ds-caselaw-marklogic-api-client 24.0.0__tar.gz → 25.0.0__tar.gz

{ds_caselaw_marklogic_api_client-24.0.0 → ds_caselaw_marklogic_api_client-25.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 24.0.0
+Version: 25.0.0
 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
@@ -11,7 +11,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: boto3 (>=1.26.112,<2.0.0)
-Requires-Dist: certifi (>=2024.7.4,<2024.8.0)
+Requires-Dist: certifi (>=2024.8.30,<2024.9.0)
 Requires-Dist: charset-normalizer (>=3.0.0,<4.0.0)
 Requires-Dist: django-environ (>=0.11.0,<0.12.0)
 Requires-Dist: ds-caselaw-utils (>=1.4.1,<2.0.0)
@@ -93,3 +93,5 @@ To create a release:
 8. Create a release in [Github releases](https://github.com/nationalarchives/ds-caselaw-custom-api-client/releases)
    using the created tag
 
+If the release fails to push to PyPI, you can delete the tag with `git pull`, `git push --delete origin v1.2.3` and try again.
+

{ds_caselaw_marklogic_api_client-24.0.0 → ds_caselaw_marklogic_api_client-25.0.0}/README.md

@@ -63,3 +63,5 @@ To create a release:
 7. Tag the merge commit on `main` with `v{major}.{minor}.{patch}` and push the tag
 8. Create a release in [Github releases](https://github.com/nationalarchives/ds-caselaw-custom-api-client/releases)
    using the created tag
+
+If the release fails to push to PyPI, you can delete the tag with `git pull`, `git push --delete origin v1.2.3` and try again.

{ds_caselaw_marklogic_api_client-24.0.0 → ds_caselaw_marklogic_api_client-25.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "24.0.0"
+version = "25.0.0"
 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"
@@ -12,7 +12,7 @@ packages = [
 
 [tool.poetry.dependencies]
 python = "^3.9"
-certifi = ">=2024.7.4,<2024.8.0"
+certifi = ">=2024.8.30,<2024.9.0"
 charset-normalizer = "^3.0.0"
 django-environ = "^0.11.0"
 idna = "^3.4"
@@ -57,11 +57,15 @@ line-length = 120
 
 [tool.ruff.lint]
 ignore = ["E501", "G004", "PLR2004", "RUF005", "RUF012", "UP040"] # long lines, fstrings in logs, magic values, consider not concat, mutable classbits, type instead of TypeAlias
-extend-select = ["W", "B", "Q", "C90", "I", "UP", "YTT", "ASYNC", "S", "BLE", "A", "COM", "C4", "DTZ", "T10", "DJ", "EM", "EXE", "FA",
-                 "ISC", "ICN", "G", "INP", "PIE", "T20", "PYI", "PT", "Q", "RSE", "RET", "SLF", "SLOT", "SIM", "TID", "TCH", "INT", "PTH",
-                 "FIX", "PGH", "PL", "TRY", "FLY", "PERF", "RUF"]
+extend-select = ["W", "I"]
+# extend-select = [ "B", "Q", "C90", "I", "UP", "YTT", "ASYNC", "S", "BLE", "A", "COM", "C4", "DTZ", "T10", "DJ", "EM", "EXE", "FA",
+#                  "ISC", "ICN", "G", "INP", "PIE", "T20", "PYI", "PT", "Q", "RSE", "RET", "SLF", "SLOT", "SIM", "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
+
 # things skipped:
 # N: naming, possibly good
 # D: docstrings missing throughout

{ds_caselaw_marklogic_api_client-24.0.0 → ds_caselaw_marklogic_api_client-25.0.0}/src/caselawclient/Client.py

@@ -8,7 +8,7 @@ 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
+from xml.etree.ElementTree import Element, ParseError, fromstring
 
 import environ
 import requests
@@ -34,7 +34,6 @@ from caselawclient.xquery_type_dicts import (
     MarkLogicPrivilegeURIString,
 )
 
-from . import xml_tools
 from .content_hash import validate_content_hash
 from .errors import (
     DocumentNotFoundError,
@@ -129,7 +128,7 @@ def get_single_string_from_marklogic_response(
         # relies on "" being falsy.
         return ""
 
-    elif part_count > 1:
+    if part_count > 1:
         raise MultipartResponseLongerThanExpected(
             f"Response returned {part_count} multipart items, expected 1",
         )
@@ -148,7 +147,7 @@ def get_single_bytestring_from_marklogic_response(
         # relies on "" being falsy.
         return b""
 
