ds-caselaw-marklogic-api-client 37.3.1__tar.gz → 38.0.0__tar.gz

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/PKG-INFO

@@ -1,16 +1,17 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: ds-caselaw-marklogic-api-client
-Version: 37.3.1
+Version: 38.0.0
 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: >=3.10.0,<4.0.0
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: boto3 (>=1.26.112,<2.0.0)
-Requires-Dist: certifi (>=2025.4.26,<2025.5.0)
+Requires-Dist: certifi (>=2025.6.15,<2025.7.0)
 Requires-Dist: charset-normalizer (>=3.0.0,<4.0.0)
 Requires-Dist: django-environ (>=0.12.0)
 Requires-Dist: ds-caselaw-utils (>=2.0.0,<3.0.0)
@@ -26,6 +27,7 @@ Requires-Dist: requests-toolbelt (>=0.10.1,<1.1.0)
 Requires-Dist: saxonche (>=12.5.0,<13.0.0)
 Requires-Dist: sqids (>=0.5.0,<0.6.0)
 Requires-Dist: typing-extensions (>=4.7.1,<5.0.0)
+Project-URL: Homepage, https://github.com/nationalarchives/ds-caselaw-custom-api-client
 Description-Content-Type: text/markdown
 
 # The National Archives: Find Case Law

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "37.3.1"
+version = "38.0.0"
 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"
@@ -12,7 +12,7 @@ packages = [
 
 [tool.poetry.dependencies]
 python = "^3.10.0"
-certifi = ">=2025.4.26,<2025.5.0"
+certifi = ">=2025.6.15,<2025.7.0"
 charset-normalizer = "^3.0.0"
 django-environ = ">=0.12.0"
 idna = "^3.4"
@@ -31,13 +31,13 @@ saxonche = "^12.5.0"
 sqids = "^0.5.0"
 
 [tool.poetry.group.dev.dependencies]
-coverage = "7.8.2"
-pytest = "8.3.5"
+coverage = "7.9.2"
+pytest = "8.4.1"
 beautifulsoup4 = "4.13.4"
 responses = "0.25.7"
-python-dotenv = "1.1.0"
+python-dotenv = "1.1.1"
 time-machine = "2.16.0"
-moto = {version = "5.1.5", extras = ["all"]}
+moto = {version = "5.1.6", extras = ["all"]}
 
 [tool.poetry.group.docs]
 optional = true

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/factories.py

@@ -1,15 +1,14 @@
 import datetime
 import json
-from typing import Any, Optional
+from typing import Any, Generic, Optional, Type, TypeAlias, TypeVar, cast
 from unittest.mock import Mock
 
-from typing_extensions import TypeAlias
-
 from caselawclient.Client import MarklogicApiClient
 from caselawclient.identifier_resolution import IdentifierResolution, IdentifierResolutions
 from caselawclient.models.documents import Document
 from caselawclient.models.documents.body import DocumentBody
 from caselawclient.models.identifiers import Identifier
+from caselawclient.models.identifiers.collection import IdentifiersCollection
 from caselawclient.models.identifiers.fclid import FindCaseLawIdentifier
 from caselawclient.models.identifiers.neutral_citation import NeutralCitationNumber
 from caselawclient.models.judgments import Judgment
@@ -17,6 +16,8 @@ from caselawclient.models.press_summaries import PressSummary
 from caselawclient.responses.search_result import SearchResult, SearchResultMetadata
 from caselawclient.types import DocumentURIString
 
+T = TypeVar("T")
+
 DEFAULT_DOCUMENT_BODY_XML = """<akomaNtoso xmlns="http://docs.oasis-open.org/legaldocml/ns/akn/3.0" xmlns:uk="https://caselaw.nationalarchives.gov.uk/akn">
             <judgment name="decision">
                 <meta/><header/>
@@ -114,13 +115,13 @@ class PressSummaryFactory(DocumentFactory):
     }
 
 
-class SimpleFactory:
-    target_class: TypeAlias = object
+class SimpleFactory(Generic[T]):
+    target_class: Type[T]
     # "name_of_attribute": "default value"
     PARAMS_MAP: dict[str, Any]
 
     @classmethod
-    def build(cls, **kwargs: Any) -> target_class:
+    def build(cls, **kwargs: Any) -> T:
         mock_object = Mock(spec=cls.target_class, autospec=True)
 
         for param, default in cls.PARAMS_MAP.items():
@@ -129,10 +130,10 @@ class SimpleFactory:
             else:
                 setattr(mock_object.return_value, param, default)
 
