ds-caselaw-marklogic-api-client 29.0.0__tar.gz → 29.0.0a2__tar.gz

{ds_caselaw_marklogic_api_client-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 29.0.0
+Version: 29.0.0a2
 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 (>=2024.12.14,<2024.13.0)
+Requires-Dist: certifi (>=2024.8.30,<2024.9.0)
 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)
@@ -25,7 +25,6 @@ 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-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "29.0.0"
+version = "29.0.0-alpha.2"
 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 = ">=2024.12.14,<2024.13.0"
+certifi = ">=2024.8.30,<2024.9.0"
 charset-normalizer = "^3.0.0"
 django-environ = "^0.11.0"
 idna = "^3.4"
@@ -28,7 +28,6 @@ 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-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/Client.py

@@ -20,7 +20,6 @@ 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,
@@ -1202,22 +1201,3 @@ 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-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/models/documents/__init__.py

@@ -15,8 +15,6 @@ from caselawclient.errors import (
     NotSupportedOnVersion,
     OnlySupportedOnVersion,
 )
-from caselawclient.models.identifiers import Identifier
-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 (
@@ -172,11 +170,13 @@ class Document:
         self.identifiers = unpack_all_identifiers_from_etree(identifiers_element_as_etree)
 
     @property
-    def best_human_identifier(self) -> Optional[Identifier]:
-        """Return the preferred identifier for the document, providing that it is considered human readable."""
-        preferred_identifier = self.identifiers.preferred()
-        if preferred_identifier and preferred_identifier.schema.human_readable:
-            return preferred_identifier
+    def best_human_identifier(self) -> Optional[str]:
+        """
+        Some identifier that is understood by legal professionals to refer to this legal event
+        that is not the name of the document.
+        Typically, this will be the neutral citation number, should it exist.
+        Should typically be overridden in subclasses.
+        """
         return None
 
     @property
@@ -432,12 +432,6 @@ 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(
@@ -506,17 +500,13 @@ class Document:
             "documentType": parser_type_noun,
             "metadata": {
                 "name": self.body.name or None,
-                "cite": None,
+                "cite": self.best_human_identifier or None,
                 "court": self.body.court or None,
                 "date": checked_date,
                 "uri": self.uri,
             },
         }
 
-        ## TODO: Remove this hack around the fact that NCNs are assumed to be present for all documents' metadata, but actually different document classes may have different metadata
-        if hasattr(self, "neutral_citation"):
-            parser_instructions["metadata"]["cite"] = self.neutral_citation
-
         request_parse(
             uri=self.uri,
             reference=self.consignment_reference,
@@ -540,11 +530,6 @@ 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-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/models/identifiers/__init__.py

@@ -32,20 +32,13 @@ class IdentifierSchema(ABC):
     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. """
-
     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):
+            if not getattr(cls, required, False):
                 raise NotImplementedError(f"Can't instantiate IdentifierSchema without {required} attribute.")
         super().__init_subclass__(**kwargs)
 
@@ -108,15 +101,6 @@ class Identifier(ABC):
     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
-
 
 class Identifiers(dict[str, Identifier]):
     def validate(self) -> None:
@@ -125,13 +109,8 @@ class Identifiers(dict[str, Identifier]):
                 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
+        self[identifier.uuid] = identifier
 
     def __delitem__(self, key: Union[Identifier, str]) -> None:
         if isinstance(key, Identifier):
@@ -139,19 +118,6 @@ class Identifiers(dict[str, Identifier]):
         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."""
@@ -162,21 +128,7 @@ class Identifiers(dict[str, Identifier]):
 
         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) == 0:
-            return None
-        return self.by_score(type)[0]
+    def save(self, document) -> None:  # type: ignore[no-untyped-def, unused-ignore]
+        """Save the current state of this Document's identifiers to MarkLogic."""
+        self.validate()
+        document.api_client.set_property_as_node(document.uri, "identifiers", self.as_etree)

{ds_caselaw_marklogic_api_client-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/models/identifiers/neutral_citation.py

@@ -30,8 +30,6 @@ class NeutralCitationNumberSchema(IdentifierSchema):
 
     name = "Neutral Citation Number"
     namespace = "ukncn"
-    human_readable = True
-    base_score_multiplier = 1.5
 
     @classmethod
     def validate_identifier(cls, value: str) -> bool:

{ds_caselaw_marklogic_api_client-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/models/identifiers/unpacker.py

