ds-caselaw-marklogic-api-client 30.0.0__tar.gz → 43.0.0__tar.gz

{ds_caselaw_marklogic_api_client-30.0.0 → ds_caselaw_marklogic_api_client-43.0.0}/PKG-INFO

@@ -1,32 +1,33 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: ds-caselaw-marklogic-api-client
-Version: 30.0.0
+Version: 43.0.0
 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
 Author: The National Archives
-Requires-Python: >=3.9,<4.0
+Requires-Python: >=3.12.0,<4.0.0
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: boto3 (>=1.26.112,<2.0.0)
-Requires-Dist: certifi (>=2024.12.14,<2024.13.0)
+Requires-Dist: certifi (>=2025.10.5,<2025.11.0)
 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)
-Requires-Dist: lxml (>=5.0.0,<6.0.0)
+Requires-Dist: lxml (>=6.0.0,<7.0.0)
 Requires-Dist: memoization (>=0.4.0,<0.5.0)
 Requires-Dist: mypy-boto3-s3 (>=1.26.104,<2.0.0)
 Requires-Dist: mypy-boto3-sns (>=1.26.69,<2.0.0)
+Requires-Dist: pydantic (>=2.12.3,<3.0.0)
 Requires-Dist: python-dateutil (>=2.9.0-post.0,<3.0.0)
-Requires-Dist: pytz (>=2024.1,<2025.0)
+Requires-Dist: pytz (>2024)
 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)
+Project-URL: Homepage, https://github.com/nationalarchives/ds-caselaw-custom-api-client
 Description-Content-Type: text/markdown
 
 # The National Archives: Find Case Law
@@ -35,7 +36,9 @@ This repository is part of the [Find Case Law](https://caselaw.nationalarchives.
 
 # MarkLogic API Client
 
-[![PyPI](https://img.shields.io/pypi/v/ds-caselaw-marklogic-api-client)](https://pypi.org/project/ds-caselaw-marklogic-api-client/) ![Libraries.io dependency status for latest release](https://img.shields.io/librariesio/release/pypi/ds-caselaw-marklogic-api-client)
+[![PyPI](https://img.shields.io/pypi/v/ds-caselaw-marklogic-api-client)](https://pypi.org/project/ds-caselaw-marklogic-api-client/)
+![Libraries.io dependency status for latest release](https://img.shields.io/librariesio/release/pypi/ds-caselaw-marklogic-api-client)
+![Code Coverage](https://img.shields.io/codecov/c/github/nationalarchives/ds-caselaw-custom-api-client)
 
 This is an API Client for connecting to Marklogic for The National Archive's Caselaw site.
 

{ds_caselaw_marklogic_api_client-30.0.0 → ds_caselaw_marklogic_api_client-43.0.0}/README.md

@@ -4,7 +4,9 @@ This repository is part of the [Find Case Law](https://caselaw.nationalarchives.
 
 # MarkLogic API Client
 
-[![PyPI](https://img.shields.io/pypi/v/ds-caselaw-marklogic-api-client)](https://pypi.org/project/ds-caselaw-marklogic-api-client/) ![Libraries.io dependency status for latest release](https://img.shields.io/librariesio/release/pypi/ds-caselaw-marklogic-api-client)
+[![PyPI](https://img.shields.io/pypi/v/ds-caselaw-marklogic-api-client)](https://pypi.org/project/ds-caselaw-marklogic-api-client/)
+![Libraries.io dependency status for latest release](https://img.shields.io/librariesio/release/pypi/ds-caselaw-marklogic-api-client)
+![Code Coverage](https://img.shields.io/codecov/c/github/nationalarchives/ds-caselaw-custom-api-client)
 
 This is an API Client for connecting to Marklogic for The National Archive's Caselaw site.
 

{ds_caselaw_marklogic_api_client-30.0.0 → ds_caselaw_marklogic_api_client-43.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "30.0.0"
+version = "43.0.0"
 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"
@@ -11,33 +11,36 @@ packages = [
 ]
 
 [tool.poetry.dependencies]
-python = "^3.9"
-certifi = ">=2024.12.14,<2024.13.0"
+python = "^3.12.0"
+certifi = ">=2025.10.5,<2025.11.0"
 charset-normalizer = "^3.0.0"
 django-environ = ">=0.12.0"
 idna = "^3.4"
 requests = "^2.28.2"
 requests-toolbelt = ">=0.10.1,<1.1.0"
 memoization = "^0.4.0"
-lxml = "^5.0.0"
+lxml = "^6.0.0"
 ds-caselaw-utils = "^2.0.0"
 boto3 = "^1.26.112"
 typing-extensions = "^4.7.1"
 mypy-boto3-s3 = "^1.26.104"
 mypy-boto3-sns = "^1.26.69"
-pytz = "^2024.1"
+pytz = ">2024"
 python-dateutil = "^2.9.0-post.0"
 saxonche = "^12.5.0"
 sqids = "^0.5.0"
+defusedxml = "^0.7.1"
+pydantic = "^2.12.3"
 