-        return mock_object()
+        return cast(T, mock_object())
 
 
-class SearchResultMetadataFactory(SimpleFactory):
+class SearchResultMetadataFactory(SimpleFactory[SearchResultMetadata]):
     target_class = SearchResultMetadata
     # "name_of_attribute": "default value"
     PARAMS_MAP = {
@@ -174,9 +175,8 @@ class IdentifierResolutionsFactory:
         return IdentifierResolutions(resolutions)
 
 
-class SearchResultFactory(SimpleFactory):
+class SearchResultFactory(SimpleFactory[SearchResult]):
     target_class = SearchResult
-
     PARAMS_MAP = {
         "uri": "d-a1b2c3",
         "name": "Judgment v Judgement",
@@ -189,5 +189,10 @@ class SearchResultFactory(SimpleFactory):
         "matches": None,
         "slug": "uksc/2025/1",
         "content_hash": "ed7002b439e9ac845f22357d822bac1444730fbdb6016d3ec9432297b9ec9f73",
-        "identifiers": {"id-1": NeutralCitationNumber("[2025] UKSC 123", "id-1")},
+        "identifiers": IdentifiersCollection(
+            {
+                "id-1": NeutralCitationNumber("[2025] UKSC 123", "id-1"),
+                "id-2": FindCaseLawIdentifier("bcdfghjk", "id-2"),
+            }
+        ),
     }

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/models/documents/__init__.py

@@ -16,6 +16,7 @@ from caselawclient.errors import (
 )
 from caselawclient.identifier_resolution import IdentifierResolutions
 from caselawclient.models.identifiers import Identifier
+from caselawclient.models.identifiers.exceptions import IdentifierValidationException
 from caselawclient.models.identifiers.fclid import FindCaseLawIdentifier, FindCaseLawIdentifierSchema
 from caselawclient.models.identifiers.unpacker import unpack_all_identifiers_from_etree
 from caselawclient.models.utilities import VersionsDict, extract_version, render_versions
@@ -33,7 +34,7 @@ from caselawclient.models.utilities.aws import (
 from caselawclient.types import DocumentURIString
 
 from .body import DocumentBody
-from .exceptions import CannotPublishUnpublishableDocument, DocumentNotSafeForDeletion
+from .exceptions import CannotEnrichUnenrichableDocument, CannotPublishUnpublishableDocument, DocumentNotSafeForDeletion
 from .statuses import DOCUMENT_STATUS_HOLD, DOCUMENT_STATUS_IN_PROGRESS, DOCUMENT_STATUS_NEW, DOCUMENT_STATUS_PUBLISHED
 
 MINIMUM_ENRICHMENT_TIME = datetime.timedelta(minutes=20)
@@ -340,22 +341,34 @@ class Document:
             now.isoformat(),
         )
 
+        if not self.can_enrich:
+            msg = f"{self.uri} cannot be enriched"
+            raise CannotEnrichUnenrichableDocument(msg)
+
         announce_document_event(
             uri=self.uri,
             status="enrich",
             enrich=True,
         )
 
-    def enrich(self) -> bool:
+    def enrich(self, even_if_recent: bool = False, accept_failures: bool = False) -> bool:
         """
         Request enrichment of a document, if it's sensible to do so.
         """
-        if self.enriched_recently is False:
-            print("Enrichment requested")
+        if not (even_if_recent) and self.enriched_recently:
+            print("Enrichment not requested as document was enriched recently")
+            return False
+
+        print("Enrichment requested")
+
+        try:
             self.force_enrich()
-            return True
-        print("Enrichment not requested as document was enriched recently")
-        return False
+        except CannotEnrichUnenrichableDocument as e:
+            if not accept_failures:
+                raise e
+            return False
+
+        return True
 
     @cached_property
     def enriched_recently(self) -> bool:
@@ -501,10 +514,22 @@ class Document:
         """
         return self.docx_exists()
 
