ds-caselaw-marklogic-api-client 29.2.0__tar.gz → 30.0.0__tar.gz

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 29.2.0
+Version: 30.0.0
 Summary: An API client for interacting with the underlying data in Find Caselaw.
 Home-page: https://github.com/nationalarchives/ds-caselaw-custom-api-client
 Keywords: national archives,caselaw

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "29.2.0"
+version = "30.0.0"
 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"

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/Client.py

@@ -25,12 +25,12 @@ from caselawclient.models.documents import (
     DOCUMENT_COLLECTION_URI_JUDGMENT,
     DOCUMENT_COLLECTION_URI_PRESS_SUMMARY,
     Document,
-    DocumentURIString,
 )
 from caselawclient.models.judgments import Judgment
 from caselawclient.models.press_summaries import PressSummary
 from caselawclient.models.utilities import move
 from caselawclient.search_parameters import SearchParameters
+from caselawclient.types import DocumentURIString
 from caselawclient.xquery_type_dicts import (
     MarkLogicDocumentURIString,
     MarkLogicDocumentVersionURIString,
@@ -1203,17 +1203,40 @@ class MarklogicApiClient:
 
         return results
 
-    def resolve_from_identifier(self, identifier_uri: str, published_only: bool = True) -> IdentifierResolutions:
+    def resolve_from_identifier_slug(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 = {
+        vars: query_dicts.ResolveFromIdentifierSlugDict = {
             "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",
+                "resolve_from_identifier_slug.xqy",
+            ),
+        )
+        return IdentifierResolutions.from_marklogic_output(raw_results)
+
+    def resolve_from_identifier(self, identifier_uri: str, published_only: bool = True) -> IdentifierResolutions:
+        warnings.warn(
+            "resolve_from_identifier deprecated, use resolve_from_identifier_slug instead", DeprecationWarning
+        )
+        return self.resolve_from_identifier(identifier_uri, published_only)
+
+    def resolve_from_identifier_value(
+        self, identifier_value: 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.ResolveFromIdentifierValueDict = {
+            "identifier_value": identifier_value,
+            "published_only": int(published_only),
+        }
+        raw_results: list[str] = get_multipart_strings_from_marklogic_response(
+            self._send_to_eval(
+                vars,
+                "resolve_from_identifier_value.xqy",
             ),
         )
         return IdentifierResolutions.from_marklogic_output(raw_results)

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/factories.py

@@ -5,11 +5,12 @@ from unittest.mock import Mock
 from typing_extensions import TypeAlias
 
 from caselawclient.Client import MarklogicApiClient
-from caselawclient.models.documents import Document, DocumentURIString
+from caselawclient.models.documents import Document
 from caselawclient.models.documents.body import DocumentBody
 from caselawclient.models.judgments import Judgment
 from caselawclient.models.press_summaries import PressSummary
 from caselawclient.responses.search_result import SearchResult, SearchResultMetadata
+from caselawclient.types import DocumentURIString
 
 DEFAULT_DOCUMENT_BODY_XML = "<akomantoso>This is some XML of a judgment.</akomantoso>"
 

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/identifier_resolution.py

@@ -1,7 +1,9 @@
 import json
 from typing import NamedTuple
 
-from caselawclient.models.documents import DocumentURIString
+from caselawclient.models.identifiers import Identifier
+from caselawclient.models.identifiers.unpacker import IDENTIFIER_NAMESPACE_MAP
+from caselawclient.types import DocumentURIString
 from caselawclient.xquery_type_dicts import MarkLogicDocumentURIString
 
 
@@ -12,7 +14,7 @@ class IdentifierResolutions(list["IdentifierResolution"]):
     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`
+    see `xquery/resolve_from_identifier_slug.xqy` and `resolve_from_identifier` in `Client.py`
     """
 
     @staticmethod
@@ -31,13 +33,20 @@ class IdentifierResolution(NamedTuple):
     document_uri: MarkLogicDocumentURIString
     identifier_slug: DocumentURIString
     document_published: bool
+    identifier_value: str
+    identifier_namespace: str
+    identifier_type: type[Identifier]
 