-    elif part_count > 1:
+    if part_count > 1:
         raise MultipartResponseLongerThanExpected(
             f"Response returned {part_count} multipart items, expected 1",
         )
@@ -231,12 +230,11 @@ class MarklogicApiClient:
 
         if DOCUMENT_COLLECTION_URI_JUDGMENT in collections:
             return Judgment
-        elif DOCUMENT_COLLECTION_URI_PRESS_SUMMARY in collections:
+        if DOCUMENT_COLLECTION_URI_PRESS_SUMMARY in collections:
             return PressSummary
-        else:
-            raise DocumentHasNoTypeCollection(
-                f"The document at URI {uri} is not part of a valid document type collection.",
-            )
+        raise DocumentHasNoTypeCollection(
+            f"The document at URI {uri} is not part of a valid document type collection.",
+        )
 
     def _get_error_code_class(self, error_code: str) -> Type[MarklogicAPIError]:
         """
@@ -251,6 +249,23 @@ class MarklogicApiClient:
     def _path_to_request_url(self, path: str) -> str:
         return f"{self.base_url}/{path.lstrip('/')}"
 
+    @classmethod
+    def _get_error_code(cls, content_as_xml: Optional[str]) -> str:
+        logging.warning(
+            "XMLTools is deprecated and will be removed in later versions. "
+            "Use methods from MarklogicApiClient.Client instead.",
+        )
+        if not content_as_xml:
+            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
+        except (ParseError, TypeError, AttributeError):
+            return "Unknown error, Marklogic returned a null or empty response"
+
     def _raise_for_status(self, response: requests.Response) -> None:
         try:
             response.raise_for_status()
@@ -269,7 +284,8 @@ class MarklogicApiClient:
 
             if new_error_class == self.default_http_error_class:
                 # Attempt to decode the error code from the response
-                error_code = xml_tools.get_error_code(response.content.decode("utf-8"))
+
+                error_code = self._get_error_code(response.content.decode("utf-8"))
 
                 new_error_class = self._get_error_code_class(error_code)
 
@@ -498,9 +514,8 @@ class MarklogicApiClient:
             court, jurisdiction = re.split("\\s*/\\s*", content)
             self.set_document_court(document_uri, court)
             return self.set_document_jurisdiction(document_uri, jurisdiction)
-        else:
-            self.set_document_court(document_uri, content)
-            return self.set_document_jurisdiction(document_uri, "")
+        self.set_document_court(document_uri, content)
+        return self.set_document_jurisdiction(document_uri, "")
 
     def set_judgment_this_uri(
         self,

{ds_caselaw_marklogic_api_client-24.0.0 → ds_caselaw_marklogic_api_client-25.0.0}/src/caselawclient/models/documents.py

@@ -217,8 +217,7 @@ class Document:
     def court_and_jurisdiction_identifier_string(self) -> CourtIdentifierString:
         if self.jurisdiction != "":
             return CourtIdentifierString("/".join((self.court, self.jurisdiction)))
-        else:
-            return CourtIdentifierString(self.court)
+        return CourtIdentifierString(self.court)
 
     @cached_property
     def document_date_as_string(self) -> str:
@@ -263,8 +262,7 @@ class Document:
         events = self.get_manifestation_datetimes(name)
         if not events:
             return None
-        else:
-            return max(events)
+        return max(events)
 
     def get_latest_manifestation_type(self) -> Optional[str]:
         return max(
@@ -404,8 +402,7 @@ class Document:
                     GatewayTimeoutGettingHTMLWithQuery,
                 )
                 return self.content_as_html(version_uri)
-            else:
-                raise e
+            raise e
 
     def number_of_mentions(self, query: str) -> int:
         html = self.content_as_html(query=query)

{ds_caselaw_marklogic_api_client-24.0.0 → ds_caselaw_marklogic_api_client-25.0.0}/src/caselawclient/models/utilities/aws.py

