ds-caselaw-marklogic-api-client 37.4.0__tar.gz → 39.0.0__tar.gz

{ds_caselaw_marklogic_api_client-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ds-caselaw-marklogic-api-client
-Version: 37.4.0
+Version: 39.0.0
 Summary: An API client for interacting with the underlying data in Find Caselaw.
 Keywords: national archives,caselaw
 Author: The National Archives
@@ -11,7 +11,7 @@ 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 (>=2025.7.9,<2025.8.0)
 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)

{ds_caselaw_marklogic_api_client-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "37.4.0"
+version = "39.0.0"
 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 = ">=2025.7.9,<2025.8.0"
 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 = "5.1.8", extras = ["all"]}
 
 [tool.poetry.group.docs]
 optional = true

{ds_caselaw_marklogic_api_client-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/factories.py

@@ -8,6 +8,7 @@ from caselawclient.identifier_resolution import IdentifierResolution, Identifier
 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
@@ -188,5 +189,10 @@ class SearchResultFactory(SimpleFactory[SearchResult]):
         "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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/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
@@ -30,10 +31,10 @@ from caselawclient.models.utilities.aws import (
     request_parse,
     unpublish_documents,
 )
-from caselawclient.types import DocumentURIString
+from caselawclient.types import DocumentURIString, SuccessFailureMessageTuple
 
 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 +514,25 @@ 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 validate_identifiers(self) -> SuccessFailureMessageTuple:
+        return self.identifiers.perform_all_validations(document_type=type(self), api_client=self.api_client)
+
     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.validate_identifiers()
+        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 +569,13 @@ 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/doc/{fcl_identifiers[0].value}"
+        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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/models/documents/body.py

@@ -174,3 +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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/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 +49,21 @@ 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))
+        noncanonical_xml = xslt_transform(self.xml_as_tree, profile_run=False, **passable_values)
+        return etree.tostring(noncanonical_xml, method="c14n2")
+
+    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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/models/identifiers/__init__.py

@@ -1,12 +1,16 @@
 from abc import ABC, abstractmethod
-from typing import Any, Optional, Union
+from typing import TYPE_CHECKING, Any, Optional
 from uuid import uuid4
 
 from lxml import etree
 
-from caselawclient.types import DocumentIdentifierSlug, DocumentIdentifierValue
+from caselawclient.types import DocumentIdentifierSlug, DocumentIdentifierValue, SuccessFailureMessageTuple
 
-from .exceptions import IdentifierValidationException, UUIDMismatchError
+from .exceptions import IdentifierValidationException
+
+if TYPE_CHECKING:
+    from caselawclient.Client import MarklogicApiClient
+    from caselawclient.models.documents import Document
 
 IDENTIFIER_PACKABLE_ATTRIBUTES: list[str] = [
     "uuid",
@@ -38,6 +42,19 @@ class IdentifierSchema(ABC):
     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 (
@@ -54,7 +71,7 @@ class IdentifierSchema(ABC):
 
     @classmethod
     @abstractmethod
-    def validate_identifier(cls, value: str) -> bool:
+    def validate_identifier_value(cls, value: str) -> bool:
         """Check that any given identifier value is valid for this schema."""
         pass
 
@@ -94,7 +111,7 @@ class Identifier(ABC):
         return self.value
 
     def __init__(self, value: str, uuid: Optional[str] = None, deprecated: bool = False) -> None:
-        if not self.schema.validate_identifier(value=value):
+        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.'
             )
@@ -132,72 +149,63 @@ class Identifier(ABC):
     @property
     def score(self) -> float:
         """Return the score of this identifier, used to calculate the preferred identifier for a document."""
+        if self.deprecated:
+            return 0
+
         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.
 
