ds-caselaw-marklogic-api-client 28.0.0__tar.gz → 28.2.0__tar.gz

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 28.0.0
+Version: 28.2.0
 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
@@ -11,7 +11,7 @@ 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)
-Requires-Dist: certifi (>=2024.8.30,<2024.9.0)
+Requires-Dist: certifi (>=2024.12.14,<2024.13.0)
 Requires-Dist: charset-normalizer (>=3.0.0,<4.0.0)
 Requires-Dist: django-environ (>=0.11.0,<0.12.0)
 Requires-Dist: ds-caselaw-utils (>=2.0.0,<3.0.0)
@@ -25,6 +25,7 @@ Requires-Dist: pytz (>=2024.1,<2025.0)
 Requires-Dist: requests (>=2.28.2,<3.0.0)
 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)
 Description-Content-Type: text/markdown
 

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "28.0.0"
+version = "28.2.0"
 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 = "^3.9"
-certifi = ">=2024.8.30,<2024.9.0"
+certifi = ">=2024.12.14,<2024.13.0"
 charset-normalizer = "^3.0.0"
 django-environ = "^0.11.0"
 idna = "^3.4"
@@ -28,6 +28,7 @@ mypy-boto3-sns = "^1.26.69"
 pytz = "^2024.1"
 python-dateutil = "^2.9.0-post.0"
 saxonche = "^12.5.0"
+sqids = "^0.5.0"
 
 [tool.poetry.group.dev.dependencies]
 coverage = "^7.2.3"

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/src/caselawclient/Client.py

@@ -13,12 +13,14 @@ from xml.etree.ElementTree import Element, ParseError, fromstring
 import environ
 import requests
 from ds_caselaw_utils.types import NeutralCitationString
+from lxml import etree
 from requests.auth import HTTPBasicAuth
 from requests.structures import CaseInsensitiveDict
 from requests_toolbelt.multipart import decoder
 
 from caselawclient import xquery_type_dicts as query_dicts
 from caselawclient.client_helpers import VersionAnnotation
+from caselawclient.identifier_resolution import IdentifierResolutions
 from caselawclient.models.documents import (
     DOCUMENT_COLLECTION_URI_JUDGMENT,
     DOCUMENT_COLLECTION_URI_PRESS_SUMMARY,
@@ -864,6 +866,17 @@ class MarklogicApiClient:
         }
         return self._eval_and_decode(vars, "get_property.xqy")
 
+    def get_property_as_node(self, judgment_uri: DocumentURIString, name: str) -> Optional[etree._Element]:
+        uri = self._format_uri_for_marklogic(judgment_uri)
+        vars: query_dicts.GetPropertyAsNodeDict = {
+            "uri": uri,
+            "name": name,
+        }
+        value = self._eval_and_decode(vars, "get_property_as_node.xqy")
+        if not value:
+            return None
+        return etree.fromstring(value)
+
     def get_version_annotation(self, judgment_uri: DocumentURIString) -> str:
         uri = self._format_uri_for_marklogic(judgment_uri)
         vars: query_dicts.GetVersionAnnotationDict = {
@@ -896,6 +909,22 @@ class MarklogicApiClient:
 
         return self._send_to_eval(vars, "set_property.xqy")
 
+    def set_property_as_node(
+        self,
+        judgment_uri: DocumentURIString,
+        name: str,
+        value: etree._Element,
+    ) -> requests.Response:
+        """Given a root node, set the value of the MarkLogic property for a document to the _contents_ of that root node. The root node itself is discarded."""
+        uri = self._format_uri_for_marklogic(judgment_uri)
+        vars: query_dicts.SetPropertyAsNodeDict = {
+            "uri": uri,
+            "value": etree.tostring(value).decode(),
+            "name": name,
+        }
+
+        return self._send_to_eval(vars, "set_property_as_node.xqy")
+
     def set_boolean_property(
         self,
         judgment_uri: DocumentURIString,
@@ -1173,3 +1202,22 @@ class MarklogicApiClient:
         )
 
         return results
+
+    def resolve_from_identifier(self, identifier_uri: str, published_only: bool = True) -> IdentifierResolutions:
+        """Given a PUI/EUI url, look up the precomputed slug and return the
+        MarkLogic document URIs which match that slug. Multiple returns should be anticipated"""
+        vars: query_dicts.ResolveFromIdentifierDict = {
+            "identifier_uri": DocumentURIString(identifier_uri),
+            "published_only": int(published_only),
+        }
+        raw_results: list[str] = get_multipart_strings_from_marklogic_response(
+            self._send_to_eval(
+                vars,
+                "resolve_from_identifier.xqy",
+            ),
+        )
+        return IdentifierResolutions.from_marklogic_output(raw_results)
+
+    def get_next_document_sequence_number(self) -> int:
+        """Increment the MarkLogic sequence number by one and return the value."""
+        return int(self._eval_and_decode({}, "get_next_document_sequence_number.xqy"))

