ds-caselaw-marklogic-api-client 29.1.0__tar.gz → 29.2.0__tar.gz

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 29.1.0
+Version: 29.2.0
 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
@@ -13,7 +13,7 @@ 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: charset-normalizer (>=3.0.0,<4.0.0)
-Requires-Dist: django-environ (>=0.11.0,<0.12.0)
+Requires-Dist: django-environ (>=0.12.0)
 Requires-Dist: ds-caselaw-utils (>=2.0.0,<3.0.0)
 Requires-Dist: idna (>=3.4,<4.0)
 Requires-Dist: lxml (>=5.0.0,<6.0.0)

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "29.1.0"
+version = "29.2.0"
 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"
@@ -14,7 +14,7 @@ packages = [
 python = "^3.9"
 certifi = ">=2024.12.14,<2024.13.0"
 charset-normalizer = "^3.0.0"
-django-environ = "^0.11.0"
+django-environ = ">=0.12.0"
 idna = "^3.4"
 requests = "^2.28.2"
 requests-toolbelt = ">=0.10.1,<1.1.0"
@@ -52,6 +52,8 @@ tag_format = "v$version"
 version_scheme = "semver2"
 version_provider = "poetry"
 update_changelog_on_bump = true
+changelog_incremental = true
+
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/src/caselawclient/errors.py

@@ -37,9 +37,7 @@ class MarklogicResourceUnmanagedError(MarklogicAPIError):
 
     status_code = 404
     default_message = (
-        "The resource isn't managed. "
-        "It probably doesn't exist, and if it does, that's a problem. "
-        "Please report it."
+        "The resource isn't managed. It probably doesn't exist, and if it does, that's a problem. Please report it."
     )
 
 

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/src/caselawclient/models/documents/__init__.py

@@ -29,7 +29,6 @@ from caselawclient.models.utilities.aws import (
     publish_documents,
     request_parse,
     unpublish_documents,
-    uri_for_s3,
 )
 
 from .body import DocumentBody
@@ -216,11 +215,11 @@ class Document:
 
     @property
     def docx_url(self) -> str:
-        return generate_docx_url(uri_for_s3(self.uri))
+        return generate_docx_url(self.uri)
 
     @property
     def pdf_url(self) -> str:
-        return generate_pdf_url(uri_for_s3(self.uri))
+        return generate_pdf_url(self.uri)
 
     @cached_property
     def assigned_to(self) -> str:
@@ -438,7 +437,7 @@ class Document:
             self.identifiers.add(document_fclid)
             self.save_identifiers()
 
-        publish_documents(uri_for_s3(self.uri))
+        publish_documents(self.uri)
         self.api_client.set_published(self.uri, True)
         announce_document_event(
             uri=self.uri,
@@ -448,7 +447,7 @@ class Document:
 
     def unpublish(self) -> None:
         self.api_client.break_checkout(self.uri)
-        unpublish_documents(uri_for_s3(self.uri))
+        unpublish_documents(self.uri)
         self.api_client.set_published(self.uri, False)
         announce_document_event(
             uri=self.uri,

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/src/caselawclient/models/documents/body.py

@@ -91,8 +91,7 @@ class DocumentBody:
     ) -> list[datetime.datetime]:
         name_filter = f"[@name='{name}']" if name else ""
         iso_datetimes = self._xml.get_xpath_match_strings(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:identification/akn:FRBRManifestation"
-            f"/akn:FRBRdate{name_filter}/@date",
+            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"},
         )
 

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/src/caselawclient/models/neutral_citation_mixin.py

@@ -23,11 +23,6 @@ class NeutralCitationMixin(ABC):
 
     def __init__(self, document_noun: str, *args: Any, **kwargs: Any) -> None:
         self.attributes_to_validate: list[tuple[str, bool, str]] = self.attributes_to_validate + [
-            (
-                "has_ncn",
-                True,
-                f"This {document_noun} has no neutral citation number",
-            ),
             (
                 "has_valid_ncn",
                 True,
@@ -50,4 +45,6 @@ class NeutralCitationMixin(ABC):
     @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
+        if self.neutral_citation is None:
+            return True
+        return neutral_url(self.neutral_citation) is not None

