ds-caselaw-marklogic-api-client 35.1.1__tar.gz → 36.0.1__tar.gz

{ds_caselaw_marklogic_api_client-35.1.1 → ds_caselaw_marklogic_api_client-36.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ds-caselaw-marklogic-api-client
-Version: 35.1.1
+Version: 36.0.1
 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
@@ -10,7 +10,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: boto3 (>=1.26.112,<2.0.0)
-Requires-Dist: certifi (>=2025.1.31,<2025.2.0)
+Requires-Dist: certifi (>=2025.4.26,<2025.5.0)
 Requires-Dist: charset-normalizer (>=3.0.0,<4.0.0)
 Requires-Dist: django-environ (>=0.12.0)
 Requires-Dist: ds-caselaw-utils (>=2.0.0,<3.0.0)

{ds_caselaw_marklogic_api_client-35.1.1 → ds_caselaw_marklogic_api_client-36.0.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ds-caselaw-marklogic-api-client"
-version = "35.1.1"
+version = "36.0.1"
 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 = "^3.10.0"
-certifi = ">=2025.1.31,<2025.2.0"
+certifi = ">=2025.4.26,<2025.5.0"
 charset-normalizer = "^3.0.0"
 django-environ = ">=0.12.0"
 idna = "^3.4"
@@ -33,11 +33,11 @@ sqids = "^0.5.0"
 [tool.poetry.group.dev.dependencies]
 coverage = "7.8.0"
 pytest = "8.3.5"
-beautifulsoup4 = "4.13.3"
+beautifulsoup4 = "4.13.4"
 responses = "0.25.7"
 python-dotenv = "1.1.0"
 time-machine = "2.16.0"
-moto = {version = "5.1.3", extras = ["all"]}
+moto = {version = "5.1.4", extras = ["all"]}
 
 [tool.poetry.group.docs]
 optional = true

{ds_caselaw_marklogic_api_client-35.1.1 → ds_caselaw_marklogic_api_client-36.0.1}/src/caselawclient/factories.py

@@ -85,7 +85,7 @@ class DocumentFactory:
         document.body = kwargs.pop("body") if "body" in kwargs else DocumentBodyFactory.build()
 
         if identifiers is None:
-            document.identifiers.add(FindCaseLawIdentifier(value="a1b2c3"))
+            document.identifiers.add(FindCaseLawIdentifier(value="tn4t35ts"))
         else:
             for identifier in identifiers:
                 document.identifiers.add(identifier)
@@ -146,15 +146,18 @@ class SearchResultMetadataFactory(SimpleFactory):
 class SearchResultFactory(SimpleFactory):
     target_class = SearchResult
 
-    # "name_of_attribute": ("name of incoming param", "default value")
     PARAMS_MAP = {
-        "uri": "test/2023/123",
+        "uri": "d-a1b2c3",
         "name": "Judgment v Judgement",
-        "neutral_citation": "[2023] Test 123",
+        "neutral_citation": "[2025] UKSC 123",
         "court": "Court of Testing",
-        "date": datetime.date(2023, 2, 3),
+        "date": datetime.datetime(2023, 2, 3),
+        "transformation_date": str(datetime.datetime(2023, 2, 3, 12, 34)),
         "metadata": SearchResultMetadataFactory.build(),
         "is_failure": False,
+        "matches": None,
+        "slug": "uksc/2025/1",
+        "content_hash": "ed7002b439e9ac845f22357d822bac1444730fbdb6016d3ec9432297b9ec9f73",
     }
 
 
@@ -173,7 +176,7 @@ class IdentifierResolutionFactory:
             "documents.compiled_url_slugs.identifier_uuid": resolution_uuid or "24b9a384-8bcf-4f20-996a-5c318f8dc657",
             "documents.compiled_url_slugs.document_uri": document_uri or "/ewca/civ/2003/547.xml",
             "documents.compiled_url_slugs.identifier_slug": identifier_slug or "ewca/civ/2003/54721",
-            "documents.compiled_url_slugs.document_published": "true" if published else "false",
+            "documents.compiled_url_slugs.document_published": published,
             "documents.compiled_url_slugs.identifier_namespace": namespace or "ukncn",
             "documents.compiled_url_slugs.identifier_value": value or "[2003] EWCA 54721 (Civ)",
         }

{ds_caselaw_marklogic_api_client-35.1.1 → ds_caselaw_marklogic_api_client-36.0.1}/src/caselawclient/identifier_resolution.py

@@ -45,7 +45,7 @@ class IdentifierResolution(NamedTuple):
             identifier_uuid=row["documents.compiled_url_slugs.identifier_uuid"],
             document_uri=MarkLogicDocumentURIString(row["documents.compiled_url_slugs.document_uri"]),
             identifier_slug=DocumentIdentifierSlug(row["documents.compiled_url_slugs.identifier_slug"]),
-            document_published=row["documents.compiled_url_slugs.document_published"] == "true",
+            document_published=row["documents.compiled_url_slugs.document_published"],
             identifier_value=DocumentIdentifierValue(row["documents.compiled_url_slugs.identifier_value"]),
             identifier_namespace=identifier_namespace,
             identifier_type=IDENTIFIER_NAMESPACE_MAP[identifier_namespace],