+    @cached_property
+    def can_enrich(self) -> bool:
+        """
+        Is it possible to enrich this document?
+        """
+        return self.body.has_content
+
     def save_identifiers(self) -> None:
-        """Save the current state of this Document's identifiers to MarkLogic."""
-        self.identifiers.validate()
-        self.api_client.set_property_as_node(self.uri, "identifiers", self.identifiers.as_etree)
+        """Validate the identifiers, and if the validation passes save them to MarkLogic"""
+        validations = self.identifiers.perform_all_validations(document_type=type(self), api_client=self.api_client)
+        if validations.success is True:
+            self.api_client.set_property_as_node(self.uri, "identifiers", self.identifiers.as_etree)
+        else:
+            raise IdentifierValidationException(
+                "Unable to save identifiers; validation constraints not met: " + ", ".join(validations.messages)
+            )
 
     def __getattr__(self, name: str) -> Any:
         warnings.warn(f"{name} no longer exists on Document, using Document.body instead", DeprecationWarning)
@@ -541,3 +566,13 @@ class Document:
     def content_as_html(self) -> str | None:
         xlst_image_location = os.getenv("XSLT_IMAGE_LOCATION", "")
         return self.body.content_html(f"{xlst_image_location}/{self.uri}")
+
+    def xml_with_correct_frbr(self) -> bytes:
+        """Dynamically modify FRBR uris to reflect current storage location and FCL id"""
+        fcl_identifiers = self.identifiers.of_type(FindCaseLawIdentifier)
+        work_uri = f"https://caselaw.nationalarchives.gov.uk/id/{fcl_identifiers[0].url_slug}"
+        expression_uri = f"https://caselaw.nationalarchives.gov.uk/{self.uri.lstrip('/')}"
+        manifestation_uri = f"https://caselaw.nationalarchives.gov.uk/{self.uri.lstrip('/')}/data.xml"
+        return self.body.apply_xslt(
+            "modify_xml_live.xsl", work_uri=work_uri, expression_uri=expression_uri, manifestation_uri=manifestation_uri
+        )

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/models/documents/body.py

@@ -51,6 +51,14 @@ class DocumentBody:
     def jurisdiction(self) -> str:
         return self.get_xpath_match_string("/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:jurisdiction/text()")
 
+    @cached_property
+    def category(self) -> Optional[str]:
+        return self.get_xpath_match_string("/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:category/text()")
+
+    @cached_property
+    def case_number(self) -> Optional[str]:
+        return self.get_xpath_match_string("/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:caseNumber/text()")
+
     @property
     def court_and_jurisdiction_identifier_string(self) -> CourtCode:
         if self.jurisdiction != "":
@@ -166,3 +174,6 @@ class DocumentBody:
         :return: `True` if there was a complete parser failure, otherwise `False`
         """
         return "error" in self._xml.root_element
+
+    def apply_xslt(self, xslt_filename: str, **values: str) -> bytes:
+        return self._xml.apply_xslt(xslt_filename, **values)

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/models/documents/exceptions.py

@@ -2,5 +2,9 @@ class CannotPublishUnpublishableDocument(Exception):
     """A document which has failed publication safety checks in `Document.is_publishable` cannot be published."""
 
 
+class CannotEnrichUnenrichableDocument(Exception):
+    """A document which cannot be enriched (see `Document.can_enrich`) tried to be sent to enrichment"""
+
+
 class DocumentNotSafeForDeletion(Exception):
     """A document which is not safe for deletion cannot be deleted."""

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/models/documents/xml.py

@@ -1,8 +1,16 @@
+import os
+
 from lxml import etree
 
 from caselawclient.xml_helpers import get_xpath_match_string, get_xpath_match_strings
 
 
+def _xslt_path(xslt_file_name: str) -> str:
+    from caselawclient.Client import ROOT_DIR
+
+    return os.path.join(ROOT_DIR, "xslt", xslt_file_name)
+
+
 class NonXMLDocumentError(Exception):
     """A document cannot be parsed as XML."""
 
@@ -41,3 +49,20 @@ class XML:
         namespaces: dict[str, str],
     ) -> list[str]:
         return get_xpath_match_strings(self.xml_as_tree, xpath, namespaces)
+
+    def _modified(
+        self,
+        xslt: str,
+        **values: str,
+    ) -> bytes:
+        """XSLT transform this XML, given a stylesheet"""
+        passable_values = {k: etree.XSLT.strparam(v) for k, v in values.items()}
+        xslt_transform = etree.XSLT(etree.fromstring(xslt))
+        return etree.tostring(xslt_transform(self.xml_as_tree, profile_run=False, **passable_values))
+
+    def apply_xslt(self, xslt_filename: str, **values: str) -> bytes:
+        """XSLT transform this XML, given a path to a stylesheet"""
+        full_xslt_filename = _xslt_path(xslt_filename)
+        with open(full_xslt_filename) as f:
+            xslt = f.read()
+        return self._modified(xslt, **values)

ds_caselaw_marklogic_api_client-38.0.0/src/caselawclient/models/identifiers/__init__.py