-class Identifiers(dict[str, Identifier]):
-    def validate(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 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)
+        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!'],
+            )
 
-    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)]
+        return SuccessFailureMessageTuple(True, [])
 
-    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]
+    def validate_valid_for_document_type(self, document_type: type["Document"]) -> SuccessFailureMessageTuple:
+        document_type_classname = document_type.__name__
 
-    @property
-    def as_etree(self) -> etree._Element:
-        """Return an etree representation of all the Document's identifiers."""
-        identifiers_root = etree.Element("identifiers")
+        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}"'
+                ],
+            )
 
-        for identifier in self.values():
-            identifiers_root.append(identifier.as_xml_tree)
+        return SuccessFailureMessageTuple(True, [])
 
-        return identifiers_root
+    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),
+        ]
 
-    def by_score(self, type: Optional[type[Identifier]] = None) -> list[Identifier]:
-        """
-        :param type: Optionally, an identifier type to constrain this list to.
+        success = True
+        messages: list[str] = []
 
-        :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)
+        for validation in validations:
+            if validation.success is False:
+                success = False
 
-    def preferred(self, type: Optional[type[Identifier]] = None) -> Optional[Identifier]:
-        """
-        :param type: Optionally, an identifier type to constrain the results to.
+            messages += validation.messages
 
-        :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]
+        return SuccessFailureMessageTuple(success, messages)

ds_caselaw_marklogic_api_client-39.0.0/src/caselawclient/models/identifiers/collection.py

@@ -0,0 +1,170 @@
+from typing import TYPE_CHECKING, Optional, Union
+
+from lxml import etree
+
+from caselawclient.types import SuccessFailureMessageTuple
+
+from . import Identifier, IdentifierSchema
+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) -> SuccessFailureMessageTuple:
+        for uuid, identifier in self.items():
+            if uuid != identifier.uuid:
+                return SuccessFailureMessageTuple(
+                    False, [f"Key of {identifier} in Identifiers is {uuid} not {identifier.uuid}"]
+                )
+
+        return SuccessFailureMessageTuple(True, [])
+
+    def _list_all_identifiers_by_schema(self) -> dict[type[IdentifierSchema], list[Identifier]]:
+        """Get a list of all identifiers, grouped by their schema."""
+        identifiers_by_schema: dict[type[IdentifierSchema], list[Identifier]] = {}
+
+        for identifier in self.values():
+            identifiers_by_schema.setdefault(identifier.schema, []).append(identifier)
+
+        return identifiers_by_schema
+
+    def check_only_single_non_deprecated_identifier_where_multiples_not_allowed(self) -> SuccessFailureMessageTuple:
+        """Check that only one non-deprecated identifier exists per schema where that schema does not allow multiples."""
+
+        for schema, identifiers in self._list_all_identifiers_by_schema().items():
+            non_deprecated_identifiers = [i for i in identifiers if not i.deprecated]
+            if len(non_deprecated_identifiers) > 1:
+                return SuccessFailureMessageTuple(
+                    False,
+                    [
+                        f"Multiple non-deprecated identifiers found for schema '{schema.name}': {', '.join(i.value for i in non_deprecated_identifiers)}"
+                    ],
+                )
+
+        return SuccessFailureMessageTuple(True, [])
+
+    def _perform_collection_level_validations(self) -> SuccessFailureMessageTuple:
+        """Perform identifier validations which are only possible at the collection level, such as UUID integrity and identifying exclusivity problems."""
+
+        success = True
+        messages: list[str] = []
+
+        collection_validations_to_run: list[SuccessFailureMessageTuple] = [
+            self.validate_uuids_match_keys(),
+            self.check_only_single_non_deprecated_identifier_where_multiples_not_allowed(),
+        ]
+
+        for validation in collection_validations_to_run:
+            if not validation.success:
+                success = False
+                messages += validation.messages
+
+        return SuccessFailureMessageTuple(success, messages)
+
+    def _perform_identifier_level_validations(
+        self, document_type: type["Document"], api_client: "MarklogicApiClient"
+    ) -> SuccessFailureMessageTuple:
+        """Perform identifier validations at the individual identifier level."""
+
+        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 perform_all_validations(
+        self, document_type: type["Document"], api_client: "MarklogicApiClient"
+    ) -> SuccessFailureMessageTuple:
+        """Perform all possible identifier validations on this collection, both at the individual and collection level."""
+
+        identifier_level_success, identifier_level_messages = self._perform_identifier_level_validations(
+            document_type=document_type, api_client=api_client
+        )
+        collection_level_success, collection_level_messages = self._perform_collection_level_validations()
+
+        success = all([identifier_level_success, collection_level_success])
+        all_messages = identifier_level_messages + collection_level_messages
+
+        return SuccessFailureMessageTuple(success, all_messages)
+
+    def contains(self, other_identifier: Identifier) -> bool:
+        """Does 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 valid_new_identifier_types(self, document_type: type["Document"]) -> list[type[Identifier]]:
+        """Return a list of identifier types which can be added to a document of the given type, given identifiers already in this collection."""
+        return [
+            t
+            for t in SUPPORTED_IDENTIFIER_TYPES
+            if t.schema.allow_editing
+            and (not t.schema.document_types or document_type.__name__ in t.schema.document_types)
+        ]
+
+    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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/models/identifiers/exceptions.py

