ds-caselaw-marklogic-api-client 25.0.0__tar.gz → 27.0.0__tar.gz

{ds_caselaw_marklogic_api_client-25.0.0 → ds_caselaw_marklogic_api_client-27.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 25.0.0
+Version: 27.0.0
 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
@@ -14,7 +14,7 @@ Requires-Dist: boto3 (>=1.26.112,<2.0.0)
 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)
+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: memoization (>=0.4.0,<0.5.0)

{ds_caselaw_marklogic_api_client-25.0.0 → ds_caselaw_marklogic_api_client-27.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "25.0.0"
+version = "27.0.0"
 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"
@@ -20,7 +20,7 @@ requests = "^2.28.2"
 requests-toolbelt = ">=0.10.1,<1.1.0"
 memoization = "^0.4.0"
 lxml = "^5.0.0"
-ds-caselaw-utils = "^1.4.1"
+ds-caselaw-utils = "^2.0.0"
 boto3 = "^1.26.112"
 typing-extensions = "^4.7.1"
 mypy-boto3-s3 = "^1.26.104"
@@ -42,6 +42,13 @@ optional = true
 [tool.poetry.group.docs.dependencies]
 pdoc = "^14.0.0"
 
+
+[tool.commitizen]
+name = "cz_conventional_commits"
+tag_format = "v$version"
+version_scheme = "semver2"
+version_provider = "poetry"
+update_changelog_on_bump = true
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
@@ -56,15 +63,16 @@ filterwarnings = ["ignore::DeprecationWarning"]
 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", "I"]
+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",
-#                  "ISC", "ICN", "G", "INP", "PIE", "T20", "PYI", "PT", "Q", "RSE", "RET", "SLF", "SLOT", "SIM", "TID", "TCH", "INT", "PTH",
+#                  "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/client/test_client.py" = ["SLF001"]  # TODO: This really shouldn't be the case, but it's not important to fix right now.
 
 # things skipped:
 # N: naming, possibly good

{ds_caselaw_marklogic_api_client-25.0.0 → ds_caselaw_marklogic_api_client-27.0.0}/src/caselawclient/Client.py

@@ -12,6 +12,7 @@ from xml.etree.ElementTree import Element, ParseError, fromstring
 
 import environ
 import requests
+from ds_caselaw_utils.types import NeutralCitationString
 from requests.auth import HTTPBasicAuth
 from requests.structures import CaseInsensitiveDict
 from requests_toolbelt.multipart import decoder
@@ -800,10 +801,7 @@ class MarklogicApiClient:
             else None
         )
 
-        if os.getenv("XSLT_IMAGE_LOCATION"):
-            image_location = os.getenv("XSLT_IMAGE_LOCATION")
-        else:
-            image_location = ""
+        image_location = os.getenv("XSLT_IMAGE_LOCATION", "")
 
         show_unpublished = self.verify_show_unpublished(show_unpublished)
 
@@ -1038,12 +1036,7 @@ class MarklogicApiClient:
         search_parameters.collections = [DOCUMENT_COLLECTION_URI_JUDGMENT]
         return self.search_and_decode_response(search_parameters)
 
-    def overwrite_document(self, old_uri: str, new_citation: str) -> str:
-        """Move the judgment at old_uri on top of the new citation, which must already exist
-        Compare to update_document_uri"""
-        return move.overwrite_document(old_uri, new_citation, api_client=self)
-
-    def update_document_uri(self, old_uri: str, new_citation: str) -> str:
+    def update_document_uri(self, old_uri: DocumentURIString, new_citation: NeutralCitationString) -> DocumentURIString:
         """
         Move the document at old_uri to the correct location based on the neutral citation
         The new neutral citation *must* not already exist (that is handled elsewhere)

