pathling 9.2.0__tar.gz → 9.2.0.dev0__tar.gz

{pathling-9.2.0 → pathling-9.2.0.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pathling
-Version: 9.2.0
+Version: 9.2.0.dev0
 Summary: Python API for Pathling
 Project-URL: Homepage, https://github.com/aehrc/pathling
 Author-email: "Australian e-Health Research Centre, CSIRO" <pathling@csiro.au>

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/bulk.py

@@ -1,12 +1,12 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
-#
+# 
 #      http://www.apache.org/licenses/LICENSE-2.0
-#
+# 
 #  Unless required by applicable law or agreed to in writing, software
 #  distributed under the License is distributed on an "AS IS" BASIS,
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@@ -49,10 +49,9 @@ def test_bulk_exports():
     # Base parameters from the demo server
     fhir_server = "https://bulk-data.smarthealthit.org/fhir"
     output_base = os.path.join(tempfile.gettempdir(), "bulk_export_test")
-
+    
     if os.path.exists(output_base):
         import shutil
-
         shutil.rmtree(output_base)
     os.makedirs(output_base)
 
@@ -76,8 +75,8 @@ def test_bulk_exports():
             "use_smart": True,
             "use_form_for_basic_auth": False,
             "scope": "system/*.read",
-            "token_expiry_tolerance": 30,
-        },
+            "token_expiry_tolerance": 30
+        }
     )
     print("System export completed successfully")
 
@@ -86,7 +85,7 @@ def test_bulk_exports():
     pc.read.bulk(
         fhir_endpoint_url=fhir_server,
         output_dir=f"{output_base}/group_basic",
-        group_id="BMCHealthNet",
+        group_id="BMCHealthNet"
     )
     print("Group export completed successfully")
 
@@ -104,7 +103,7 @@ def test_bulk_exports():
         type_filters=["Patient?status=active"],
         output_extension="ndjson",
         timeout=1800,
-        max_concurrent_downloads=8,
+        max_concurrent_downloads=8
     )
     print("Group export completed successfully")
 
@@ -115,8 +114,8 @@ def test_bulk_exports():
         output_dir=f"{output_base}/patient_basic",
         patients=[
             "Patient/58c297c4-d684-4677-8024-01131d93835e",
-            "Patient/118616a4-f0b2-411f-8050-39d5d27c738c",
-        ],
+            "Patient/118616a4-f0b2-411f-8050-39d5d27c738c"
+        ]
     )
     print("Patient export completed successfully")
 
@@ -128,7 +127,7 @@ def test_bulk_exports():
         patients=[
             "Patient/58c297c4-d684-4677-8024-01131d93835e",
             "Patient/118616a4-f0b2-411f-8050-39d5d27c738c",
-            "Patient/21fba439-ca79-411f-a081-37a432a78f3a",
+            "Patient/21fba439-ca79-411f-a081-37a432a78f3a"
         ],
         output_format="application/fhir+ndjson",
         since=datetime(2020, 1, 1, tzinfo=timezone.utc),
@@ -138,7 +137,7 @@ def test_bulk_exports():
         type_filters=["Observation?category=vital-signs"],
         output_extension="ndjson",
         timeout=2400,
-        max_concurrent_downloads=3,
+        max_concurrent_downloads=3
     )
     print("Patient export completed successfully")
 

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/designation.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -15,14 +15,14 @@
 
 import os
 
-from pathling import Coding, PathlingContext, designation, to_snomed_coding
+from pathling import PathlingContext, Coding, to_snomed_coding, designation
 
 HERE = os.path.abspath(os.path.dirname(__file__))
 
 pc = PathlingContext.create()
 
 csv = pc.spark.read.options(header=True).csv(
-    f"file://{os.path.join(HERE, 'data/csv/conditions.csv')}"
+    f'file://{os.path.join(HERE, "data/csv/conditions.csv")}'
 )
 