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/src/caselawclient/factories.py

@@ -62,6 +62,7 @@ class DocumentFactory:
         if not api_client:
             api_client = Mock(spec=MarklogicApiClient)
             api_client.get_judgment_xml_bytestring.return_value = DEFAULT_DOCUMENT_BODY_XML.encode(encoding="utf-8")
+            api_client.get_property_as_node.return_value = None
 
         document = cls.target_class(uri, api_client=api_client)
         document.content_as_html = Mock(return_value=html)  # type: ignore[method-assign]

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/identifier_resolution.py

@@ -0,0 +1,43 @@
+import json
+from typing import NamedTuple
+
+from caselawclient.models.documents import DocumentURIString
+from caselawclient.xquery_type_dicts import MarkLogicDocumentURIString
+
+
+class IdentifierResolutions(list["IdentifierResolution"]):
+    """
+    A list of candidate MarkLogic documents which correspond to a Public UI uri
+
+    MarkLogic returns a list of dictionaries; IdentifierResolution handles a single dictionary
+    which corresponds to a single identifier to MarkLogic document mapping.
+
+    see `xquery/resolve_from_identifier.xqy` and `resolve_from_identifier` in `Client.py`
+    """
+
+    @staticmethod
+    def from_marklogic_output(table: list[str]) -> "IdentifierResolutions":
+        return IdentifierResolutions(list(IdentifierResolution.from_marklogic_output(row) for row in table))
+
+    def published(self) -> "IdentifierResolutions":
+        "Filter the list so that only published documents are returned"
+        return IdentifierResolutions(list(x for x in self if x.document_published))
+
+
+class IdentifierResolution(NamedTuple):
+    """A single response from MarkLogic about a single identifier / document mapping"""
+
+    identifier_uuid: str
+    document_uri: MarkLogicDocumentURIString
+    identifier_slug: DocumentURIString
+    document_published: bool
+
+    @staticmethod
+    def from_marklogic_output(raw_row: str) -> "IdentifierResolution":
+        row = json.loads(raw_row)
+        return IdentifierResolution(
+            identifier_uuid=row["documents.compiled_url_slugs.identifier_uuid"],
+            document_uri=MarkLogicDocumentURIString(row["documents.compiled_url_slugs.document_uri"]),
+            identifier_slug=DocumentURIString(row["documents.compiled_url_slugs.identifier_slug"]),
+            document_published=row["documents.compiled_url_slugs.document_published"] == "true",
+        )

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/src/caselawclient/models/documents/__init__.py

@@ -15,6 +15,8 @@ from caselawclient.errors import (
     NotSupportedOnVersion,
     OnlySupportedOnVersion,
 )
+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
 from caselawclient.models.utilities.aws import (
     ParserInstructionsDict,
@@ -146,6 +148,8 @@ class Document:
         )
         """ `Document.body` represents the body of the document itself, without any information such as version tracking or properties. """
 
+        self._initialise_identifiers()
+
     def __repr__(self) -> str:
         name = self.body.name or "un-named"
         return f"<{self.document_noun} {self.uri}: {name}>"
@@ -160,6 +164,12 @@ class Document:
         """There is a docx in S3 private bucket for this Document"""
         return check_docx_exists(self.uri)
 
+    def _initialise_identifiers(self) -> None:
+        """Load this document's identifiers from MarkLogic."""
+
+        identifiers_element_as_etree = self.api_client.get_property_as_node(self.uri, "identifiers")
+        self.identifiers = unpack_all_identifiers_from_etree(identifiers_element_as_etree)
+
     @property
     def best_human_identifier(self) -> Optional[str]:
         """
@@ -423,6 +433,12 @@ class Document:
         if not self.is_publishable:
             raise CannotPublishUnpublishableDocument
 
+        ## If it doesn't already have one, get a new FCLID for this document and assign
+        if len(self.identifiers.of_type(FindCaseLawIdentifier)) < 1:
+            document_fclid = FindCaseLawIdentifierSchema.mint(self.api_client)
+            self.identifiers.add(document_fclid)
+            self.save_identifiers()
+
         publish_documents(uri_for_s3(self.uri))
         self.api_client.set_published(self.uri, True)
         announce_document_event(
@@ -521,6 +537,11 @@ class Document:
         """
         return self.docx_exists()
 