ds_caselaw_marklogic_api_client-27.0.0/src/caselawclient/factories.py

@@ -0,0 +1,165 @@
+import datetime
+from typing import Any, Optional, cast
+from unittest.mock import Mock, patch
+
+from typing_extensions import TypeAlias
+
+from caselawclient.Client import MarklogicApiClient
+from caselawclient.models.documents import Document
+from caselawclient.models.documents.body import DocumentBody
+from caselawclient.models.judgments import Judgment
+from caselawclient.models.press_summaries import PressSummary
+from caselawclient.responses.search_result import SearchResult, SearchResultMetadata
+
+DEFAULT_DOCUMENT_BODY_XML = "<akomantoso>This is some XML of a judgment.</akomantoso>"
+
+
+class DocumentBodyFactory:
+    # "name_of_attribute": "default value"
+    PARAMS_MAP: dict[str, Any] = {
+        "name": "Judgment v Judgement",
+        "court": "Court of Testing",
+        "document_date_as_string": "2023-02-03",
+    }
+
+    @classmethod
+    def build(cls, xml_string: str = DEFAULT_DOCUMENT_BODY_XML, **kwargs: Any) -> DocumentBody:
+        document_body = DocumentBody(
+            xml_bytestring=xml_string.encode(encoding="utf-8"),
+        )
+
+        for param_name, default_value in cls.PARAMS_MAP.items():
+            value = kwargs.get(param_name, default_value)
+            setattr(document_body, param_name, value)
+
+        return document_body
+
+
+class DocumentFactory:
+    # "name_of_attribute": "default value"
+    PARAMS_MAP: dict[str, Any] = {
+        "is_published": False,
+        "is_sensitive": False,
+        "is_anonymised": False,
+        "is_failure": False,
+        "source_name": "Example Uploader",
+        "source_email": "uploader@example.com",
+        "consignment_reference": "TDR-12345",
+        "assigned_to": "",
+        "versions": [],
+    }
+
+    target_class: TypeAlias = Document
+
+    @classmethod
+    def build(
+        cls,
+        uri: str = "test/2023/123",
+        html: str = "<p>This is a judgment.</p>",
+        api_client: Optional[MarklogicApiClient] = None,
+        **kwargs: Any,
+    ) -> target_class:
+        if not api_client:
+            api_client = Mock(spec=MarklogicApiClient)
+            api_client.get_judgment_xml_bytestring.return_value = DEFAULT_DOCUMENT_BODY_XML.encode(encoding="utf-8")
+
+        with patch.object(cls.target_class, "content_as_html") as mock_content_as_html:
+            mock_content_as_html.return_value = html
+            document = cls.target_class(uri, api_client=api_client)
+
+        document.body = kwargs.pop("body") if "body" in kwargs else DocumentBodyFactory.build()
+
+        for param_name, default_value in cls.PARAMS_MAP.items():
+            value = kwargs.get(param_name, default_value)
+            setattr(document, param_name, value)
+
+        return document
+
+
+class JudgmentFactory(DocumentFactory):
+    target_class = Judgment
+
+    def __init__(self) -> None:
+        self.PARAMS_MAP = self.PARAMS_MAP | {
+            "neutral_citation": "[2023] Test 123",
+            "best_human_identifier": "[2023] Test 123",
+        }
+
+        super().__init__()
+
+    @classmethod
+    def build(
+        cls,
+        uri: str = "test/2023/123",
+        html: str = "<p>This is a judgment.</p>",
+        api_client: Optional[MarklogicApiClient] = None,
+        **kwargs: Any,
+    ) -> Judgment:
+        return cast(Judgment, super().build(uri, html, api_client, **kwargs))
+
+
+class PressSummaryFactory(DocumentFactory):
+    target_class = PressSummary
+
+    def __init__(self) -> None:
+        self.PARAMS_MAP = self.PARAMS_MAP | {
+            "neutral_citation": "[2023] Test 123",
+            "best_human_identifier": "[2023] Test 123",
+        }
+
+        super().__init__()
+
+    @classmethod
+    def build(
+        cls,
+        uri: str = "test/2023/123/press-summary/1",
+        html: str = "<p>This is a judgment.</p>",
+        api_client: Optional[MarklogicApiClient] = None,
+        **kwargs: Any,
+    ) -> PressSummary:
+        return cast(PressSummary, super().build(uri, html, api_client, **kwargs))
+
+
+class SimpleFactory:
+    # "name_of_attribute": "default value"
+    PARAMS_MAP: dict[str, Any]
+
+    target_class: TypeAlias = object
+
+    @classmethod
+    def build(cls, **kwargs: Any) -> target_class:
+        mock_object = Mock(spec=cls.target_class, autospec=True)
+
+        for param, default in cls.PARAMS_MAP.items():
+            if param in kwargs:
+                setattr(mock_object.return_value, param, kwargs[param])
+            else:
+                setattr(mock_object.return_value, param, default)
+
+        return mock_object()
+
+
+class SearchResultMetadataFactory(SimpleFactory):
+    target_class = SearchResultMetadata
+    # "name_of_attribute": "default value"
+    PARAMS_MAP = {
+        "author": "Fake Name",
+        "author_email": "fake.email@gov.invalid",
+        "consignment_reference": "TDR-2023-ABC",
+        "submission_datetime": datetime.datetime(2023, 2, 3, 9, 12, 34),
+    }
+
+
+class SearchResultFactory(SimpleFactory):
+    target_class = SearchResult
+
+    # "name_of_attribute": ("name of incoming param", "default value")
+    PARAMS_MAP = {
+        "uri": "test/2023/123",
+        "name": "Judgment v Judgement",
+        "neutral_citation": "[2023] Test 123",
+        "court": "Court of Testing",
+        "date": datetime.date(2023, 2, 3),
+        "metadata": SearchResultMetadataFactory.build(),
+        "is_failure": False,
+    }

