ds-caselaw-marklogic-api-client 43.0.0__tar.gz → 44.0.1__tar.gz

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ds-caselaw-marklogic-api-client
-Version: 43.0.0
+Version: 44.0.1
 Summary: An API client for interacting with the underlying data in Find Caselaw.
 Keywords: national archives,caselaw
 Author: The National Archives
@@ -9,7 +9,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: boto3 (>=1.26.112,<2.0.0)
-Requires-Dist: certifi (>=2025.10.5,<2025.11.0)
+Requires-Dist: certifi (>=2025.11.12,<2025.12.0)
 Requires-Dist: charset-normalizer (>=3.0.0,<4.0.0)
 Requires-Dist: defusedxml (>=0.7.1,<0.8.0)
 Requires-Dist: django-environ (>=0.12.0)

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "43.0.0"
+version = "44.0.1"
 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 = "^3.12.0"
-certifi = ">=2025.10.5,<2025.11.0"
+certifi = ">=2025.11.12,<2025.12.0"
 charset-normalizer = "^3.0.0"
 django-environ = ">=0.12.0"
 idna = "^3.4"
@@ -33,20 +33,20 @@ defusedxml = "^0.7.1"
 pydantic = "^2.12.3"
 
 [tool.poetry.group.dev.dependencies]
-coverage = "7.11.0"
-pytest = "8.4.2"
+coverage = "7.12.0"
+pytest = "9.0.1"
 pytest-cov = "7.0.0"
 beautifulsoup4 = "4.14.2"
 responses = "0.25.8"
 python-dotenv = "1.2.1"
 time-machine = "2.19.0"
-moto = {version = "5.1.15", extras = ["all"]}
+moto = {version = "5.1.17", extras = ["all"]}
 
 [tool.poetry.group.docs]
 optional = true
 
 [tool.poetry.group.docs.dependencies]
-pdoc = "^15.0.0"
+pdoc = "^16.0.0"
 
 
 [tool.commitizen]

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/src/caselawclient/factories.py

@@ -20,7 +20,7 @@ T = TypeVar("T")
 
 DEFAULT_DOCUMENT_BODY_XML = """<akomaNtoso xmlns="http://docs.oasis-open.org/legaldocml/ns/akn/3.0" xmlns:uk="https://caselaw.nationalarchives.gov.uk/akn">
             <judgment name="decision">
-                <meta/><header/>
+                <meta/><header><p>Header contains text</p></header>
                 <judgmentBody>
                 <decision>
                 <p>This is a document.</p>

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/src/caselawclient/models/documents/__init__.py

@@ -26,6 +26,7 @@ from caselawclient.models.utilities import VersionsDict, extract_version, render
 from caselawclient.models.utilities.aws import (
     ParserInstructionsDict,
     announce_document_event,
+    are_unpublished_assets_clean,
     check_docx_exists,
     delete_documents_from_private_bucket,
     generate_docx_url,
@@ -102,6 +103,11 @@ class Document:
             True,
             "There is another document with identical content",
         ),
+        (
+            "has_only_clean_assets",
+            True,
+            "An uncleaned asset exists for this document",
+        ),
     ]
     """
     A list of tuples in the form:
@@ -252,7 +258,7 @@ class Document:
         """
         if self.is_version:
             raise NotSupportedOnVersion(
-                "Cannot get versions of a version for {self.uri}",
+                f"Cannot get versions of a version for {self.uri}",
             )
         docs = []
         for version in self.versions:
@@ -370,6 +376,11 @@ class Document:
         """Check if the content hash of this document is unique compared to all other documents in MarkLogic."""
         return self.api_client.has_unique_content_hash(self.uri)
 
+    @cached_property
+    def has_only_clean_assets(self) -> bool:
+        """False if any non-tar.gz assets associated with this document have not been cleaned."""
+        return are_unpublished_assets_clean(self.uri)
+
     @cached_property
     def version_created_datetime(self) -> datetime.datetime:
         return self.api_client.get_version_created_datetime(self.uri)

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/src/caselawclient/models/documents/body.py