@@ -0,0 +1,208 @@
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING, Any, Optional
+from uuid import uuid4
+
+from lxml import etree
+
+from caselawclient.types import DocumentIdentifierSlug, DocumentIdentifierValue, SuccessFailureMessageTuple
+
+from .exceptions import IdentifierValidationException
+
+if TYPE_CHECKING:
+    from caselawclient.Client import MarklogicApiClient
+    from caselawclient.models.documents import Document
+
+IDENTIFIER_PACKABLE_ATTRIBUTES: list[str] = [
+    "uuid",
+    "value",
+    "deprecated",
+    "url_slug",
+]
+"""A list of attributes of an Identifier to pack into an XML representation."""
+
+IDENTIFIER_UNPACKABLE_ATTRIBUTES: list[str] = [
+    "uuid",
+    "value",
+    "deprecated",
+]
+"""A list of attributes to unpack from an XML representation."""
+
+
+class IdentifierSchema(ABC):
+    """
+    A base class which describes what an identifier schema should look like.
+    """
+
+    name: str
+    namespace: str
+
+    human_readable: bool
+    """ Should this identifier type be considered for display as a 'human readable' identifier? """
+
+    base_score_multiplier: float = 1.0
+    """ A multiplier used to adjust the relative ranking of this identifier when calculating preferred identifiers. """
+
+    allow_editing: bool = True
+    """ Should editors be allowed to manually manipulate identifiers under this schema? """
+
+    require_globally_unique: bool = True
+    """ Must this identifier be globally unique? """
+
+    document_types: Optional[list[str]] = None
+    """
+    If present, a list of the names of document classes which can have this identifier.
+
+    If `None`, this identifier is valid for all document types.
+    """
+
+    def __init_subclass__(cls: type["IdentifierSchema"], **kwargs: Any) -> None:
+        """Ensure that subclasses have the required attributes set."""
+        for required in (
+            "name",
+            "namespace",
+            "human_readable",
+        ):
+            if not hasattr(cls, required):
+                raise NotImplementedError(f"Can't instantiate IdentifierSchema without {required} attribute.")
+        super().__init_subclass__(**kwargs)
+
+    def __repr__(self) -> str:
+        return self.name
+
+    @classmethod
+    @abstractmethod
+    def validate_identifier_value(cls, value: str) -> bool:
+        """Check that any given identifier value is valid for this schema."""
+        pass
+
+    @classmethod
+    @abstractmethod
+    def compile_identifier_url_slug(cls, value: str) -> DocumentIdentifierSlug:
+        """Convert an identifier into a precompiled URL slug."""
+        pass
+
+
+class Identifier(ABC):
+    """A base class for subclasses representing a concrete identifier."""
+
+    schema: type[IdentifierSchema]
+
+    uuid: str
+    value: DocumentIdentifierValue
+
+    deprecated: bool
+    """Should this identifier be considered deprecated, ie although we know it refers to a particular document its usage should be discouraged?"""
+
+    def __init_subclass__(cls: type["Identifier"], **kwargs: Any) -> None:
+        """Ensure that subclasses have the required attributes set."""
+        for required in ("schema",):
+            if not getattr(cls, required, False):
+                raise NotImplementedError(f"Can't instantiate Identifier without {required} attribute.")
+        super().__init_subclass__(**kwargs)
+
+    def __repr__(self) -> str:
+        representation = f"{self.schema.name} {self.value}: {self.uuid}"
+
+        if self.deprecated:
+            return f"<{representation} (deprecated)> "
+        return f"<{representation}>"
+
+    def __str__(self) -> str:
+        return self.value
+
+    def __init__(self, value: str, uuid: Optional[str] = None, deprecated: bool = False) -> None:
+        if not self.schema.validate_identifier_value(value=value):
+            raise IdentifierValidationException(