ds_caselaw_marklogic_api_client-25.0.0/src/caselawclient/models/documents.py → ds_caselaw_marklogic_api_client-27.0.0/src/caselawclient/models/documents/__init__.py

@@ -1,27 +1,22 @@
 import datetime
 import warnings
 from functools import cached_property
-from typing import TYPE_CHECKING, Any, Dict, NewType, Optional
+from typing import TYPE_CHECKING, Any, NewType, Optional
 
-import pytz
 from ds_caselaw_utils import courts
 from ds_caselaw_utils.courts import CourtNotFoundException
-from lxml import etree
+from ds_caselaw_utils.types import NeutralCitationString
 from lxml import html as html_parser
 from requests_toolbelt.multipart import decoder
 
-from caselawclient.models.utilities import extract_version
-from caselawclient.models.utilities.dates import parse_string_date_as_utc
-
-from ..errors import (
+from caselawclient.errors import (
     DocumentNotFoundError,
     GatewayTimeoutError,
     NotSupportedOnVersion,
     OnlySupportedOnVersion,
 )
-from ..xml_helpers import get_xpath_match_string, get_xpath_match_strings
-from .utilities import VersionsDict, render_versions
-from .utilities.aws import (
+from caselawclient.models.utilities import VersionsDict, extract_version, render_versions
+from caselawclient.models.utilities.aws import (
     ParserInstructionsDict,
     announce_document_event,
     check_docx_exists,
@@ -34,31 +29,17 @@ from .utilities.aws import (
     uri_for_s3,
 )
 
-MINIMUM_ENRICHMENT_TIME = datetime.timedelta(minutes=20)
-
+from .body import DocumentBody
+from .exceptions import CannotPublishUnpublishableDocument, DocumentNotSafeForDeletion
+from .statuses import DOCUMENT_STATUS_HOLD, DOCUMENT_STATUS_IN_PROGRESS, DOCUMENT_STATUS_NEW, DOCUMENT_STATUS_PUBLISHED
 
-class UnparsableDate(Warning):
-    pass
+MINIMUM_ENRICHMENT_TIME = datetime.timedelta(minutes=20)
 
 
 class GatewayTimeoutGettingHTMLWithQuery(RuntimeWarning):
     pass
 
 
-DOCUMENT_STATUS_HOLD = "On hold"
-""" This document has been placed on hold to actively prevent publication. """
-
-DOCUMENT_STATUS_PUBLISHED = "Published"
-""" This document has been published and should be considered publicly visible. """
-
-DOCUMENT_STATUS_IN_PROGRESS = "In progress"
-""" This document has not been published or put on hold, and has been picked up by an editor and
-    should be progressing through the document pipeline. """
-
-DOCUMENT_STATUS_NEW = "New"
-""" This document isn't published, on hold, or assigned, and can be picked up by an editor in the future. """
-
-
 DOCUMENT_COLLECTION_URI_JUDGMENT = "judgment"
 DOCUMENT_COLLECTION_URI_PRESS_SUMMARY = "press-summary"
 
@@ -67,19 +48,6 @@ if TYPE_CHECKING:
 
 
 DocumentURIString = NewType("DocumentURIString", str)
-CourtIdentifierString = NewType("CourtIdentifierString", str)
-
-
-class CannotPublishUnpublishableDocument(Exception):
-    """A document which has failed publication safety checks in `Document.is_publishable` cannot be published."""
-
-
-class DocumentNotSafeForDeletion(Exception):
-    """A document which is not safe for deletion cannot be deleted."""
-
-
-class NonXMLDocumentError(Exception):
-    """A document cannot be parsed as XML."""
 
 
 class Document:
@@ -96,7 +64,7 @@ class Document:
 
     attributes_to_validate: list[tuple[str, bool, str]] = [
         (
-            "failed_to_parse",
+            "is_failure",
             False,
             "This document failed to parse",
         ),
@@ -143,20 +111,18 @@ class Document:
 