@@ -2,9 +2,5 @@ class InvalidIdentifierXMLRepresentationException(Exception):
     pass
 
 
-class UUIDMismatchError(Exception):
-    pass
-
-
 class IdentifierValidationException(Exception):
     pass

{ds_caselaw_marklogic_api_client-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/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-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/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")

{ds_caselaw_marklogic_api_client-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/models/identifiers/unpacker.py

@@ -3,22 +3,18 @@ from warnings import warn
 
 from lxml import etree
 
-from . import IDENTIFIER_UNPACKABLE_ATTRIBUTES, Identifier, Identifiers
+from . import IDENTIFIER_UNPACKABLE_ATTRIBUTES, Identifier
+from .collection import SUPPORTED_IDENTIFIER_TYPES, IdentifiersCollection
 from .exceptions import InvalidIdentifierXMLRepresentationException
-from .fclid import FindCaseLawIdentifier
-from .neutral_citation import NeutralCitationNumber
-from .press_summary_ncn import PressSummaryRelatedNCNIdentifier
 
 IDENTIFIER_NAMESPACE_MAP: dict[str, type[Identifier]] = {
-    "fclid": FindCaseLawIdentifier,
-    "ukncn": NeutralCitationNumber,
-    "uksummaryofncn": PressSummaryRelatedNCNIdentifier,
+    identifier_type.schema.namespace: identifier_type for identifier_type in SUPPORTED_IDENTIFIER_TYPES
 }
 
 
-def unpack_all_identifiers_from_etree(identifiers_etree: Optional[etree._Element]) -> Identifiers:
+def unpack_all_identifiers_from_etree(identifiers_etree: Optional[etree._Element]) -> IdentifiersCollection:
     """This expects the entire <identifiers> tag, and unpacks all Identifiers inside it"""
-    identifiers = Identifiers()
+    identifiers = IdentifiersCollection()
     if identifiers_etree is None:
         return identifiers
     for identifier_etree in identifiers_etree.findall("identifier"):

{ds_caselaw_marklogic_api_client-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/responses/search_result.py

@@ -12,7 +12,7 @@ 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.collection import IdentifiersCollection
 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
@@ -180,7 +180,7 @@ class SearchResult:
         )
 
     @property
-    def identifiers(self) -> Identifiers:
+    def identifiers(self) -> IdentifiersCollection:
         identifiers_etrees = self._get_xpath(".//identifiers")
         count = len(identifiers_etrees)
         if count != 1:

{ds_caselaw_marklogic_api_client-37.4.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/types.py

@@ -1,3 +1,6 @@
+from typing import NamedTuple
+
+
 class InvalidDocumentURIException(Exception):
     """The document URI is not valid."""
 