 [tool.poetry.group.dev.dependencies]
-coverage = "^7.2.3"
-pytest = "^8.0.0"
-beautifulsoup4 = "^4.12.3"
-responses = "^0.25.0"
-python-dotenv = "^1.0.0"
-time-machine = "^2.13.0"
-moto = {version = "^5.0.1", extras = ["all"]}
+coverage = "7.11.0"
+pytest = "8.4.2"
+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"]}
 
 [tool.poetry.group.docs]
 optional = true
@@ -69,14 +72,15 @@ 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
+"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-30.0.0 → ds_caselaw_marklogic_api_client-43.0.0}/src/caselawclient/Client.py

@@ -7,11 +7,13 @@ 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 dateutil.parser import isoparse
+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
@@ -19,19 +21,20 @@ from requests.structures import CaseInsensitiveDict
 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,
     Document,
 )
+from caselawclient.models.documents.versions import VersionAnnotation
 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.types import DocumentIdentifierSlug, DocumentIdentifierValue, DocumentURIString
 from caselawclient.xquery_type_dicts import (
+    CheckContentHashUniqueByUriDict,
     MarkLogicDocumentURIString,
     MarkLogicDocumentVersionURIString,
     MarkLogicPrivilegeURIString,
@@ -55,6 +58,11 @@ from .errors import (
 )
 
 env = environ.Env()
+
+# Requests timeouts: https://requests.readthedocs.io/en/latest/user/advanced/
+CONNECT_TIMEOUT = float(os.environ.get("CONNECT_TIMEOUT", "3.05"))
+READ_TIMEOUT = float(os.environ.get("READ_TIMEOUT", "10.0"))
+
 ROOT_DIR = os.path.dirname(os.path.realpath(__file__))
 DEFAULT_XSL_TRANSFORM = "accessible-html.xsl"
 
@@ -77,12 +85,6 @@ class MultipartResponseLongerThanExpected(Exception):
     """
 
 
-class DocumentHasNoTypeCollection(Exception):
-    """
-    A MarkLogic document is not part of a collection which identifies its document type.
-    """
-
-
 def get_multipart_strings_from_marklogic_response(
     response: requests.Response,
 ) -> list[str]:
@@ -175,6 +177,7 @@ class MarklogicApiClient:
     error_code_classes: dict[str, Type[MarklogicAPIError]] = {
         "XDMP-DOCNOTFOUND": MarklogicResourceNotFoundError,
         "XDMP-LOCKCONFLICT": MarklogicResourceLockedError,
+        "XDMP-LOCKED": MarklogicResourceLockedError,
         "DLS-UNMANAGED": MarklogicResourceUnmanagedError,
         "DLS-NOTCHECKEDOUT": MarklogicResourceNotCheckedOutError,
         "DLS-CHECKOUTCONFLICT": MarklogicCheckoutConflictError,
@@ -239,9 +242,7 @@ class MarklogicApiClient:
             return Judgment
         if DOCUMENT_COLLECTION_URI_PRESS_SUMMARY in collections:
             return PressSummary
-        raise DocumentHasNoTypeCollection(
-            f"The document at URI {uri} is not part of a valid document type collection.",
-        )
+        return Document
 
     def _get_error_code_class(self, error_code: str) -> Type[MarklogicAPIError]:
         """
@@ -266,10 +267,12 @@ 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"
 
@@ -322,11 +325,13 @@ class MarklogicApiClient:
         self,
         vars: query_dicts.MarkLogicAPIDict,
         xquery_file_name: str,
+        timeout: tuple[float, float] = (CONNECT_TIMEOUT, READ_TIMEOUT),
     ) -> requests.Response:
         return self.eval(
             self._xquery_path(xquery_file_name),
             vars=json.dumps(vars),
             accept_header="application/xml",
+            timeout=timeout,
         )
 
     def _eval_and_decode(
@@ -572,6 +577,7 @@ class MarklogicApiClient:
         self,
         document_uri: DocumentURIString,
         document_xml: Element,
+        document_type: type[Document],
         annotation: VersionAnnotation,
     ) -> requests.Response:
         """
@@ -579,6 +585,7 @@ class MarklogicApiClient:
 