         :raises DocumentNotFoundError: The document does not exist within MarkLogic
         """
-        self.uri = DocumentURIString(uri.strip("/"))
-        self.api_client = api_client
+        self.uri: DocumentURIString = DocumentURIString(uri.strip("/"))
+        self.api_client: MarklogicApiClient = api_client
         if not self.document_exists():
             raise DocumentNotFoundError(f"Document {self.uri} does not exist")
 
-        self.xml = self.XML(
-            xml_bytestring=self.api_client.get_judgment_xml_bytestring(
-                self.uri,
-                show_unpublished=True,
-            ),
+        self.body: DocumentBody = DocumentBody(
+            xml_bytestring=self.api_client.get_judgment_xml_bytestring(self.uri, show_unpublished=True),
         )
+        """ `Document.body` represents the XML of the document itself, without any information such as version tracking or properties. """
 
     def __repr__(self) -> str:
-        name = self.name or "un-named"
+        name = self.body.name or "un-named"
         return f"<{self.document_noun} {self.uri}: {name}>"
 
     def document_exists(self) -> bool:
@@ -186,104 +152,6 @@ class Document:
         """
         return f"https://caselaw.nationalarchives.gov.uk/{self.uri}"
 
-    @cached_property
-    def name(self) -> str:
-        return self.xml.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:identification/akn:FRBRWork/akn:FRBRname/@value",
-            {"akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0"},
-        )
-
-    @cached_property
-    def court(self) -> str:
-        return self.xml.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:court/text()",
-            {
-                "uk": "https://caselaw.nationalarchives.gov.uk/akn",
-                "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
-            },
-        )
-
-    @cached_property
-    def jurisdiction(self) -> str:
-        return self.xml.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:proprietary/uk:jurisdiction/text()",
-            {
-                "uk": "https://caselaw.nationalarchives.gov.uk/akn",
-                "akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0",
-            },
-        )
-
-    @property
-    def court_and_jurisdiction_identifier_string(self) -> CourtIdentifierString:
-        if self.jurisdiction != "":
-            return CourtIdentifierString("/".join((self.court, self.jurisdiction)))
-        return CourtIdentifierString(self.court)
-
-    @cached_property
-    def document_date_as_string(self) -> str:
-        return self.xml.get_xpath_match_string(
-            "/akn:akomaNtoso/akn:*/akn:meta/akn:identification/akn:FRBRWork/akn:FRBRdate/@date",
-            {"akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0"},
-        )
-
-    @cached_property
-    def document_date_as_date(self) -> Optional[datetime.date]:
-        if not self.document_date_as_string:
-            return None
-        try:
-            return datetime.datetime.strptime(
-                self.document_date_as_string,
-                "%Y-%m-%d",
-            ).date()
-        except ValueError:
-            warnings.warn(
-                f"Unparsable date encountered: {self.document_date_as_string}",
-                UnparsableDate,
-            )
-            return None
-
-    def get_manifestation_datetimes(
-        self,
-        name: Optional[str] = None,
-    ) -> 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",
-            {"akn": "http://docs.oasis-open.org/legaldocml/ns/akn/3.0"},
-        )
-
-        return [parse_string_date_as_utc(event, pytz.UTC) for event in iso_datetimes]
-
-    def get_latest_manifestation_datetime(
-        self,
-        name: Optional[str] = None,
-    ) -> Optional[datetime.datetime]:
-        events = self.get_manifestation_datetimes(name)
-        if not events:
-            return None
-        return max(events)
-
-    def get_latest_manifestation_type(self) -> Optional[str]:
-        return max(
-            (
-                (type, time)
-                for type in ["transform", "tna-enriched"]
-                if (time := self.get_latest_manifestation_datetime(type))
-            ),
-            key=lambda x: x[1],
-        )[0]
-
-    @cached_property
-    def transformation_datetime(self) -> Optional[datetime.datetime]:
-        """When was this document successfully parsed or reparsed (date from XML)"""
-        return self.get_latest_manifestation_datetime("transform")
-
-    @cached_property
-    def enrichment_datetime(self) -> Optional[datetime.datetime]:
-        """When was this document successfully enriched (date from XML)"""
-        return self.get_latest_manifestation_datetime("tna-enriched")
-
     @cached_property
     def is_published(self) -> bool:
         return self.api_client.get_published(self.uri)
@@ -372,10 +240,6 @@ class Document:
         "Is this document a potentially historic version of a document, or is it the main document itself?"
         return extract_version(self.uri) != 0
 
-    @cached_property
-    def content_as_xml(self) -> str:
-        return self.xml.xml_as_string
-
     def content_as_html(
         self,
         version_uri: Optional[DocumentURIString] = None,
@@ -418,39 +282,21 @@ class Document:
 