@@ -3,11 +3,9 @@ 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,
 }
 

{ds_caselaw_marklogic_api_client-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/models/judgments.py

@@ -25,17 +25,20 @@ class Judgment(NeutralCitationMixin, Document):
         super().__init__(self.document_noun, uri, *args, **kwargs)
 
     @cached_property
-    def neutral_citation(self) -> Optional[NeutralCitationString]:
-        value_in_xml = self.body.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:cite/text()",
-            {
-                "uk": "https://caselaw.nationalarchives.gov.uk/akn",
-                "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
-            },
+    def neutral_citation(self) -> NeutralCitationString:
+        return NeutralCitationString(
+            self.body.get_xpath_match_string(
+                "/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:cite/text()",
+                {
+                    "uk": "https://caselaw.nationalarchives.gov.uk/akn",
+                    "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
+                },
+            )
         )
-        if value_in_xml:
-            return NeutralCitationString(value_in_xml)
-        return None
+
+    @property
+    def best_human_identifier(self) -> str:
+        return self.neutral_citation
 
     @cached_property
     def linked_document(self) -> Optional["PressSummary"]:

{ds_caselaw_marklogic_api_client-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/models/neutral_citation_mixin.py

@@ -1,10 +1,9 @@
 from abc import ABC, abstractmethod
 from functools import cached_property
-from typing import Any, Optional
+from typing import Any
 
 from ds_caselaw_utils import neutral_url
 from ds_caselaw_utils.types import NeutralCitationString
-from typing_extensions import deprecated
 
 
 class NeutralCitationMixin(ABC):
@@ -39,15 +38,12 @@ class NeutralCitationMixin(ABC):
 
     @cached_property
     @abstractmethod
-    @deprecated("Legacy usage of NCNs is deprecated; you should be moving to the Identifiers framework")
-    def neutral_citation(self) -> Optional[NeutralCitationString]: ...
+    def neutral_citation(self) -> NeutralCitationString: ...
 
     @cached_property
-    @deprecated("Legacy usage of NCNs is deprecated; you should be moving to the Identifiers framework")
     def has_ncn(self) -> bool:
-        return self.neutral_citation is not None and self.neutral_citation != ""
+        return bool(self.neutral_citation)
 
     @cached_property
-    @deprecated("Legacy usage of NCNs is deprecated; you should be moving to the Identifiers framework")
     def has_valid_ncn(self) -> bool:
-        return self.neutral_citation is not None and neutral_url(self.neutral_citation) is not None
+        return self.has_ncn and neutral_url(self.neutral_citation) is not None

{ds_caselaw_marklogic_api_client-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/models/press_summaries.py

@@ -27,16 +27,19 @@ class PressSummary(NeutralCitationMixin, Document):
         super().__init__(self.document_noun, uri, *args, **kwargs)
 
     @cached_property
-    def neutral_citation(self) -> Optional[NeutralCitationString]:
-        value_in_xml = self.body.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:doc/akn:preface/akn:p/akn:neutralCitation/text()",
-            {
-                "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
-            },
+    def neutral_citation(self) -> NeutralCitationString:
+        return NeutralCitationString(
+            self.body.get_xpath_match_string(
+                "/akn:akomaNtoso/akn:doc/akn:preface/akn:p/akn:neutralCitation/text()",
+                {
+                    "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
+                },
+            )
         )
-        if value_in_xml:
-            return NeutralCitationString(value_in_xml)
-        return None
+
+    @property
+    def best_human_identifier(self) -> str:
+        return self.neutral_citation
 
     @cached_property
     def linked_document(self) -> Optional[Judgment]:

{ds_caselaw_marklogic_api_client-29.0.0 → ds_caselaw_marklogic_api_client-29.0.0a2}/src/caselawclient/xquery_type_dicts.py

@@ -141,12 +141,6 @@ 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

ds_caselaw_marklogic_api_client-29.0.0/src/caselawclient/identifier_resolution.py

@@ -1,43 +0,0 @@
-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-29.0.0/src/caselawclient/models/identifiers/fclid.py

@@ -1,50 +0,0 @@
-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"
-    human_readable = False
-    base_score_multiplier = 0.8
-
-    @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-29.0.0/src/caselawclient/xquery/get_next_document_sequence_number.xqy

@@ -1,14 +0,0 @@
-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-29.0.0/src/caselawclient/xquery/resolve_from_identifier.xqy

@@ -1,17 +0,0 @@
-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)
-  ))
-)
-