+                f'Identifier value "{value}" is not valid according to the {self.schema.name} schema.'
+            )
+
+        self.value = DocumentIdentifierValue(value)
+        if uuid:
+            self.uuid = uuid
+        else:
+            self.uuid = "id-" + str(uuid4())
+
+        self.deprecated = deprecated
+
+    @property
+    def as_xml_tree(self) -> etree._Element:
+        """Convert this Identifier into a packed XML representation for storage."""
+        identifier_root = etree.Element("identifier")
+
+        namespace_attribute = etree.SubElement(identifier_root, "namespace")
+        namespace_attribute.text = self.schema.namespace
+
+        for attribute_name in IDENTIFIER_PACKABLE_ATTRIBUTES:
+            packed_attribute = etree.SubElement(identifier_root, attribute_name)
+            attribute_value = getattr(self, attribute_name)
+            if type(attribute_value) is bool:
+                packed_attribute.text = str(attribute_value).lower()
+            else:
+                packed_attribute.text = getattr(self, attribute_name)
+
+        return identifier_root
+
+    @property
+    def url_slug(self) -> str:
+        return self.schema.compile_identifier_url_slug(self.value)
+
+    @property
+    def score(self) -> float:
+        """Return the score of this identifier, used to calculate the preferred identifier for a document."""
+        return 1 * self.schema.base_score_multiplier
+
+    def same_as(self, other: "Identifier") -> bool:
+        "Is this the same as another identifier (in value and schema)?"
+        return self.value == other.value and self.schema == other.schema
+
+    def validate_require_globally_unique(self, api_client: "MarklogicApiClient") -> SuccessFailureMessageTuple:
+        """
+        Check against the list of identifiers in the database that this value does not currently exist.
+
+        nb: We don't need to check that the identifier value is unique within a parent `Identifiers` object, because `Identifiers.add()` will only allow one value per namespace.
+        """
+        resolutions = [
+            resolution
+            for resolution in api_client.resolve_from_identifier_value(identifier_value=self.value)
+            if resolution.identifier_namespace == self.schema.namespace
+        ]
+        if len(resolutions) > 0:
+            return SuccessFailureMessageTuple(
+                False,
+                [f'Identifiers in scheme "{self.schema.namespace}" must be unique; "{self.value}" already exists!'],
+            )
+
+        return SuccessFailureMessageTuple(True, [])
+
+    def validate_valid_for_document_type(self, document_type: type["Document"]) -> SuccessFailureMessageTuple:
+        document_type_classname = document_type.__name__
+
+        if self.schema.document_types and document_type_classname not in self.schema.document_types:
+            return SuccessFailureMessageTuple(
+                False,
+                [
+                    f'Document type "{document_type_classname}" is not accepted for identifier schema "{self.schema.name}"'
+                ],
+            )
+
+        return SuccessFailureMessageTuple(True, [])
+
+    def perform_all_validations(
+        self, document_type: type["Document"], api_client: "MarklogicApiClient"
+    ) -> SuccessFailureMessageTuple:
+        """Perform all validations on a given identifier"""
+        validations = [
+            self.validate_require_globally_unique(api_client=api_client),
+            self.validate_valid_for_document_type(document_type=document_type),
+        ]
+
+        success = True
+        messages: list[str] = []
+
+        for validation in validations:
+            if validation.success is False:
+                success = False
+
+            messages += validation.messages
+
+        return SuccessFailureMessageTuple(success, messages)

