ds-caselaw-marklogic-api-client 39.0.0__tar.gz → 39.1.0__tar.gz

{ds_caselaw_marklogic_api_client-39.0.0 → ds_caselaw_marklogic_api_client-39.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ds-caselaw-marklogic-api-client
-Version: 39.0.0
+Version: 39.1.0
 Summary: An API client for interacting with the underlying data in Find Caselaw.
 Keywords: national archives,caselaw
 Author: The National Archives
@@ -13,6 +13,7 @@ Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: boto3 (>=1.26.112,<2.0.0)
 Requires-Dist: certifi (>=2025.7.9,<2025.8.0)
 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)
 Requires-Dist: ds-caselaw-utils (>=2.0.0,<3.0.0)
 Requires-Dist: idna (>=3.4,<4.0)

{ds_caselaw_marklogic_api_client-39.0.0 → ds_caselaw_marklogic_api_client-39.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "39.0.0"
+version = "39.1.0"
 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"
@@ -29,9 +29,10 @@ pytz = ">2024"
 python-dateutil = "^2.9.0-post.0"
 saxonche = "^12.5.0"
 sqids = "^0.5.0"
+defusedxml = "^0.7.1"
 
 [tool.poetry.group.dev.dependencies]
-coverage = "7.9.2"
+coverage = "7.10.1"
 pytest = "8.4.1"
 beautifulsoup4 = "4.13.4"
 responses = "0.25.7"
@@ -69,14 +70,15 @@ line-length = 120
 
 [tool.ruff.lint]
 ignore = ["E501", "G004", "PLR2004", "RUF005", "RUF012", "UP040"] # longlines, fstrings in logs, magic values, consider not concat, mutable classbits, type instead of TypeAlias
-extend-select = ["W", "I", "SLF", "SIM"]
-# extend-select = [ "B", "Q", "C90", "I", "UP", "YTT", "ASYNC", "S", "BLE", "A", "COM", "C4", "DTZ", "T10", "DJ", "EM", "EXE", "FA",
+extend-select = ["W", "I", "SLF", "SIM", "C90", "S"]
+# extend-select = [ "B", "Q", "I", "UP", "YTT", "ASYNC", "BLE", "A", "COM", "C4", "DTZ", "T10", "DJ", "EM", "EXE", "FA",
 #                  "ISC", "ICN", "G", "INP", "PIE", "T20", "PYI", "PT", "Q", "RSE", "RET", "SLOT", "TID", "TCH", "INT", "PTH",
 #                  "FIX", "PGH", "PL", "TRY", "FLY", "PERF", "RUF"]
 unfixable = ["ERA"]
 
 [tool.ruff.lint.extend-per-file-ignores]
 "tests/*" = ["S101"]  # `assert` is fine in tests
+"smoketest/*" = ["S101"] # `assert` is fine in tests
 "tests/client/test_client.py" = ["SLF001"]  # TODO: This really shouldn't be the case, but it's not important to fix right now.
 
 # things skipped:

{ds_caselaw_marklogic_api_client-39.0.0 → ds_caselaw_marklogic_api_client-39.1.0}/src/caselawclient/Client.py

@@ -7,11 +7,12 @@ import warnings
 from datetime import datetime, time, timedelta
 from pathlib import Path
 from typing import Any, Optional, Type, Union
-from xml.etree import ElementTree
-from xml.etree.ElementTree import Element, ParseError, fromstring
+from xml.etree.ElementTree import Element
 
 import environ
 import requests
+from defusedxml import ElementTree
+from defusedxml.ElementTree import ParseError, fromstring
 from ds_caselaw_utils.types import NeutralCitationString
 from lxml import etree
 from requests.auth import HTTPBasicAuth
@@ -258,10 +259,12 @@ class MarklogicApiClient:
             return "Unknown error, Marklogic returned a null or empty response"
         try:
             xml = fromstring(content_as_xml)
-            return xml.find(
-                "message-code",
-                namespaces={"": "http://marklogic.com/xdmp/error"},
-            ).text  # type: ignore
+            return str(
+                xml.find(
+                    "message-code",
+                    namespaces={"": "http://marklogic.com/xdmp/error"},
+                ).text
+            )
         except (ParseError, TypeError, AttributeError):
             return "Unknown error, Marklogic returned a null or empty response"
 