@@ -218,8 +218,7 @@ def build_new_key(old_key: str, new_uri: str) -> str:
     if old_filename.endswith(".docx") or old_filename.endswith(".pdf"):
         new_filename = new_uri.replace("/", "_")
         return f"{new_uri}/{new_filename}.{old_filename.split('.')[-1]}"
-    else:
-        return f"{new_uri}/{old_filename}"
+    return f"{new_uri}/{old_filename}"
 
 
 def request_parse(
@@ -244,7 +243,7 @@ def request_parse(
         "parameters": {
             "s3Bucket": env("PRIVATE_ASSET_BUCKET"),
             "s3Key": generate_docx_key(uri),
-            "reference": reference or f"FCL-{uuid.uuid4()}",
+            "reference": reference or f"FCL-{str(uuid.uuid4())[:-13]}",  # uuid truncated at request of TRE
             "originator": "FCL",
             "parserInstructions": parser_instructions,
         },

ds_caselaw_marklogic_api_client-24.0.0/src/caselawclient/xml_tools.py

@@ -1,129 +0,0 @@
-import logging
-from typing import List, Optional
-from xml.etree.ElementTree import (
-    Element,
-    ElementTree,
-    ParseError,
-    QName,
-    fromstring,
-    tostring,
-)
-
-akn_uk_namespaces = {
-    "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
-    "uk": "https://caselaw.nationalarchives.gov.uk/akn",
-}
-akn_namespace_uri = "http://docs.oasis-open.org/legaldocml/ns/akn/3.0"
-uk_namespace_uri = "https://caselaw.nationalarchives.gov.uk/akn"
-search_namespace = {"search": "http://marklogic.com/appservices/search"}
-
-
-class JudgmentMissingMetadataError(IndexError):
-    pass
-
-
-def get_element(
-    xml: ElementTree,
-    xpath: str,
-    element_name: str = "FRBRname",
-    element_namespace: str = akn_namespace_uri,
-    has_value_attribute: bool = True,
-) -> Element:
-    logging.warning(
-        "XMLTools is deprecated and will be removed in later versions. "
-        "Use methods from MarklogicApiClient.Client instead.",
-    )
-    name = xml.find(
-        xpath,
-        namespaces=akn_uk_namespaces,
-    )
-
-    if name is None:
-        element = Element(QName(element_namespace, element_name))  # type: ignore
-        if has_value_attribute:
-            element.set("value", "")
-        return element
-
-    return name
-
-
-def get_neutral_citation_element(xml: ElementTree) -> Element:
-    return get_element(xml, ".//uk:cite", "cite", uk_namespace_uri, False)
-
-
-def get_neutral_citation_name_value(xml: ElementTree) -> Optional[str]:
-    return get_neutral_citation_element(xml).text
-
-
-def get_judgment_date_element(xml: ElementTree) -> Element:
-    logging.warning(
-        "XMLTools is deprecated and will be removed in later versions. "
-        "Use methods from MarklogicApiClient.Client instead.",
-    )
-    name = xml.find(
-        ".//akn:FRBRWork/akn:FRBRdate",
-        namespaces=akn_uk_namespaces,
-    )
-
-    if name is None:
-        element = Element(QName(akn_namespace_uri, "FRBRdate"))  # type: ignore
-        element.set("date", "")
-        element.set("name", "judgment")
-
-        return element
-
-    return name
-
-
-def get_judgment_date_value(xml: ElementTree) -> str:
-    return get_judgment_date_element(xml).attrib["date"]
-
-
-def get_court_element(xml: ElementTree) -> Element:
-    return get_element(xml, ".//uk:court", "court", uk_namespace_uri, False)
-
-
-def get_court_value(xml: ElementTree) -> Optional[str]:
-    return get_court_element(xml).text
-
-
-def get_metadata_name_element(xml: ElementTree) -> Element:
-    return get_element(xml, ".//akn:FRBRname", "FRBRname", akn_namespace_uri, True)
-
-
-def get_metadata_name_value(xml: ElementTree) -> str:
-    name = get_metadata_name_element(xml)
-    value = name.attrib["value"]
-    if value is None:
-        return ""
-    return value
-
-
-def get_search_matches(element: ElementTree) -> List[str]:
-    logging.warning(
-        "XMLTools is deprecated and will be removed in later versions. "
-        "Use methods from MarklogicApiClient.Client instead.",
-    )
-    nodes = element.findall(".//search:match", namespaces=search_namespace)
-    results = []
-    for node in nodes:
-        text = tostring(node, method="text", encoding="UTF-8")
-        results.append(text.decode("UTF-8").strip())
-    return results
-
-
-def get_error_code(content_as_xml: Optional[str]) -> str:
-    logging.warning(
-        "XMLTools is deprecated and will be removed in later versions. "
-        "Use methods from MarklogicApiClient.Client instead.",
-    )
-    if not content_as_xml:
-        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
-    except (ParseError, TypeError, AttributeError):
-        return "Unknown error, Marklogic returned a null or empty response"