ds_caselaw_marklogic_api_client-38.0.0/src/caselawclient/models/identifiers/collection.py

@@ -0,0 +1,102 @@
+from typing import TYPE_CHECKING, Optional, Union
+
+from lxml import etree
+
+from caselawclient.types import SuccessFailureMessageTuple
+
+from . import Identifier
+from .exceptions import UUIDMismatchError
+from .fclid import FindCaseLawIdentifier
+from .neutral_citation import NeutralCitationNumber
+from .press_summary_ncn import PressSummaryRelatedNCNIdentifier
+
+if TYPE_CHECKING:
+    from caselawclient.Client import MarklogicApiClient
+    from caselawclient.models.documents import Document
+
+SUPPORTED_IDENTIFIER_TYPES: list[type["Identifier"]] = [
+    FindCaseLawIdentifier,
+    NeutralCitationNumber,
+    PressSummaryRelatedNCNIdentifier,
+]
+
+
+class IdentifiersCollection(dict[str, Identifier]):
+    def validate_uuids_match_keys(self) -> None:
+        for uuid, identifier in self.items():
+            if uuid != identifier.uuid:
+                msg = "Key of {identifier} in Identifiers is {uuid} not {identifier.uuid}"
+                raise UUIDMismatchError(msg)
+
+    def perform_all_validations(
+        self, document_type: type["Document"], api_client: "MarklogicApiClient"
+    ) -> SuccessFailureMessageTuple:
+        self.validate_uuids_match_keys()
+
+        success = True
+        messages: list[str] = []
+
+        for _, identifier in self.items():
+            validations = identifier.perform_all_validations(document_type=document_type, api_client=api_client)
+            if validations.success is False:
+                success = False
+
+            messages += validations.messages
+
+        return SuccessFailureMessageTuple(success, messages)
+
+    def contains(self, other_identifier: Identifier) -> bool:
+        "Do the identifier's value and namespace already exist in this group?"
+        return any(other_identifier.same_as(identifier) for identifier in self.values())
+
+    def add(self, identifier: Identifier) -> None:
+        if not self.contains(identifier):
+            self[identifier.uuid] = identifier
+
+    def __delitem__(self, key: Union[Identifier, str]) -> None:
+        if isinstance(key, Identifier):
+            super().__delitem__(key.uuid)
+        else:
+            super().__delitem__(key)
+
+    def of_type(self, identifier_type: type[Identifier]) -> list[Identifier]:
+        """Return a list of all identifiers of a given type."""
+        uuids = self.keys()
+        return [self[uuid] for uuid in list(uuids) if isinstance(self[uuid], identifier_type)]
+
+    def delete_type(self, deleted_identifier_type: type[Identifier]) -> None:
+        "For when we want an identifier to be the only valid identifier of that type, delete the others first"
+        uuids = self.keys()
+        for uuid in list(uuids):
+            # we could use compare to .schema instead, which would have diffferent behaviour for subclasses
+            if isinstance(self[uuid], deleted_identifier_type):
+                del self[uuid]
+
+    @property
+    def as_etree(self) -> etree._Element:
+        """Return an etree representation of all the Document's identifiers."""
+        identifiers_root = etree.Element("identifiers")
+
+        for identifier in self.values():
+            identifiers_root.append(identifier.as_xml_tree)
+
+        return identifiers_root
+
+    def by_score(self, type: Optional[type[Identifier]] = None) -> list[Identifier]:
+        """
+        :param type: Optionally, an identifier type to constrain this list to.
+
+        :return: Return a list of identifiers, sorted by their score in descending order.
+        """
+        identifiers = self.of_type(type) if type else list(self.values())
+        return sorted(identifiers, key=lambda v: v.score, reverse=True)
+
+    def preferred(self, type: Optional[type[Identifier]] = None) -> Optional[Identifier]:
+        """
+        :param type: Optionally, an identifier type to constrain the results to.
+
+        :return: Return the highest scoring identifier of the given type (or of any type, if none is specified). Returns `None` if no identifier is available.
+        """
+        if len(self.by_score(type)) == 0:
+            return None
+        return self.by_score(type)[0]

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/models/identifiers/fclid.py

@@ -32,8 +32,11 @@ class FindCaseLawIdentifierSchema(IdentifierSchema):
     human_readable = False
     base_score_multiplier = 0.6
 
+    allow_editing = False
+    require_globally_unique = True
+
     @classmethod
-    def validate_identifier(cls, value: str) -> bool:
+    def validate_identifier_value(cls, value: str) -> bool:
         return bool(VALID_FCLID_PATTERN.match(value))
 
     @classmethod

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/models/identifiers/neutral_citation.py

@@ -48,8 +48,10 @@ class NeutralCitationNumberSchema(IdentifierSchema):
     human_readable = True
     base_score_multiplier = 1.5
 
+    document_types = ["Judgment"]
+
     @classmethod
-    def validate_identifier(cls, value: str) -> bool:
+    def validate_identifier_value(cls, value: str) -> bool:
         # Quick check to see if the NCN matches the expected pattern
         if not bool(VALID_NCN_PATTERN.match(value)):
             raise NCNDoesNotMatchExpectedPatternException(f"NCN '{value}' is not in the expected format")

{ds_caselaw_marklogic_api_client-37.3.1 → ds_caselaw_marklogic_api_client-38.0.0}/src/caselawclient/models/identifiers/press_summary_ncn.py

@@ -13,6 +13,8 @@ class PressSummaryRelatedNCNIdentifierSchema(NeutralCitationNumberSchema):
     human_readable = True
     base_score_multiplier = 0.8
 
+    document_types = ["PressSummary"]
+
     @classmethod
     def compile_identifier_url_slug(cls, value: str) -> DocumentIdentifierSlug:
         return DocumentIdentifierSlug(super().compile_identifier_url_slug(value) + "/press-summary")