         :return: `True` if this document is in a 'failure' state, otherwise `False`
         """
-        if self.failed_to_parse:
-            return True
-        return False
+        return self.body.failed_to_parse
 
     @cached_property
     def is_parked(self) -> bool:
-        if "parked" in self.uri:
-            return True
-        return False
-
-    @cached_property
-    def failed_to_parse(self) -> bool:
-        """
-        Did this document entirely fail to parse?
-
-        :return: `True` if there was a complete parser failure, otherwise `False`
-        """
-        if "error" in self.xml.root_element:
-            return True
-        return False
+        return "parked" in self.uri
 
     @cached_property
     def has_name(self) -> bool:
-        if not self.name:
-            return False
-
-        return True
+        return bool(self.body.name)
 
     @cached_property
     def has_valid_court(self) -> bool:
         try:
             return bool(
-                courts.get_by_code(self.court_and_jurisdiction_identifier_string),
+                courts.get_by_code(self.body.court_and_jurisdiction_identifier_string),
             )
         except CourtNotFoundException:
             return False
@@ -521,9 +367,7 @@ class Document:
         """
         Is it sensible to enrich this document?
         """
-        if (self.enriched_recently is False) and self.validates_against_schema:
-            return True
-        return False
+        return (self.enriched_recently is False) and self.validates_against_schema
 
     @cached_property
     def enriched_recently(self) -> bool:
@@ -531,14 +375,13 @@ class Document:
         Has this document been enriched recently?
         """
 
-        last_enrichment = self.enrichment_datetime
+        last_enrichment = self.body.enrichment_datetime
         if not last_enrichment:
             return False
 
         now = datetime.datetime.now(tz=datetime.timezone.utc)
-        if now - last_enrichment < MINIMUM_ENRICHMENT_TIME:
-            return True
-        return False
+
+        return now - last_enrichment < MINIMUM_ENRICHMENT_TIME
 
     @cached_property
     def validates_against_schema(self) -> bool:
@@ -599,10 +442,7 @@ class Document:
         else:
             raise DocumentNotSafeForDeletion
 
-    def overwrite(self, new_citation: str) -> None:
-        self.api_client.overwrite_document(self.uri, new_citation)
-
-    def move(self, new_citation: str) -> None:
+    def move(self, new_citation: NeutralCitationString) -> None:
         self.api_client.update_document_uri(self.uri, new_citation)
 
     def force_reparse(self) -> None:
@@ -612,7 +452,11 @@ class Document:
         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 = self.document_date_as_string if self.document_date_as_string > "1001" else None
+        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)
+            else None
+        )
 
         # the keys of parser_instructions should exactly match the parser output
         # in the *-metadata.json files by the parser. Whilst typically empty
@@ -621,9 +465,9 @@ class Document:
         parser_instructions: ParserInstructionsDict = {
             "documentType": parser_type_noun,
             "metadata": {
-                "name": self.name or None,
+                "name": self.body.name or None,
                 "cite": self.best_human_identifier or None,
-                "court": self.court or None,
+                "court": self.body.court or None,
                 "date": checked_date,
                 "uri": self.uri,
             },
@@ -650,41 +494,4 @@ class Document:
         """
         Is it sensible to reparse this document?
         """
-        if self.docx_exists():
-            return True
-        return False
-
-    class XML:
-        """
-        Represents the XML of a document, and should contain all methods for interacting with it.
-        """
-
-        def __init__(self, xml_bytestring: bytes):
-            """
-            :raises NonXMLDocumentError: This document is not valid XML
-            """
-            try:
-                self.xml_as_tree: etree.Element = etree.fromstring(xml_bytestring)
-            except etree.XMLSyntaxError:
-                raise NonXMLDocumentError
-
-        @property
-        def xml_as_string(self) -> str:
-            """
-            :return: A string representation of this document's XML tree.
-            """
-            return str(etree.tostring(self.xml_as_tree).decode(encoding="utf-8"))
-
-        @property
-        def root_element(self) -> str:
-            return str(self.xml_as_tree.tag)
-
-        def get_xpath_match_string(self, xpath: str, namespaces: Dict[str, str]) -> str:
-            return get_xpath_match_string(self.xml_as_tree, xpath, namespaces)
-
-        def get_xpath_match_strings(
-            self,
-            xpath: str,
-            namespaces: Dict[str, str],
-        ) -> list[str]:
-            return get_xpath_match_strings(self.xml_as_tree, xpath, namespaces)
+        return self.docx_exists()