 # Obtain display name for snomed codes

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/display.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -15,14 +15,14 @@
 
 import os
 
-from pathling import PathlingContext, display, to_snomed_coding
+from pathling import PathlingContext, to_snomed_coding, display
 
 HERE = os.path.abspath(os.path.dirname(__file__))
 
 pc = PathlingContext.create()
 
 csv = pc.spark.read.options(header=True).csv(
-    f"file://{os.path.join(HERE, 'data/csv/conditions.csv')}"
+    f'file://{os.path.join(HERE, "data/csv/conditions.csv")}'
 )
 
 # Obtain display name for snomed codes

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/encode_bundles.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/encode_resources.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/fhir_view.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -14,7 +14,6 @@
 #  limitations under the License.
 
 import os
-
 from pathling import PathlingContext
 
 HERE = os.path.abspath(os.path.dirname(__file__))
@@ -25,38 +24,35 @@ pc = PathlingContext.create()
 datasource = pc.read.ndjson(NDJSON_DIR)
 
 view_ds = datasource.view(
-    resource="Patient",
+    resource='Patient',
     select=[
         {
-            "column": [
-                {"path": "id", "name": "id"},
-                {"path": "gender", "name": "gender"},
-                {
-                    "path": "telecom.where(system='phone').value ",
-                    "name": "phone_numbers",
-                    "collection": True,
-                },
+            'column': [
+                {'path': 'id', 'name': 'id'},
+                {'path': 'gender', 'name': 'gender'},
+                {'path': "telecom.where(system='phone').value ", 'name': 'phone_numbers',
+                 'collection': True},
             ]
         },
         {
-            "forEach": "name",
-            "column": [
-                {"path": "use", "name": "name_use"},
-                {"path": "family", "name": "family_name"},
+            'forEach': 'name',
+            'column': [
+                {'path': 'use', 'name': 'name_use'},
+                {'path': 'family', 'name': 'family_name'},
             ],
-            "select": [
+            'select': [
                 {
-                    "forEachOrNull": "given",
-                    "column": [
-                        {"path": "$this", "name": "given_name"},
+                    'forEachOrNull': 'given',
+                    'column': [
+                        {'path': '$this', 'name': 'given_name'},
                     ],
                 }
-            ],
+            ]
         },
     ],
     where=[
-        {"path": "gender = 'male'"},
-    ],
+        {'path': "gender = 'male'"},
+    ]
 )
 
 view_ds.show()

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/member_of.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -17,9 +17,9 @@ import os
 
 from pathling import (
     PathlingContext,
-    member_of,
-    to_ecl_value_set,
     to_snomed_coding,
+    to_ecl_value_set,
+    member_of,
 )
 
 HERE = os.path.abspath(os.path.dirname(__file__))
@@ -34,7 +34,7 @@ pc = PathlingContext.create(
 pc.spark.sparkContext.setLogLevel("DEBUG")
 
 csv = pc.spark.read.options(header=True).csv(
-    f"file://{os.path.join(HERE, 'data/csv/conditions.csv')}"
+    f'file://{os.path.join(HERE, "data/csv/conditions.csv")}'
 )
 
 VIRAL_INFECTION_ECL = """

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/property_of.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -17,10 +17,10 @@ import os
 
 from pathling import (
     PathlingContext,
-    PropertyType,
-    display,
-    property_of,
     to_snomed_coding,
+    property_of,
+    display,
+    PropertyType,
 )
 
 HERE = os.path.abspath(os.path.dirname(__file__))
@@ -28,7 +28,7 @@ HERE = os.path.abspath(os.path.dirname(__file__))
 pc = PathlingContext.create()
 
 csv = pc.spark.read.options(header=True).csv(
-    f"file://{os.path.join(HERE, 'data/csv/conditions.csv')}"
+    f'file://{os.path.join(HERE, "data/csv/conditions.csv")}'
 )
 