+    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)
+
     def __getattr__(self, name: str) -> Any:
         warnings.warn(f"{name} no longer exists on Document, using Document.body instead", DeprecationWarning)
         try:

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/src/caselawclient/models/documents/xml.py

@@ -17,7 +17,7 @@ class XML:
         :raises NonXMLDocumentError: This document is not valid XML
         """
         try:
-            self.xml_as_tree: etree.Element = etree.fromstring(xml_bytestring)
+            self.xml_as_tree: etree._Element = etree.fromstring(xml_bytestring)
         except etree.XMLSyntaxError:
             raise NonXMLDocumentError
 

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/models/identifiers/__init__.py

@@ -0,0 +1,151 @@
+from abc import ABC, abstractmethod
+from typing import Any, Optional, Union
+from uuid import uuid4
+
+from lxml import etree
+
+IDENTIFIER_PACKABLE_ATTRIBUTES: list[str] = [
+    "uuid",
+    "value",
+    "url_slug",
+]
+
+IDENTIFIER_UNPACKABLE_ATTRIBUTES: list[str] = [
+    "uuid",
+    "value",
+]
+
+
+class InvalidIdentifierXMLRepresentationException(Exception):
+    pass
+
+
+class UUIDMismatchError(Exception):
+    pass
+
+
+class IdentifierSchema(ABC):
+    """
+    A base class which describes what an identifier schema should look like.
+    """
+
+    name: str
+    namespace: str
+
+    def __init_subclass__(cls: type["IdentifierSchema"], **kwargs: Any) -> None:
+        """Ensure that subclasses have the required attributes set."""
+        for required in (
+            "name",
+            "namespace",
+        ):
+            if not getattr(cls, required, False):
+                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(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) -> str:
+        """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: str
+
+    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:
+        return f"<{self.schema.name} {self.value}: {self.uuid}>"
+
+    def __init__(self, value: str, uuid: Optional[str] = None) -> None:
+        self.value = value
+        if uuid:
+            self.uuid = uuid
+        else:
+            self.uuid = "id-" + str(uuid4())
+
+    @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 in IDENTIFIER_PACKABLE_ATTRIBUTES:
+            packed_attribute = etree.SubElement(identifier_root, attribute)
+            packed_attribute.text = getattr(self, attribute)
+
+        return identifier_root
+
+    @property
+    def url_slug(self) -> str:
+        return self.schema.compile_identifier_url_slug(self.value)
+
+    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
+
+
+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)
+
+    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

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/models/identifiers/fclid.py

@@ -0,0 +1,48 @@
+import re
+from typing import TYPE_CHECKING
+
+from sqids import Sqids
+
+from . import Identifier, IdentifierSchema
+
+if TYPE_CHECKING:
+    from caselawclient.Client import MarklogicApiClient
+
+
+VALID_FCLID_PATTERN = re.compile(r"^[bcdfghjkmnpqrstvwxyz23456789]{4,}$")
+
+FCLID_MINIMUM_LENGTH = 8
+FCLID_ALPHABET = "bcdfghjkmnpqrstvwxyz23456789"
+
+sqids = Sqids(
+    min_length=FCLID_MINIMUM_LENGTH,
+    alphabet=FCLID_ALPHABET,
+)
+
+
+class FindCaseLawIdentifierSchema(IdentifierSchema):
+    """
+    Identifier schema describing a Find Case Law Identifier.
+    """
+
+    name = "Find Case Law Identifier"
+    namespace = "fclid"
+
+    @classmethod
+    def validate_identifier(cls, value: str) -> bool:
+        return bool(VALID_FCLID_PATTERN.match(value))
+
+    @classmethod
+    def compile_identifier_url_slug(cls, value: str) -> str:
+        return "tna." + value
+
+    @classmethod
+    def mint(cls, api_client: "MarklogicApiClient") -> "FindCaseLawIdentifier":
+        """Generate a totally new Find Case Law identifier."""
+        next_sequence_number = api_client.get_next_document_sequence_number()
+        new_identifier = sqids.encode([next_sequence_number])
+        return FindCaseLawIdentifier(value=new_identifier)
+
+
+class FindCaseLawIdentifier(Identifier):
+    schema = FindCaseLawIdentifierSchema

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/models/identifiers/neutral_citation.py