@@ -58,3 +61,11 @@ class DocumentIdentifierSlug(str):
 
 class DocumentIdentifierValue(str):
     pass
+
+
+SuccessFailureMessageTuple = NamedTuple("SuccessFailureMessageTuple", [("success", bool), ("messages", list[str])])
+"""
+A tuple used to return if an operation has succeeded or failed (and optionally a list of messages associated with that operation).
+
+This should only be used where a failure is considered a routine part of the application (eg during validation options); where an unexpected action has led to a failure the application should raise an appropriate exception.
+"""

ds_caselaw_marklogic_api_client-39.0.0/src/caselawclient/xslt/modify_xml_live.xsl

@@ -0,0 +1,70 @@
+<?xml version="1.0"?>
+<xsl:stylesheet version="1.0"
+    xmlns='http://docs.oasis-open.org/legaldocml/ns/akn/3.0'
+    xmlns:akn='http://docs.oasis-open.org/legaldocml/ns/akn/3.0'
+    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+    xmlns:uk='https://caselaw.nationalarchives.gov.uk/akn'>
+    <xsl:param name="work_uri" />
+    <xsl:param name="expression_uri" />
+    <xsl:param name="manifestation_uri" />
+    <xsl:output method="xml" indent="yes" />
+
+    <!-- Identify transformation -->
+    <xsl:template match="@* | node()">
+        <xsl:copy>
+            <xsl:apply-templates select="@* | node()" />
+        </xsl:copy>
+    </xsl:template>
+
+    <!-- <xsl:template match="akn:identification/FRBRWork/FRBRthistext/text()"><xsl:copy-of select="$cat" /></xsl:template> -->
+
+    <xsl:template match="akn:identification/akn:FRBRWork/akn:FRBRthis">
+        <FRBRthis>
+            <xsl:attribute name="value">
+                <xsl:value-of select="$work_uri" />
+            </xsl:attribute>
+        </FRBRthis>
+    </xsl:template>
+
+    <xsl:template match="akn:identification/akn:FRBRWork/akn:FRBRuri">
+        <FRBRuri>
+            <xsl:attribute name="value">
+                <xsl:value-of select="$work_uri" />
+            </xsl:attribute>
+        </FRBRuri>
+    </xsl:template>
+
+    <xsl:template match="akn:identification/akn:FRBRExpression/akn:FRBRthis">
+        <FRBRthis>
+            <xsl:attribute name="value">
+                <xsl:value-of select="$expression_uri" />
+            </xsl:attribute>
+        </FRBRthis>
+    </xsl:template>
+
+    <xsl:template match="akn:identification/akn:FRBRExpression/akn:FRBRuri">
+        <FRBRuri>
+            <xsl:attribute name="value">
+                <xsl:value-of select="$expression_uri" />
+            </xsl:attribute>
+        </FRBRuri>
+    </xsl:template>
+
+    <xsl:template match="akn:identification/akn:FRBRManifestation/akn:FRBRthis">
+        <FRBRthis>
+            <xsl:attribute name="value">
+                <xsl:value-of select="$manifestation_uri" />
+            </xsl:attribute>
+        </FRBRthis>
+    </xsl:template>
+
+    <xsl:template match="akn:identification/akn:FRBRManifestation/akn:FRBRuri">
+        <FRBRuri>
+            <xsl:attribute name="value">
+                <xsl:value-of select="$manifestation_uri" />
+            </xsl:attribute>
+        </FRBRuri>
+    </xsl:template>
+
+
+</xsl:stylesheet>

ds_caselaw_marklogic_api_client-39.0.0/src/caselawclient/xslt/sample.xsl

@@ -0,0 +1,26 @@
+<?xml version="1.0"?>
+<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+    xmlns:uk='https://caselaw.nationalarchives.gov.uk/akn'
+    xmlns:akn='http://docs.oasis-open.org/legaldocml/ns/akn/3.0'>
+
+    <xsl:param name="dog" />
+    <xsl:param name="cat" />
+    <xsl:output method="xml" indent="yes" />
+
+    <xsl:template match="@* | node()">
+        <xsl:copy>
+            <xsl:apply-templates select="@* | node()" />
+        </xsl:copy>
+    </xsl:template>
+
+    <xsl:template match="akn:text/text()"><xsl:copy-of select="$cat" /></xsl:template>
+
+    <xsl:template match="akn:attribute">
+        <akn:attribute>
+            <xsl:attribute name="attribute">
+                <xsl:value-of select="$dog" />
+            </xsl:attribute>
+        </akn:attribute>
+    </xsl:template>
+
+</xsl:stylesheet>