 # Get the parent codes for each code in the dataset.

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/subsumes.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -15,14 +15,14 @@
 
 import os
 
-from pathling import Coding, PathlingContext, subsumes, to_coding
+from pathling import PathlingContext, Coding, to_coding, subsumes
 
 HERE = os.path.abspath(os.path.dirname(__file__))
 
 pc = PathlingContext.create()
 
 csv = pc.spark.read.options(header=True).csv(
-    f"file://{os.path.join(HERE, 'data/csv/conditions.csv')}"
+    f'file://{os.path.join(HERE, "data/csv/conditions.csv")}'
 )
 first_3 = csv.limit(3)
 cross_join = first_3.selectExpr(

{pathling-9.2.0 → pathling-9.2.0.dev0}/examples/translate.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -24,7 +24,7 @@ HERE = os.path.abspath(os.path.dirname(__file__))
 pc = PathlingContext.create()
 
 csv = pc.spark.read.options(header=True).csv(
-    f"file://{os.path.join(HERE, 'data/csv/conditions.csv')}"
+    f'file://{os.path.join(HERE, "data/csv/conditions.csv")}'
 )
 
 # Translate codings to Read CTV3 using the map that ships with SNOMED CT.

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/__init__.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -16,19 +16,19 @@
 from .coding import Coding
 from .context import PathlingContext, StorageType
 from .core import Expression, VariableExpression
-from .datasource import DataSource, DataSources
+from .datasource import DataSources, DataSource
 from .fhir import MimeType, Version
-from .functions import to_coding, to_ecl_value_set, to_snomed_coding
+from .functions import to_coding, to_snomed_coding, to_ecl_value_set
 from .udfs import (
-    Equivalence,
-    PropertyType,
-    designation,
-    display,
     member_of,
-    property_of,
-    subsumed_by,
-    subsumes,
     translate,
+    subsumes,
+    subsumed_by,
+    property_of,
+    display,
+    designation,
+    PropertyType,
+    Equivalence,
 )
 
 __all__ = [

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/_version.py

@@ -2,8 +2,8 @@
 # Auto generated from POM project version.
 # Please do not modify.
 #
-__version__="9.2.0"
-__java_version__="9.2.0"
+__version__="9.2.0.dev0"
+__java_version__="9.2.0-SNAPSHOT"
 __scala_version__="2.13"
 __delta_version__="4.0.0"
 __hadoop_version__="3.4.1"

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/bulk.py

@@ -1,12 +1,12 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
-#
+# 
 #      http://www.apache.org/licenses/LICENSE-2.0
-#
+# 
 #  Unless required by applicable law or agreed to in writing, software
 #  distributed under the License is distributed on an "AS IS" BASIS,
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@@ -15,7 +15,7 @@
 
 from dataclasses import dataclass
 from datetime import datetime, timezone
-from typing import Callable, List, Optional, Tuple
+from typing import List, Optional, Tuple, Callable
 
 from py4j.java_gateway import JavaObject, JVMView
 from pyspark.sql import SparkSession
@@ -26,7 +26,6 @@ class FileResult:
     """
     Represents the result of a single file export operation.
     """
-
     source: str
     """
     The source URL of the exported file.
@@ -46,7 +45,6 @@ class ExportResult:
     """
     Represents the result of a bulk export operation.
     """
-
     transaction_time: datetime
     """
     The time at which the transaction was processed at the server.
@@ -58,29 +56,30 @@ class ExportResult:
     """
 
     @classmethod
-    def from_java(cls, java_result: JavaObject) -> "ExportResult":
+    def from_java(cls, java_result: JavaObject) -> 'ExportResult':
         """
         Create an ExportResult from a Java export result object.
-
+        
         :param java_result: The Java export result object
         :return: A Python ExportResult object
         """
         # Convert transaction time from Java Instant to Python datetime
         transaction_time = datetime.fromtimestamp(
-            java_result.getTransactionTime().toEpochMilli() / 1000.0, tz=timezone.utc
-        )
+            java_result.getTransactionTime().toEpochMilli() / 1000.0, tz=timezone.utc)
 