@@ -0,0 +1,49 @@
+import re
+
+from ds_caselaw_utils import neutral_url
+from ds_caselaw_utils.types import NeutralCitationString
+
+from . import Identifier, IdentifierSchema
+
+VALID_NCN_PATTERN = re.compile(r"(^\[([0-9]{4})\] ([a-zA-Z]+)(?: ([a-zA-Z]+))? ([0-9]+)(?: \(([a-zA-Z]+)\))?$)")
+"""
+This is a catch-all pattern for anything which looks like a Neutral Citation, even if the court itself isn't valid. Checking that an NCN is plausibly correct is handled elsewhere.
+
+This pattern also defines five capture groups to standardise how we interface with the elements:
+
+- `0`: The year of the decision
+- `1`: The court
+- `2`: (Optionally) the jurisdiction or division, depending on the court
+- `3`: The sequence number of the decision
+- `4`: (Optionally) the jurisdiction or division, depending on the court
+
+TODO: When these capture groups are being used in anger (eg to build URL slugs) you should go through and name the groups.
+"""
+
+
+class NeutralCitationNumberSchema(IdentifierSchema):
+    """
+    Identifier schema describing a Neutral Citation Number.
+
+    https://www.iclr.co.uk/knowledge/case-law/neutral-citations/
+    """
+
+    name = "Neutral Citation Number"
+    namespace = "ukncn"
+
+    @classmethod
+    def validate_identifier(cls, value: str) -> bool:
+        return bool(VALID_NCN_PATTERN.match(value))
+
+    @classmethod
+    def compile_identifier_url_slug(cls, value: str) -> str:
+        ncn_based_uri_string = neutral_url(
+            NeutralCitationString(value)
+        )  # TODO: At some point this should move out of utils and into this class.
+        if not ncn_based_uri_string:
+            raise Exception(f"Unable to convert NCN {value} into NCN-based URL slug")
+        return ncn_based_uri_string
+
+
+class NeutralCitationNumber(Identifier):
+    schema = NeutralCitationNumberSchema

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/models/identifiers/unpacker.py

@@ -0,0 +1,46 @@
+from typing import Optional
+
+from lxml import etree
+
+from . import IDENTIFIER_UNPACKABLE_ATTRIBUTES, Identifier, Identifiers, InvalidIdentifierXMLRepresentationException
+from .fclid import FindCaseLawIdentifier
+from .neutral_citation import NeutralCitationNumber
+
+IDENTIFIER_NAMESPACE_MAP: dict[str, type[Identifier]] = {
+    "fclid": FindCaseLawIdentifier,
+    "ukncn": NeutralCitationNumber,
+}
+
+
+def unpack_all_identifiers_from_etree(identifiers_etree: Optional[etree._Element]) -> Identifiers:
+    """This expects the entire <identifiers> tag, and unpacks all Identifiers inside it"""
+    identifiers = Identifiers()
+    if identifiers_etree is None:
+        return identifiers
+    for identifier_etree in identifiers_etree.findall("identifier"):
+        identifier = unpack_an_identifier_from_etree(identifier_etree)
+        identifiers.add(identifier)
+    return identifiers
+
+
+def unpack_an_identifier_from_etree(identifier_xml: etree._Element) -> Identifier:
+    """Given an etree representation of a single identifier, unpack it into an appropriate instance of an Identifier."""
+
+    namespace_element = identifier_xml.find("namespace")
+
+    if namespace_element is None or not namespace_element.text:
+        raise InvalidIdentifierXMLRepresentationException(
+            "Identifer XML representation is not valid: namespace not present or empty"
+        )
+
+    kwargs: dict[str, str] = {}
+
+    for attribute in IDENTIFIER_UNPACKABLE_ATTRIBUTES:
+        element = identifier_xml.find(attribute)
+        if element is None or not element.text:
+            raise InvalidIdentifierXMLRepresentationException(
+                f"Identifer XML representation is not valid: {element} not present or empty"
+            )
+        kwargs[attribute] = element.text
+
+    return IDENTIFIER_NAMESPACE_MAP[namespace_element.text](**kwargs)

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/src/caselawclient/models/utilities/aws.py

@@ -137,12 +137,14 @@ def publish_documents(uri: str) -> None:
     response = client.list_objects(Bucket=private_bucket, Prefix=uri)
 
     for result in response.get("Contents", []):
+        print(f"Contemplating copying {result!r}")
         key = str(result["Key"])
 
         if not key.endswith("parser.log") and not key.endswith(".tar.gz"):
             source: CopySourceTypeDef = {"Bucket": private_bucket, "Key": key}
             extra_args: dict[str, str] = {}
             try:
+                print(f"Copying {key!r} from {private_bucket!r} to {public_bucket!r}")
                 client.copy(source, public_bucket, key, extra_args)
             except botocore.client.ClientError as e:
                 logging.warning(