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/src/caselawclient/models/utilities/aws.py

@@ -2,7 +2,7 @@ import datetime
 import json
 import logging
 import uuid
-from typing import Any, Literal, Optional, TypedDict, overload
+from typing import TYPE_CHECKING, Any, Literal, Optional, TypedDict, overload
 
 import boto3
 import botocore.client
@@ -13,9 +13,21 @@ 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
+
 env = environ.Env()
 
 
+class S3PrefixString(str):
+    def __new__(cls, content: str) -> "S3PrefixString":
+        if content[-1] != "/":
+            raise RuntimeError("S3 Prefixes must end in / so they behave like directories")
+        return str.__new__(cls, content)
+
+
 class ParserInstructionsMetadataDict(TypedDict):
     name: Optional[str]
     cite: Optional[str]
@@ -58,8 +70,9 @@ def create_sns_client() -> SNSClient:
     return create_aws_client("sns")
 
 
-def uri_for_s3(uri: str) -> str:
-    return uri.lstrip("/")
+def uri_for_s3(uri: DocumentURIString) -> S3PrefixString:
+    """An S3 Prefix must end with / to avoid uksc/2004/1 matching uksc/2004/1000"""
+    return S3PrefixString(uri + "/")
 
 
 def generate_signed_asset_url(key: str) -> str:
@@ -79,7 +92,7 @@ def generate_signed_asset_url(key: str) -> str:
     )
 
 
-def check_docx_exists(uri: str) -> bool:
+def check_docx_exists(uri: DocumentURIString) -> bool:
     """Does the docx for a document URI actually exist?"""
     bucket = env("PRIVATE_ASSET_BUCKET", None)
     s3_key = generate_docx_key(uri)
@@ -93,25 +106,25 @@ def check_docx_exists(uri: str) -> bool:
         raise
 
 
-def generate_docx_key(uri: str) -> str:
+def generate_docx_key(uri: DocumentURIString) -> str:
     """from a canonical caselaw URI (eat/2022/1) return the S3 key of the associated docx"""
-    return f'{uri}/{uri.replace("/", "_")}.docx'
+    return f"{uri}/{uri.replace('/', '_')}.docx"
 
 
-def generate_docx_url(uri: str) -> str:
+def generate_docx_url(uri: DocumentURIString) -> str:
     """from a canonical caselaw URI (eat/2022/1) return a signed S3 link for the front end"""
     return generate_signed_asset_url(generate_docx_key(uri))
 
 
-def generate_pdf_url(uri: str) -> str:
-    key = f'{uri}/{uri.replace("/", "_")}.pdf'
+def generate_pdf_url(uri: DocumentURIString) -> str:
+    key = f"{uri}/{uri.replace('/', '_')}.pdf"
 
     return generate_signed_asset_url(key)
 
 
-def delete_from_bucket(uri: str, bucket: str) -> None:
+def delete_from_bucket(uri: DocumentURIString, bucket: str) -> None:
     client = create_s3_client()
-    response = client.list_objects(Bucket=bucket, Prefix=uri)
+    response = client.list_objects(Bucket=bucket, Prefix=uri_for_s3(uri))
 
     if response.get("Contents"):
         objects_to_delete: list[ObjectIdentifierTypeDef] = [{"Key": obj["Key"]} for obj in response.get("Contents", [])]
@@ -123,7 +136,7 @@ def delete_from_bucket(uri: str, bucket: str) -> None:
         )
 
 
-def publish_documents(uri: str) -> None:
+def publish_documents(uri: DocumentURIString) -> None:
     """
     Copy assets from the unpublished bucket to the published one.
     Don't copy parser logs and package tar gz.
@@ -134,7 +147,7 @@ def publish_documents(uri: str) -> None:
     public_bucket = env("PUBLIC_ASSET_BUCKET")
     private_bucket = env("PRIVATE_ASSET_BUCKET")
 