{ds_caselaw_marklogic_api_client-35.1.1 → ds_caselaw_marklogic_api_client-36.0.1}/src/caselawclient/models/identifiers/__init__.py

@@ -6,6 +6,8 @@ from lxml import etree
 
 from caselawclient.types import DocumentIdentifierSlug, DocumentIdentifierValue
 
+from .exceptions import IdentifierValidationException, UUIDMismatchError
+
 IDENTIFIER_PACKABLE_ATTRIBUTES: list[str] = [
     "uuid",
     "value",
@@ -18,14 +20,6 @@ IDENTIFIER_UNPACKABLE_ATTRIBUTES: list[str] = [
 ]
 
 
-class InvalidIdentifierXMLRepresentationException(Exception):
-    pass
-
-
-class UUIDMismatchError(Exception):
-    pass
-
-
 class IdentifierSchema(ABC):
     """
     A base class which describes what an identifier schema should look like.
@@ -89,6 +83,11 @@ class Identifier(ABC):
         return self.value
 
     def __init__(self, value: str, uuid: Optional[str] = None) -> None:
+        if not self.schema.validate_identifier(value=value):
+            raise IdentifierValidationException(
+                f'Identifier value "{value}" is not valid according to the {self.schema.name} schema.'
+            )
+
         self.value = DocumentIdentifierValue(value)
         if uuid:
             self.uuid = uuid

ds_caselaw_marklogic_api_client-36.0.1/src/caselawclient/models/identifiers/exceptions.py

@@ -0,0 +1,10 @@
+class InvalidIdentifierXMLRepresentationException(Exception):
+    pass
+
+
+class UUIDMismatchError(Exception):
+    pass
+
+
+class IdentifierValidationException(Exception):
+    pass

{ds_caselaw_marklogic_api_client-35.1.1 → ds_caselaw_marklogic_api_client-36.0.1}/src/caselawclient/models/identifiers/neutral_citation.py

@@ -6,6 +6,7 @@ from ds_caselaw_utils.types import NeutralCitationString
 from caselawclient.types import DocumentIdentifierSlug
 
 from . import Identifier, IdentifierSchema
+from .exceptions import IdentifierValidationException
 
 VALID_NCN_PATTERN = re.compile(r"(^\[([0-9]{4})\] ([a-zA-Z]+)(?: ([a-zA-Z]+))? ([0-9]+)(?: \(([a-zA-Z]+)\))?$)")
 """
@@ -23,6 +24,18 @@ TODO: When these capture groups are being used in anger (eg to build URL slugs)
 """
 
 
+class NCNValidationException(IdentifierValidationException):
+    pass
+
+
+class NCNDoesNotMatchExpectedPatternException(NCNValidationException):
+    pass
+
+
+class NCNCannotConvertToValidURLSlugException(NCNValidationException):
+    pass
+
+
 class NeutralCitationNumberSchema(IdentifierSchema):
     """
     Identifier schema describing a Neutral Citation Number.
@@ -37,7 +50,16 @@ class NeutralCitationNumberSchema(IdentifierSchema):
 
     @classmethod
     def validate_identifier(cls, value: str) -> bool:
-        return bool(VALID_NCN_PATTERN.match(value))
+        # Quick check to see if the NCN matches the expected pattern
+        if not bool(VALID_NCN_PATTERN.match(value)):
+            raise NCNDoesNotMatchExpectedPatternException(f"NCN '{value}' is not in the expected format")
+
+        # Can we convert this to a URL? neutral_url returns False if not.
+        # This functionally tests to see if the court exists, since only valid patterns (where we know how to match the court code) will convert
+        if not neutral_url(NeutralCitationString(value)):
+            raise NCNCannotConvertToValidURLSlugException(f"NCN '{value}' cannot be converted to an NCN-based URL slug")
+
+        return True
 
     @classmethod
     def compile_identifier_url_slug(cls, value: str) -> DocumentIdentifierSlug:
@@ -45,7 +67,7 @@ class NeutralCitationNumberSchema(IdentifierSchema):
             NeutralCitationString(value)
         )  # TODO: At some point this should move out of utils and into this class.
         if not ncn_based_uri_string:
-            raise Exception(f"Unable to convert NCN {value} into NCN-based URL slug")
+            raise NCNCannotConvertToValidURLSlugException(f"NCN '{value}' cannot be converted to an NCN-based URL slug")
         return DocumentIdentifierSlug(ncn_based_uri_string)
 
 

{ds_caselaw_marklogic_api_client-35.1.1 → ds_caselaw_marklogic_api_client-36.0.1}/src/caselawclient/models/identifiers/unpacker.py

@@ -3,7 +3,8 @@ from warnings import warn
 
 from lxml import etree
 
-from . import IDENTIFIER_UNPACKABLE_ATTRIBUTES, Identifier, Identifiers, InvalidIdentifierXMLRepresentationException
+from . import IDENTIFIER_UNPACKABLE_ATTRIBUTES, Identifier, Identifiers
+from .exceptions import InvalidIdentifierXMLRepresentationException
 from .fclid import FindCaseLawIdentifier
 from .neutral_citation import NeutralCitationNumber
 from .press_summary_ncn import PressSummaryRelatedNCNIdentifier