ds-caselaw-marklogic-api-client 38.0.0__tar.gz → 39.0.0__tar.gz

{ds_caselaw_marklogic_api_client-38.0.0 → 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: 38.0.0
+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 (>=2025.6.15,<2025.7.0)
+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-38.0.0 → ds_caselaw_marklogic_api_client-39.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "38.0.0"
+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 = ">=2025.6.15,<2025.7.0"
+certifi = ">=2025.7.9,<2025.8.0"
 charset-normalizer = "^3.0.0"
 django-environ = ">=0.12.0"
 idna = "^3.4"
@@ -37,7 +37,7 @@ beautifulsoup4 = "4.13.4"
 responses = "0.25.7"
 python-dotenv = "1.1.1"
 time-machine = "2.16.0"
-moto = {version = "5.1.6", extras = ["all"]}
+moto = {version = "5.1.8", extras = ["all"]}
 
 [tool.poetry.group.docs]
 optional = true

{ds_caselaw_marklogic_api_client-38.0.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/models/documents/__init__.py

@@ -31,7 +31,7 @@ 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 CannotEnrichUnenrichableDocument, CannotPublishUnpublishableDocument, DocumentNotSafeForDeletion
@@ -521,9 +521,12 @@ class 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:
         """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)
+        validations = self.validate_identifiers()
         if validations.success is True:
             self.api_client.set_property_as_node(self.uri, "identifiers", self.identifiers.as_etree)
         else:
@@ -570,7 +573,7 @@ class Document:
     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}"
+        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(

{ds_caselaw_marklogic_api_client-38.0.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/models/documents/xml.py

@@ -58,7 +58,8 @@ class XML:
         """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))
+        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"""

{ds_caselaw_marklogic_api_client-38.0.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/models/identifiers/__init__.py

@@ -149,6 +149,9 @@ 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:

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-38.0.0 → 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-38.0.0 → ds_caselaw_marklogic_api_client-39.0.0}/src/caselawclient/xslt/modify_xml_live.xsl

@@ -1,6 +1,9 @@
 <?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: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" />
@@ -16,51 +19,51 @@
     <!-- <xsl:template match="akn:identification/FRBRWork/FRBRthistext/text()"><xsl:copy-of select="$cat" /></xsl:template> -->
 
     <xsl:template match="akn:identification/akn:FRBRWork/akn:FRBRthis">
-        <akn:FRBRthis>
+        <FRBRthis>
             <xsl:attribute name="value">
                 <xsl:value-of select="$work_uri" />
             </xsl:attribute>
-        </akn:FRBRthis>
+        </FRBRthis>
     </xsl:template>
 
     <xsl:template match="akn:identification/akn:FRBRWork/akn:FRBRuri">
-        <akn:FRBRuri>
+        <FRBRuri>
             <xsl:attribute name="value">
                 <xsl:value-of select="$work_uri" />
             </xsl:attribute>
-        </akn:FRBRuri>
+        </FRBRuri>
     </xsl:template>
 
     <xsl:template match="akn:identification/akn:FRBRExpression/akn:FRBRthis">
-        <akn:FRBRthis>
+        <FRBRthis>
             <xsl:attribute name="value">
                 <xsl:value-of select="$expression_uri" />
             </xsl:attribute>
-        </akn:FRBRthis>
+        </FRBRthis>
     </xsl:template>
 
     <xsl:template match="akn:identification/akn:FRBRExpression/akn:FRBRuri">
-        <akn:FRBRuri>
+        <FRBRuri>
             <xsl:attribute name="value">
                 <xsl:value-of select="$expression_uri" />
             </xsl:attribute>
-        </akn:FRBRuri>
+        </FRBRuri>
     </xsl:template>
 
     <xsl:template match="akn:identification/akn:FRBRManifestation/akn:FRBRthis">
-        <akn:FRBRthis>
+        <FRBRthis>
             <xsl:attribute name="value">
                 <xsl:value-of select="$manifestation_uri" />
             </xsl:attribute>
-        </akn:FRBRthis>
+        </FRBRthis>
     </xsl:template>
 
     <xsl:template match="akn:identification/akn:FRBRManifestation/akn:FRBRuri">
-        <akn:FRBRuri>
+        <FRBRuri>
             <xsl:attribute name="value">
                 <xsl:value-of select="$manifestation_uri" />
             </xsl:attribute>
-        </akn:FRBRuri>
+        </FRBRuri>
     </xsl:template>
 
 

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

@@ -1,102 +0,0 @@
-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]