@@ -682,10 +685,12 @@ class MarklogicApiClient:
         if content == "":
             return None
         response_xml = ElementTree.fromstring(content)
-        return response_xml.find(
-            "dls:annotation",
-            namespaces={"dls": "http://marklogic.com/xdmp/dls"},
-        ).text  # type: ignore
+        return str(
+            response_xml.find(
+                "dls:annotation",
+                namespaces={"dls": "http://marklogic.com/xdmp/dls"},
+            ).text
+        )
 
     def get_judgment_version(
         self,

{ds_caselaw_marklogic_api_client-39.0.0 → ds_caselaw_marklogic_api_client-39.1.0}/src/caselawclient/models/documents/__init__.py

@@ -63,6 +63,9 @@ class Document:
     document_noun_plural = "documents"
     """ The noun for a plural of this document type. """
 
+    _default_reparse_document_type: Optional[str] = None
+    """ The default noun to pass to the parser when reparsing given the document type if known. This is used to determine how the document should be parsed and processed."""
+
     type_collection_name: str
 
     attributes_to_validate: list[tuple[str, bool, str]] = [
@@ -465,7 +468,6 @@ class Document:
         now = datetime.datetime.now(datetime.timezone.utc)
         self.api_client.set_property(self.uri, "last_sent_to_parser", now.isoformat())
 
-        parser_type_noun = {"judgment": "judgment", "press summary": "pressSummary"}[self.document_noun]
         checked_date: Optional[str] = (
             self.body.document_date_as_date.isoformat()
             if self.body.document_date_as_date and self.body.document_date_as_date > datetime.date(1001, 1, 1)
@@ -477,16 +479,18 @@ class Document:
         # values are "" from the API, we should pass None instead in this case.
 
         parser_instructions: ParserInstructionsDict = {
-            "documentType": parser_type_noun,
             "metadata": {
                 "name": self.body.name or None,
                 "cite": None,
                 "court": self.body.court or None,
                 "date": checked_date,
                 "uri": self.uri,
-            },
+            }
         }
 
+        if self._default_reparse_document_type:
+            parser_instructions["documentType"] = self._default_reparse_document_type
+
         ## 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

{ds_caselaw_marklogic_api_client-39.0.0 → ds_caselaw_marklogic_api_client-39.1.0}/src/caselawclient/models/judgments.py

@@ -24,6 +24,7 @@ class Judgment(NeutralCitationMixin, Document):
     document_noun = "judgment"
     document_noun_plural = "judgments"
     type_collection_name = "judgment"
+    _default_reparse_document_type = "judgment"
 
     def __init__(self, uri: DocumentURIString, *args: Any, **kwargs: Any) -> None:
         super().__init__(self.document_noun, uri, *args, **kwargs)

{ds_caselaw_marklogic_api_client-39.0.0 → ds_caselaw_marklogic_api_client-39.1.0}/src/caselawclient/models/parser_logs.py

@@ -11,3 +11,4 @@ class ParserLog(Document):
     document_noun = "parser log"
     document_noun_plural = "parser logs"
     type_collection_name = "parser-log"
+    _default_reparse_document_type = "parserLog"

{ds_caselaw_marklogic_api_client-39.0.0 → ds_caselaw_marklogic_api_client-39.1.0}/src/caselawclient/models/press_summaries.py

@@ -25,6 +25,7 @@ class PressSummary(NeutralCitationMixin, Document):
     document_noun = "press summary"
     document_noun_plural = "press summaries"
     type_collection_name = "press-summary"
+    _default_reparse_document_type = "pressSummary"
 
     def __init__(self, uri: DocumentURIString, *args: Any, **kwargs: Any) -> None:
         super().__init__(self.document_noun, uri, *args, **kwargs)