@@ -177,7 +177,7 @@ class DocumentBody:
     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."""
-        trailing_tags = self._xml.xml_as_tree.xpath("//*[preceding::akn:meta]", namespaces=DEFAULT_NAMESPACES)
+        trailing_tags = self._xml.xml_as_tree.xpath("//akn:header/*", namespaces=DEFAULT_NAMESPACES)
         for tag in trailing_tags:
             if tag.tail and tag.tail.strip():
                 return True

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/src/caselawclient/models/utilities/aws.py

@@ -231,6 +231,26 @@ def copy_assets(old_uri: DocumentURIString, new_uri: DocumentURIString) -> None:
             )
 
 
+def are_unpublished_assets_clean(uri: DocumentURIString) -> bool:
+    """Returns true if all non-tar.gz assets in the relevant S3 bucket have been cleaned
+    (they have a DOCUMENT_PROCESSOR_VERSION tag)
+    Note: if there are no assets, then this returns true."""
+    client = create_s3_client()
+    bucket = env("PRIVATE_ASSET_BUCKET")
+    response = client.list_objects(Bucket=bucket, Prefix=uri_for_s3(uri))
+    for result in response.get("Contents", []):
+        file_key = str(result["Key"])
+        # ignore original tar.gz files
+        if file_key.endswith(".tar.gz"):
+            continue
+
+        # check if assets are tagged as being processed by S3
+        tag_response = client.get_object_tagging(Bucket=bucket, Key=file_key)
+        if not (any(tag["Key"] == "DOCUMENT_PROCESSOR_VERSION" for tag in tag_response["TagSet"])):
+            return False
+    return True
+
+
 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"""

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/src/caselawclient/xquery/get_judgment.xqy

@@ -11,7 +11,7 @@ declare variable $version_uri as xs:string? external;
 declare variable $search_query as xs:string? external;
 
 (: Note that `xsl:output method` is changed from `html` to `xml` and we've namespaced the tag :)
-let $number_marks_xslt := (
+let $delete_meta_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"
@@ -25,16 +25,6 @@ let $number_marks_xslt := (
     <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:number count="//uk:mark" level="any" from="//*[ancestor::akn:meta]" />
-          </xsl:attribute>
-          <xsl:apply-templates />
-      </xsl:copy>
-    </xsl:template>
   </xsl:stylesheet>
 )
 
@@ -56,7 +46,7 @@ let $raw_xml := if ($show_unpublished) then
 (: If a search query string is present, highlight instances :)
 let $transformed := if($search_query) then
       xdmp:xslt-eval(
-        $number_marks_xslt,
+        $delete_meta_marks_xslt,
         cts:highlight(
           $raw_xml,
           helper:make-q-query($search_query),

{ds_caselaw_marklogic_api_client-43.0.0 → ds_caselaw_marklogic_api_client-44.0.1}/src/caselawclient/xquery/xslt_transform.xqy

@@ -17,27 +17,6 @@ let $xsl_path := fn:concat("judgments/xslts/", $xsl_filename)
 
 let $params := map:map()
 
-let $number_marks_xslt := (
-  <xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
-                  version="2.0">
-    <xsl:output method="html" />
-    <xsl:template match="@*|node()">
-      <xsl:copy>
-        <xsl:apply-templates select="@*|node()"/>
-      </xsl:copy>
-    </xsl:template>
-    <xsl:template match="mark">
-      <xsl:copy>
-          <xsl:copy-of select="*" />
-          <xsl:attribute name="id">
-              <xsl:text>mark_</xsl:text>
-              <xsl:value-of select="count(preceding::mark)"/>
-          </xsl:attribute>
-          <xsl:apply-templates />
-      </xsl:copy>
-    </xsl:template>
-  </xsl:stylesheet>
-)
 (: change the image-base of the document to match the location of the assets in $image_base
    so that references to images point to the correct places on the internet :)
 let $_put := map:put(
@@ -59,13 +38,10 @@ let $retrieved_value := if (xs:boolean($is_published) or $show_unpublished) then
         ()
 
 let $return_value := if($query) then
-      xdmp:xslt-eval(
-        $number_marks_xslt,
-        cts:highlight(
-          $retrieved_value,
-          helper:make-q-query($query),
-          <mark>{$cts:text}</mark>
-        )
+      cts:highlight(
+        $retrieved_value,
+        helper:make-q-query($query),
+        <mark>{$cts:text}</mark>
       )
     else
       $retrieved_value