     @staticmethod
     def from_marklogic_output(raw_row: str) -> "IdentifierResolution":
         row = json.loads(raw_row)
+        identifier_namespace = row["documents.compiled_url_slugs.identifier_namespace"]
         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",
+            identifier_value=row["documents.compiled_url_slugs.identifier_value"],
+            identifier_namespace=identifier_namespace,
+            identifier_type=IDENTIFIER_NAMESPACE_MAP[identifier_namespace],
         )

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/models/documents/__init__.py

@@ -30,9 +30,10 @@ from caselawclient.models.utilities.aws import (
     request_parse,
     unpublish_documents,
 )
+from caselawclient.types import DocumentURIString
 
 from .body import DocumentBody
-from .exceptions import CannotPublishUnpublishableDocument, DocumentNotSafeForDeletion, InvalidDocumentURIException
+from .exceptions import 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)
@@ -49,28 +50,6 @@ if TYPE_CHECKING:
     from caselawclient.Client import MarklogicApiClient
 
 
-class DocumentURIString(str):
-    """
-    This class checks that the string is actually a valid Document URI on creation. It does _not_ manipulate the string.
-    """
-
-    def __new__(cls, content: str) -> "DocumentURIString":
-        # Check that the URI doesn't begin or end with a slash
-        if content[0] == "/" or content[-1] == "/":
-            raise InvalidDocumentURIException(
-                f'"{content}" is not a valid document URI; URIs cannot begin or end with slashes.'
-            )
-
-        # Check that the URI doesn't contain a full stop
-        if "." in content:
-            raise InvalidDocumentURIException(
-                f'"{content}" is not a valid document URI; URIs cannot contain full stops.'
-            )
-
-        # If everything is good, return as usual
-        return str.__new__(cls, content)
-
-
 class Document:
     """
     A base class from which all other document types are extensions. This class includes the essential methods for

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/models/documents/body.py

@@ -3,6 +3,7 @@ import os
 import warnings
 from functools import cache, cached_property
 from typing import Optional
+from xml.etree.ElementTree import Element
 
 import pytz
 from ds_caselaw_utils.types import CourtCode
@@ -12,6 +13,11 @@ from caselawclient.models.utilities.dates import parse_string_date_as_utc
 
 from .xml import XML
 
+DEFAULT_NAMESPACES = {
+    "uk": "https://caselaw.nationalarchives.gov.uk/akn",
+    "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
+}
+
 
 class UnparsableDate(Warning):
     pass
@@ -26,35 +32,25 @@ class DocumentBody:
         self._xml = XML(xml_bytestring=xml_bytestring)
         """ This is an instance of the `Document.XML` class for manipulation of the XML document itself. """
 
-    def get_xpath_match_string(self, xpath: str, namespaces: dict[str, str]) -> str:
+    def get_xpath_match_string(self, xpath: str, namespaces: dict[str, str] = DEFAULT_NAMESPACES) -> str:
         return self._xml.get_xpath_match_string(xpath, namespaces)
 
+    def get_xpath_match_strings(self, xpath: str, namespaces: dict[str, str] = DEFAULT_NAMESPACES) -> list[str]:
+        return self._xml.get_xpath_match_strings(xpath, namespaces)
+
     @cached_property
     def name(self) -> str:
-        return self._xml.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:identification/akn:FRBRWork/akn:FRBRname/@value",
-            {"akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0"},
+        return self.get_xpath_match_string(
+            "/akn:akomaNtoso/akn:*/akn:meta/akn:identification/akn:FRBRWork/akn:FRBRname/@value"
         )
 
     @cached_property
     def court(self) -> str:
-        return self._xml.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:court/text()",
-            {
-                "uk": "https://caselaw.nationalarchives.gov.uk/akn",
-                "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
-            },
-        )
+        return self.get_xpath_match_string("/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:court/text()")
 