         :param document_uri: The URI to insert the document at
         :param document_xml: The XML of the document to insert
+        :param document_type: The type class of the document
         :param annotation: Annotations to record alongside this version
 
         :return: The response object from MarkLogic
@@ -592,6 +599,7 @@ class MarklogicApiClient:
 
         vars: query_dicts.InsertDocumentDict = {
             "uri": uri,
+            "type_collection": document_type.type_collection_name,
             "document": xml.decode("utf-8"),
             "annotation": annotation.as_json,
         }
@@ -687,10 +695,12 @@ 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,
@@ -719,11 +729,20 @@ class MarklogicApiClient:
             == 0
         )
 
+    def has_unique_content_hash(self, judgment_uri: DocumentURIString) -> bool:
+        """
+        Returns True if the content hash for this document is unique (not shared with other documents).
+        """
+        uri = self._format_uri_for_marklogic(judgment_uri)
+        vars: CheckContentHashUniqueByUriDict = {"uri": uri}
+        return self._eval_and_decode(vars, "check_content_hash_unique_by_uri.xqy") == "true"
+
     def eval(
         self,
         xquery_path: str,
         vars: str,
         accept_header: str = "multipart/mixed",
+        timeout: tuple[float, float] = (CONNECT_TIMEOUT, READ_TIMEOUT),
     ) -> requests.Response:
         headers = {
             "Content-type": "application/x-www-form-urlencoded",
@@ -743,6 +762,7 @@ class MarklogicApiClient:
             url=self._path_to_request_url(path),
             headers=headers,
             data=data,
+            timeout=timeout,
         )
         # Raise relevant exception for an erroneous response
         self._raise_for_status(response)
@@ -782,6 +802,8 @@ class MarklogicApiClient:
         :param judge:
         :param party:
         :param neutral_citation:
+        :param document_name:
+        :param consignment_number:
         :param specific_keyword:
         :param order:
         :param date_from:
@@ -938,12 +960,50 @@ class MarklogicApiClient:
             "value": string_value,
             "name": name,
         }
+        """
+        Set a property within MarkLogic which is specifically a boolean.
+
+        Since XML has no concept of boolean, the actual value in the database is set to `"true"` or `"false"`.
+        """
         return self._send_to_eval(vars, "set_boolean_property.xqy")
 
     def get_boolean_property(self, judgment_uri: DocumentURIString, name: str) -> bool:
+        """
+        Get a property from MarkLogic which is specifically a boolean.
+
+        :return: `True` if the property exists and has a value of `"true"`, otherwise `False`
+        """
         content = self.get_property(judgment_uri, name)
         return content == "true"
 
+    def set_datetime_property(
+        self,
+        judgment_uri: DocumentURIString,
+        name: str,
+        value: datetime,
+    ) -> requests.Response:
+        """Set a property within MarkLogic which is specifically a datetime."""
+        uri = self._format_uri_for_marklogic(judgment_uri)
+        vars: query_dicts.SetDatetimePropertyDict = {
+            "uri": uri,
+            "value": value.isoformat(),
+            "name": name,
+        }
+        return self._send_to_eval(vars, "set_datetime_property.xqy")
+
+    def get_datetime_property(self, judgment_uri: DocumentURIString, name: str) -> Optional[datetime]:
+        """
+        Get a property from MarkLogic which is specifically a datetime.
+
+        :return: A datetime with the value of the property, or `None` if it does not exist
+        """
+        content = self.get_property(judgment_uri, name)
+
+        if content:
+            return isoparse(content)
+
+        return None
+
     def set_published(
         self,
         judgment_uri: DocumentURIString,
@@ -1052,10 +1112,6 @@ class MarklogicApiClient:
         if show_unpublished and not self.user_can_view_unpublished_judgments(
             self.username,
         ):
-            # The user cannot view unpublished judgments but is requesting to see them
-            logging.warning(
-                f"User {self.username} is attempting to view unpublished judgments but does not have that privilege.",
-            )
             return False
         return show_unpublished
 
@@ -1068,14 +1124,14 @@ class MarklogicApiClient:
         response = self._send_to_eval(vars, "get_properties_for_search_results.xqy")
         return get_single_string_from_marklogic_response(response)
 
-    def search_and_decode_response(self, search_parameters: SearchParameters) -> str:
+    def search_and_decode_response(self, search_parameters: SearchParameters) -> bytes:
         response = self.advanced_search(search_parameters)
-        return get_single_string_from_marklogic_response(response)
+        return get_single_bytestring_from_marklogic_response(response)
 
     def search_judgments_and_decode_response(
         self,
         search_parameters: SearchParameters,
-    ) -> str:
+    ) -> bytes:
         search_parameters.collections = [DOCUMENT_COLLECTION_URI_JUDGMENT]
         return self.search_and_decode_response(search_parameters)
 