         # Convert file results
         file_results = [
             FileResult(
                 source=str(java_file_result.getSource()),
                 destination=str(java_file_result.getDestination()),
-                size=java_file_result.getSize(),
-            )
+                size=java_file_result.getSize())
             for java_file_result in java_result.getResults()
         ]
 
-        return cls(transaction_time=transaction_time, results=file_results)
+        return cls(
+            transaction_time=transaction_time,
+            results=file_results
+        )
 
 
 class BulkExportClient:
@@ -91,7 +90,7 @@ class BulkExportClient:
     def __init__(self, java_client):
         """
         Create a new BulkExportClient that wraps a Java BulkExportClient.
-
+        
         :param java_client: The Java BulkExportClient instance to wrap
         """
         self._java_client = java_client
@@ -99,33 +98,27 @@ class BulkExportClient:
     def export(self) -> ExportResult:
         """
         Export data from the FHIR server.
-
+        
         :return: The result of the export operation as a Python ExportResult object
         """
         java_result = self._java_client.export()
         return ExportResult.from_java(java_result)
 
     @classmethod
-    def _configure_builder(
-        cls,
-        jvm,
-        builder,
-        fhir_endpoint_url: str,
-        output_dir: str,
-        output_format: str = "application/fhir+ndjson",
-        since: Optional[datetime] = None,
-        types: Optional[List[str]] = None,
-        elements: Optional[List[str]] = None,
-        include_associated_data: Optional[List[str]] = None,
-        type_filters: Optional[List[str]] = None,
-        output_extension: str = "ndjson",
-        timeout: Optional[int] = None,
-        max_concurrent_downloads: int = 10,
-        auth_config: Optional[dict] = None,
-    ):
+    def _configure_builder(cls, jvm, builder, fhir_endpoint_url: str, output_dir: str,
+                           output_format: str = "application/fhir+ndjson",
+                           since: Optional[datetime] = None,
+                           types: Optional[List[str]] = None,
+                           elements: Optional[List[str]] = None,
+                           include_associated_data: Optional[List[str]] = None,
+                           type_filters: Optional[List[str]] = None,
+                           output_extension: str = "ndjson",
+                           timeout: Optional[int] = None,
+                           max_concurrent_downloads: int = 10,
+                           auth_config: Optional[dict] = None):
         """
         Configure common builder parameters.
-
+        
         :param jvm: The JVM instance
         :param builder: The builder instance to configure
         :param fhir_endpoint_url: The URL of the FHIR server
@@ -164,13 +157,11 @@ class BulkExportClient:
             if since.tzinfo is None:
                 raise ValueError("datetime must include timezone information")
             # Format with microsecond precision and timezone offset
-            instant_str = since.strftime("%Y-%m-%dT%H:%M:%S.%f")[
-                :-3
-            ]  # Truncate to milliseconds
+            instant_str = since.strftime('%Y-%m-%dT%H:%M:%S.%f')[:-3]  # Truncate to milliseconds
             if since.utcoffset() is None:
-                instant_str += "Z"
+                instant_str += 'Z'
             else:
-                offset = since.strftime("%z")
+                offset = since.strftime('%z')
                 # Insert colon in timezone offset
                 instant_str += f"{offset[:3]}:{offset[3:]}"
             java_instant = jvm.java.time.Instant.parse(instant_str)
@@ -201,33 +192,33 @@ class BulkExportClient:
             auth_builder.tokenExpiryTolerance(120)
 