     @cached_property
     def jurisdiction(self) -> str:
-        return self._xml.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:jurisdiction/text()",
-            {
-                "uk": "https://caselaw.nationalarchives.gov.uk/akn",
-                "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
-            },
-        )
+        return self.get_xpath_match_string("/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:jurisdiction/text()")
 
     @property
     def court_and_jurisdiction_identifier_string(self) -> CourtCode:
@@ -64,9 +60,8 @@ class DocumentBody:
 
     @cached_property
     def document_date_as_string(self) -> str:
-        return self._xml.get_xpath_match_string(
+        return self.get_xpath_match_string(
             "/akn:akomaNtoso/akn:*/akn:meta/akn:identification/akn:FRBRWork/akn:FRBRdate/@date",
-            {"akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0"},
         )
 
     @cached_property
@@ -90,9 +85,8 @@ class DocumentBody:
         name: Optional[str] = None,
     ) -> list[datetime.datetime]:
         name_filter = f"[@name='{name}']" if name else ""
-        iso_datetimes = self._xml.get_xpath_match_strings(
+        iso_datetimes = self.get_xpath_match_strings(
             f"/akn:akomaNtoso/akn:*/akn:meta/akn:identification/akn:FRBRManifestation/akn:FRBRdate{name_filter}/@date",
-            {"akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0"},
         )
 
         return [parse_string_date_as_utc(event, pytz.UTC) for event in iso_datetimes]
@@ -130,9 +124,23 @@ class DocumentBody:
     def content_as_xml(self) -> str:
         return self._xml.xml_as_string
 
+    @cached_property
+    def has_content(self) -> bool:
+        """If we do not have a word document, the XML will not contain
+        the contents of the judgment, but will contain a preamble."""
+
+        def stripped_tag_text(tag: Element) -> str:
+            return "".join(tag.itertext()).strip()
+
+        header = self._xml.xml_as_tree.xpath("//akn:header", namespaces=DEFAULT_NAMESPACES)[0]
+        content = self._xml.xml_as_tree.xpath("//akn:judgmentBody", namespaces=DEFAULT_NAMESPACES)[0]
+        return not (stripped_tag_text(header) == "" and stripped_tag_text(content) == "")
+
     @cache
-    def content_as_html(self, image_base_url: Optional[str] = None) -> str:
+    def content_as_html(self, image_base_url: Optional[str] = None) -> Optional[str]:
         """Convert the XML representation of the Document into HTML for rendering."""
+        if not self.has_content:
+            return None
 
         html_xslt_location = os.path.join(os.path.dirname(os.path.realpath(__file__)), "transforms", "html.xsl")
 

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/models/documents/exceptions.py

@@ -4,7 +4,3 @@ class CannotPublishUnpublishableDocument(Exception):
 
 class DocumentNotSafeForDeletion(Exception):
     """A document which is not safe for deletion cannot be deleted."""
-
-
-class InvalidDocumentURIException(Exception):
-    """The document URI is not valid."""

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/models/judgments.py

@@ -10,7 +10,9 @@ from caselawclient.models.neutral_citation_mixin import NeutralCitationMixin
 if TYPE_CHECKING:
     from caselawclient.models.press_summaries import PressSummary
 
-from .documents import Document, DocumentURIString
+from caselawclient.types import DocumentURIString
+
+from .documents import Document
 
 
 class Judgment(NeutralCitationMixin, Document):

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/models/press_summaries.py

@@ -8,8 +8,9 @@ from ds_caselaw_utils.types import NeutralCitationString
 
 from caselawclient.errors import DocumentNotFoundError
 from caselawclient.models.neutral_citation_mixin import NeutralCitationMixin
+from caselawclient.types import DocumentURIString
 
-from .documents import Document, DocumentURIString
+from .documents import Document
 
 if TYPE_CHECKING:
     from caselawclient.models.judgments import Judgment

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/models/utilities/aws.py

@@ -2,7 +2,7 @@ import datetime
 import json
 import logging
 import uuid
-from typing import TYPE_CHECKING, Any, Literal, Optional, TypedDict, overload
+from typing import Any, Literal, Optional, TypedDict, overload
 
 import boto3
 import botocore.client
@@ -13,10 +13,7 @@ from mypy_boto3_sns.client import SNSClient
 from mypy_boto3_sns.type_defs import MessageAttributeValueTypeDef
 from typing_extensions import NotRequired
 
