     type: str
@@ -112,3 +123,26 @@ class VersionAnnotation:
 
     def __str__(self) -> str:
         return self.as_json
+
+
+def get_document_type_class(xml: bytes) -> type[Document]:
+    """Attempt to get the type of the document based on the top-level structure of the XML document."""
+
+    node = etree.fromstring(xml)
+
+    # If the main node is `<judgment>`, it's a judgment
+    if node.xpath("/akn:akomaNtoso/akn:judgment", namespaces=DEFAULT_NAMESPACES):
+        return Judgment
+
+    # 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 determine the Document type by its XML",
+    )

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/models/documents/__init__.py

@@ -61,6 +61,8 @@ class Document:
     document_noun_plural = "documents"
     """ The noun for a plural of this document type. """
 
+    type_collection_name: str
+
     attributes_to_validate: list[tuple[str, bool, str]] = [
         (
             "is_failure",

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/models/judgments.py

@@ -23,6 +23,7 @@ class Judgment(NeutralCitationMixin, Document):
 
     document_noun = "judgment"
     document_noun_plural = "judgments"
+    type_collection_name = "judgment"
 
     def __init__(self, uri: DocumentURIString, *args: Any, **kwargs: Any) -> None:
         super().__init__(self.document_noun, uri, *args, **kwargs)

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/models/press_summaries.py

@@ -24,6 +24,7 @@ class PressSummary(NeutralCitationMixin, Document):
 
     document_noun = "press summary"
     document_noun_plural = "press summaries"
+    type_collection_name = "press-summary"
 
     def __init__(self, uri: DocumentURIString, *args: Any, **kwargs: Any) -> None:
         super().__init__(self.document_noun, uri, *args, **kwargs)

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/responses/search_result.py

@@ -3,7 +3,7 @@ import os
 from datetime import datetime
 from enum import Enum
 from functools import cached_property
-from typing import Dict, Optional
+from typing import Any, Dict, Optional
 
 from dateutil import parser as dateparser
 from dateutil.parser import ParserError
@@ -12,6 +12,8 @@ from ds_caselaw_utils.types import CourtCode, JurisdictionCode
 from lxml import etree
 
 from caselawclient.Client import MarklogicApiClient
+from caselawclient.models.identifiers import Identifiers
+from caselawclient.models.identifiers.unpacker import unpack_all_identifiers_from_etree
 from caselawclient.types import DocumentURIString
 from caselawclient.xml_helpers import get_xpath_match_string
 
@@ -169,6 +171,21 @@ class SearchResult:
             self._get_xpath_match_string("@uri").lstrip("/").split(".xml")[0],
         )
 
+    @property
+    def identifiers(self) -> 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]
+        return unpack_all_identifiers_from_etree(identifiers_etree)
+
+    @cached_property
+    def slug(self) -> str:
+        preferred = self.identifiers.preferred()
+        if not preferred:
+            raise RuntimeError("No preferred identifier for search result")
+        return str(preferred.url_slug)
+
     @property
     def neutral_citation(self) -> str:
         """
@@ -278,3 +295,6 @@ class SearchResult:
 
     def _get_xpath_match_string(self, path: str) -> str:
         return get_xpath_match_string(self.node, path, namespaces=self.NAMESPACES)
+
+    def _get_xpath(self, path: str) -> Any:
+        return self.node.xpath(path, namespaces=self.NAMESPACES)

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/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,

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/xquery/insert_document.xqy

@@ -4,20 +4,16 @@ import module namespace dls = "http://marklogic.com/xdmp/dls" at "/MarkLogic/dls
 
 declare variable $uri as xs:string external;
 declare variable $document as xs:string external;
+declare variable $type_collection as xs:string external;
 declare variable $annotation as xs:string external;
 
 let $document_xml := xdmp:unquote($document)
 
-let $collections :=
-  if (fn:contains($uri, 'press-summary'))
-  then ("press-summary")
-  else ("judgment")
-
 return dls:document-insert-and-manage(
   $uri,
   fn:true(),
   $document_xml,
   $annotation,
   (),
-  $collections
+  ($type_collection)
 )

{ds_caselaw_marklogic_api_client-33.0.0 → ds_caselaw_marklogic_api_client-34.0.1}/src/caselawclient/xquery_type_dicts.py

@@ -133,6 +133,7 @@ class GetVersionCreatedDict(MarkLogicAPIDict):
 class InsertDocumentDict(MarkLogicAPIDict):
     annotation: str
     document: str
+    type_collection: str
     uri: MarkLogicDocumentURIString