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/src/caselawclient/xml_helpers.py

@@ -9,8 +9,7 @@ def get_xpath_match_string(
     namespaces: Optional[Dict[str, str]] = None,
     fallback: str = "",
 ) -> str:
-    kwargs = {"namespaces": namespaces} if namespaces else {}
-    return str((node.xpath(path, **kwargs) or [fallback])[0])
+    return str((node.xpath(path, namespaces=namespaces) or [fallback])[0])
 
 
 def get_xpath_match_strings(
@@ -18,5 +17,4 @@ def get_xpath_match_strings(
     path: str,
     namespaces: Optional[Dict[str, str]] = None,
 ) -> list[str]:
-    kwargs = {"namespaces": namespaces} if namespaces else {}
-    return [str(x) for x in node.xpath(path, **kwargs)]
+    return [str(x) for x in node.xpath(path, namespaces=namespaces)]

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/xquery/get_next_document_sequence_number.xqy

@@ -0,0 +1,14 @@
+xquery version "1.0-ml";
+declare option xdmp:transaction-mode "update";
+
+let $_ := xdmp:set-transaction-mode("update")
+let $state_doc := fn:doc("state.xml")
+let $counter_node := $state_doc/state/document_counter
+
+let $current_counter := $counter_node/text()
+let $new_counter := fn:sum(($current_counter, 1))
+
+let $_ := xdmp:node-replace($counter_node, <document_counter>{$new_counter}</document_counter>)
+let $_ := xdmp:commit()
+
+return $new_counter

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/xquery/get_property_as_node.xqy

@@ -0,0 +1,9 @@
+xquery version "1.0-ml";
+
+declare variable $uri as xs:string external;
+
+declare variable $name as xs:string external;
+
+let $prop := fn:QName("", $name)
+
+return xdmp:document-get-properties($uri, $prop)

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/xquery/resolve_from_identifier.xqy

@@ -0,0 +1,17 @@
+xquery version "1.0-ml";
+
+declare namespace xdmp="http://marklogic.com/xdmp"; 
+declare variable $identifier_uri as xs:string external;
+declare variable $published_only as xs:int? external := 1;
+
+let $published_query := if ($published_only) then " AND document_published = 'true'" else ""
+let $query := "SELECT * from compiled_url_slugs WHERE (identifier_slug = @uri)" ||  $published_query
+
+return xdmp:sql(
+  $query,
+  "map",
+  map:new((
+    map:entry("uri", $identifier_uri)
+  ))
+)
+

ds_caselaw_marklogic_api_client-28.2.0/src/caselawclient/xquery/set_property_as_node.xqy

@@ -0,0 +1,11 @@
+xquery version "1.0-ml";
+
+import module namespace dls = "http://marklogic.com/xdmp/dls" at "/MarkLogic/dls.xqy";
+
+declare variable $uri as xs:string external;
+declare variable $value as xs:string external;
+declare variable $name as xs:string external;
+
+let $props := ( element {$name} {xdmp:unquote($value)/*/*} )
+
+return dls:document-set-property($uri, $props)

{ds_caselaw_marklogic_api_client-28.0.0 → ds_caselaw_marklogic_api_client-28.2.0}/src/caselawclient/xquery_type_dicts.py

@@ -113,6 +113,12 @@ class GetPropertyDict(MarkLogicAPIDict):
     uri: MarkLogicDocumentURIString
 
 
+# get_property_as_node.xqy
+class GetPropertyAsNodeDict(MarkLogicAPIDict):
+    name: str
+    uri: MarkLogicDocumentURIString
+
+
 # get_version_annotation.xqy
 class GetVersionAnnotationDict(MarkLogicAPIDict):
     uri: MarkLogicDocumentURIString
@@ -135,6 +141,12 @@ class ListJudgmentVersionsDict(MarkLogicAPIDict):
     uri: MarkLogicDocumentURIString
 
 
+# resolve_from_identifier.xqy
+class ResolveFromIdentifierDict(MarkLogicAPIDict):
+    identifier_uri: DocumentURIString
+    published_only: Optional[int]
+
+
 # set_boolean_property.xqy
 class SetBooleanPropertyDict(MarkLogicAPIDict):
     name: str
@@ -187,6 +199,13 @@ class SetPropertyDict(MarkLogicAPIDict):
     value: str
 
 
+# set_property_as_node.xqy
+class SetPropertyAsNodeDict(MarkLogicAPIDict):
+    name: str
+    uri: MarkLogicDocumentURIString
+    value: str
+
+
 # update_document.xqy
 class UpdateDocumentDict(MarkLogicAPIDict):
     annotation: str