-    response = client.list_objects(Bucket=private_bucket, Prefix=uri)
+    response = client.list_objects(Bucket=private_bucket, Prefix=uri_for_s3(uri))
 
     for result in response.get("Contents", []):
         print(f"Contemplating copying {result!r}")
@@ -152,15 +165,15 @@ def publish_documents(uri: str) -> None:
                 )
 
 
-def unpublish_documents(uri: str) -> None:
+def unpublish_documents(uri: DocumentURIString) -> None:
     delete_from_bucket(uri, env("PUBLIC_ASSET_BUCKET"))
 
 
-def delete_documents_from_private_bucket(uri: str) -> None:
+def delete_documents_from_private_bucket(uri: DocumentURIString) -> None:
     delete_from_bucket(uri, env("PRIVATE_ASSET_BUCKET"))
 
 
-def announce_document_event(uri: str, status: str, enrich: bool = False) -> None:
+def announce_document_event(uri: DocumentURIString, status: str, enrich: bool = False) -> None:
     client = create_sns_client()
 
     message_attributes: dict[str, MessageAttributeValueTypeDef] = {}
@@ -186,17 +199,14 @@ def announce_document_event(uri: str, status: str, enrich: bool = False) -> None
     )
 
 
-def copy_assets(old_uri: str, new_uri: str) -> None:
+def copy_assets(old_uri: DocumentURIString, new_uri: DocumentURIString) -> None:
     """
     Copy *unpublished* assets from one path to another,
     renaming DOCX and PDF files as appropriate.
     """
     client = create_s3_client()
     bucket = env("PRIVATE_ASSET_BUCKET")
-    old_uri = uri_for_s3(old_uri)
-    new_uri = uri_for_s3(new_uri)
-
-    response = client.list_objects(Bucket=bucket, Prefix=old_uri)
+    response = client.list_objects(Bucket=bucket, Prefix=uri_for_s3(old_uri))
 
     for result in response.get("Contents", []):
         old_key = str(result["Key"])
@@ -212,7 +222,7 @@ def copy_assets(old_uri: str, new_uri: str) -> None:
             )
 
 
-def build_new_key(old_key: str, new_uri: str) -> str:
+def build_new_key(old_key: str, new_uri: DocumentURIString) -> str:
     """Ensure that DOCX and PDF filenames are modified to reflect their new home
     as we get the name of the new S3 path"""
     old_filename = old_key.rsplit("/", 1)[-1]
@@ -224,7 +234,7 @@ def build_new_key(old_key: str, new_uri: str) -> str:
 
 
 def request_parse(
-    uri: str,
+    uri: DocumentURIString,
     reference: Optional[str],
     parser_instructions: Optional[ParserInstructionsDict] = None,
 ) -> None:

{ds_caselaw_marklogic_api_client-29.1.0 → ds_caselaw_marklogic_api_client-29.2.0}/src/caselawclient/xquery/get_judgment.xqy

@@ -14,6 +14,7 @@ declare variable $search_query as xs:string? external;
 let $number_marks_xslt := (
   <xsl:stylesheet 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"
                   version="2.0">
     <xsl:output method="xml" />
     <xsl:template match="@*|node()">
@@ -21,12 +22,15 @@ let $number_marks_xslt := (
         <xsl:apply-templates select="@*|node()"/>
       </xsl:copy>
     </xsl:template>
+    <xsl:template match="//akn:meta//uk:mark">
+          <xsl:apply-templates />
+    </xsl:template>
     <xsl:template match="uk:mark">
       <xsl:copy>
           <xsl:copy-of select="@*" />
           <xsl:attribute name="id">
               <xsl:text>mark_</xsl:text>
-              <xsl:value-of select="count(preceding::uk:mark)"/>
+              <xsl:number count="//uk:mark" level="any" from="//*[ancestor::akn:meta]" />
           </xsl:attribute>
           <xsl:apply-templates />
       </xsl:copy>
@@ -62,5 +66,4 @@ let $transformed := if($search_query) then
     else
       $raw_xml
 
-
 return $transformed