-if TYPE_CHECKING:
-    from caselawclient.models.documents import DocumentURIString
-else:
-    DocumentURIString = None
+from caselawclient.types import DocumentURIString
 
 env = environ.Env()
 

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/models/utilities/move.py

@@ -4,8 +4,8 @@ import ds_caselaw_utils as caselawutils
 from ds_caselaw_utils.types import NeutralCitationString
 
 from caselawclient.errors import MarklogicAPIError
-from caselawclient.models.documents import DocumentURIString
 from caselawclient.models.utilities.aws import copy_assets
+from caselawclient.types import DocumentURIString
 
 if TYPE_CHECKING:
     from caselawclient.Client import MarklogicApiClient

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/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.documents import DocumentURIString
+from caselawclient.types import DocumentURIString
 from caselawclient.xml_helpers import get_xpath_match_string
 
 

ds_caselaw_marklogic_api_client-30.0.0/src/caselawclient/types.py

@@ -0,0 +1,24 @@
+class InvalidDocumentURIException(Exception):
+    """The document URI is not valid."""
+
+
+class DocumentURIString(str):
+    """
+    This class checks that the string is actually a valid Document URI on creation. It does _not_ manipulate the string.
+    """
+
+    def __new__(cls, content: str) -> "DocumentURIString":
+        # Check that the URI doesn't begin or end with a slash
+        if content[0] == "/" or content[-1] == "/":
+            raise InvalidDocumentURIException(
+                f'"{content}" is not a valid document URI; URIs cannot begin or end with slashes.'
+            )
+
+        # Check that the URI doesn't contain a full stop
+        if "." in content:
+            raise InvalidDocumentURIException(
+                f'"{content}" is not a valid document URI; URIs cannot contain full stops.'
+            )
+
+        # If everything is good, return as usual
+        return str.__new__(cls, content)

ds_caselaw_marklogic_api_client-30.0.0/src/caselawclient/xquery/resolve_from_identifier_value.xqy

@@ -0,0 +1,17 @@
+xquery version "1.0-ml";
+
+declare namespace xdmp="http://marklogic.com/xdmp"; 
+declare variable $identifier_value 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_value = @value)" ||  $published_query
+
+return xdmp:sql(
+  $query,
+  "map",
+  map:new((
+    map:entry("value", $identifier_value)
+  ))
+)
+

{ds_caselaw_marklogic_api_client-29.2.0 → ds_caselaw_marklogic_api_client-30.0.0}/src/caselawclient/xquery_type_dicts.py

@@ -7,7 +7,7 @@ checks. They are used to enforce appropriately typed variables being passed in t
 """
 
 from typing import Any, NewType, Optional, TypedDict
-from caselawclient.models.documents import DocumentURIString
+from caselawclient.types import DocumentURIString
 
 MarkLogicDocumentURIString = NewType("MarkLogicDocumentURIString", str)
 MarkLogicDocumentVersionURIString = NewType("MarkLogicDocumentVersionURIString", MarkLogicDocumentURIString)
@@ -141,12 +141,18 @@ class ListJudgmentVersionsDict(MarkLogicAPIDict):
     uri: MarkLogicDocumentURIString
 
 
-# resolve_from_identifier.xqy
-class ResolveFromIdentifierDict(MarkLogicAPIDict):
+# resolve_from_identifier_slug.xqy
+class ResolveFromIdentifierSlugDict(MarkLogicAPIDict):
     identifier_uri: DocumentURIString
     published_only: Optional[int]
 
 
+# resolve_from_identifier_value.xqy
+class ResolveFromIdentifierValueDict(MarkLogicAPIDict):
+    identifier_value: str
+    published_only: Optional[int]
+
+
 # set_boolean_property.xqy
 class SetBooleanPropertyDict(MarkLogicAPIDict):
     name: str