@@ -1203,11 +1259,31 @@ class MarklogicApiClient:
 
         return results
 
-    def resolve_from_identifier_slug(self, identifier_uri: str, published_only: bool = True) -> IdentifierResolutions:
+    def get_missing_fclid(
+        self,
+        maximum_records: int = 50,
+    ) -> list[str]:
+        """Retrieve the URIs of published documents which do not have an identifier in the `fclid` schema."""
+        vars: query_dicts.GetMissingFclidDict = {
+            "maximum_records": maximum_records,
+        }
+
+        results: list[str] = get_multipart_strings_from_marklogic_response(
+            self._send_to_eval(
+                vars,
+                "get_missing_fclid.xqy",
+            )
+        )
+
+        return results
+
+    def resolve_from_identifier_slug(
+        self, identifier_slug: DocumentIdentifierSlug, 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.ResolveFromIdentifierSlugDict = {
-            "identifier_uri": DocumentURIString(identifier_uri),
+            "identifier_slug": identifier_slug,
             "published_only": int(published_only),
         }
         raw_results: list[str] = get_multipart_strings_from_marklogic_response(
@@ -1218,14 +1294,8 @@ class MarklogicApiClient:
         )
         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
+        self, identifier_value: DocumentIdentifierValue, 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"""

ds_caselaw_marklogic_api_client-43.0.0/src/caselawclient/__init__.py

@@ -0,0 +1,63 @@
+import os
+
+if os.getenv("PDOC_DYNAMIC_VERSION") == "1":
+    from pathlib import Path
+
+    import tomllib
+
+    pyproject_path = Path(__file__).parent.parent.parent / "pyproject.toml"
+    with pyproject_path.open("rb") as f:
+        __version__ = tomllib.load(f)["tool"]["poetry"]["version"]
+        __pip_version_string__ = f"~={__version__}"
+        __poetry_version_string__ = f' = "^{__version__}"'
+
+else:
+    __pip_version_string__ = ""
+    __poetry_version_string__ = ""
+
+__doc__ = f"""
+
+# Installation
+
+Include the API client in your project using Pip or Poetry:
+
+```bash
+pip install ds-caselaw-marklogic-api-client
+```
+
+```bash
+poetry add ds-caselaw-marklogic-api-client
+```
+
+or in your projects `requirements.txt` with:
+
+```text
+ds-caselaw-marklogic-api-client{__pip_version_string__}
+```
+
+or `pyproject.toml` for Poetry with:
+
+```text
+ds-caselaw-marklogic-api-client{__poetry_version_string__}
+```
+
+# Usage
+
+## Initialising the client
+
+Import the `MarklogicApiClient` class and instantiate with appropriate credentials:
+
+```python
+
+from caselawclient.Client import MarklogicApiClient
+
+client = MarklogicApiClient(
+    host="hostname",
+    username="username",
+    password="password",
+    use_https=True,
+)
+
+```
+
+"""

ds_caselaw_marklogic_api_client-43.0.0/src/caselawclient/client_helpers/__init__.py

@@ -0,0 +1,35 @@
+from lxml import etree
+
+from caselawclient.xml_helpers import DEFAULT_NAMESPACES
+
+from ..models.documents import Document
+from ..models.judgments import Judgment
+from ..models.parser_logs import ParserLog
+from ..models.press_summaries import PressSummary
+
+
+class CannotDetermineDocumentType(Exception):
+    pass
+
+
+def get_document_type_class(xml: bytes) -> type[Document]:
+    """Attempt to get the type of the document based on the top-level structure of the XML document."""
+
+    node = etree.fromstring(xml)
+
+    # If the main node is `<judgment>`, it's a judgment
+    if node.xpath("/akn:akomaNtoso/akn:judgment", namespaces=DEFAULT_NAMESPACES):
+        return Judgment
+
+    # If the main node is `<doc name='pressSummary'>`, it's a press summary
+    if node.xpath("/akn:akomaNtoso/akn:doc[@name='pressSummary']", namespaces=DEFAULT_NAMESPACES):
+        return PressSummary
+
+    # If the document is a parser error with a root element of `error`, it's not of a special type.
+    if node.xpath("/error", namespaces=DEFAULT_NAMESPACES):
+        return ParserLog
+
+    # Otherwise, we don't know for sure. Fail out.
+    raise CannotDetermineDocumentType(
+        "Unable to determine the Document type by its XML",
+    )