             # Map Python config to Java builder methods
-            if "enabled" in auth_config:
-                auth_builder.enabled(auth_config["enabled"])
-            if "use_smart" in auth_config:
-                auth_builder.useSMART(auth_config["use_smart"])
-            if "token_endpoint" in auth_config:
-                auth_builder.tokenEndpoint(auth_config["token_endpoint"])
-            if "client_id" in auth_config:
-                auth_builder.clientId(auth_config["client_id"])
-            if "client_secret" in auth_config:
-                auth_builder.clientSecret(auth_config["client_secret"])
-            if "private_key_jwk" in auth_config:
-                auth_builder.privateKeyJWK(auth_config["private_key_jwk"])
-            if "use_form_for_basic_auth" in auth_config:
-                auth_builder.useFormForBasicAuth(auth_config["use_form_for_basic_auth"])
-            if "scope" in auth_config:
-                auth_builder.scope(auth_config["scope"])
-            if "token_expiry_tolerance" in auth_config:
-                auth_builder.tokenExpiryTolerance(auth_config["token_expiry_tolerance"])
+            if 'enabled' in auth_config:
+                auth_builder.enabled(auth_config['enabled'])
+            if 'use_smart' in auth_config:
+                auth_builder.useSMART(auth_config['use_smart'])
+            if 'token_endpoint' in auth_config:
+                auth_builder.tokenEndpoint(auth_config['token_endpoint'])
+            if 'client_id' in auth_config:
+                auth_builder.clientId(auth_config['client_id'])
+            if 'client_secret' in auth_config:
+                auth_builder.clientSecret(auth_config['client_secret'])
+            if 'private_key_jwk' in auth_config:
+                auth_builder.privateKeyJWK(auth_config['private_key_jwk'])
+            if 'use_form_for_basic_auth' in auth_config:
+                auth_builder.useFormForBasicAuth(auth_config['use_form_for_basic_auth'])
+            if 'scope' in auth_config:
+                auth_builder.scope(auth_config['scope'])
+            if 'token_expiry_tolerance' in auth_config:
+                auth_builder.tokenExpiryTolerance(auth_config['token_expiry_tolerance'])
 
             auth_config_obj = auth_builder.build()
             builder.withAuthConfig(auth_config_obj)
 
     @classmethod
-    def for_system(cls, spark, *args, **kwargs) -> "BulkExportClient":
+    def for_system(cls, spark, *args, **kwargs) -> 'BulkExportClient':
         """
         Create a builder for a system-level export.
-
+        
         :param spark: The SparkSession instance
         :param fhir_endpoint_url: The URL of the FHIR server to export from
         :param output_dir: The directory to write the output files to
@@ -248,18 +239,11 @@ class BulkExportClient:
         return cls(builder.build())
 
     @classmethod
-    def for_group(
-        cls,
-        spark,
-        fhir_endpoint_url: str,
-        output_dir: str,
-        group_id: str,
-        *args,
-        **kwargs,
-    ) -> "BulkExportClient":
+    def for_group(cls, spark, fhir_endpoint_url: str, output_dir: str,
+                  group_id: str, *args, **kwargs) -> 'BulkExportClient':
         """
         Create a builder for a group-level export.
-
+        
         :param spark: The SparkSession instance
         :param fhir_endpoint_url: The URL of the FHIR server to export from
         :param output_dir: The directory to write the output files to
@@ -278,24 +262,15 @@ class BulkExportClient:
         """
         # Pass group_id directly to groupBuilder
         builder, jvm = cls._create_builder(spark, lambda bc: bc.groupBuilder(group_id))
-        cls._configure_builder(
-            jvm, builder, fhir_endpoint_url, output_dir, *args, **kwargs
-        )
+        cls._configure_builder(jvm, builder, fhir_endpoint_url, output_dir, *args, **kwargs)
         return cls(builder.build())
 
     @classmethod
-    def for_patient(
-        cls,
-        spark,
-        fhir_endpoint_url: str,
-        output_dir: str,
-        patients: Optional[List[str]] = None,
-        *args,
-        **kwargs,
-    ) -> "BulkExportClient":
+    def for_patient(cls, spark, fhir_endpoint_url: str, output_dir: str,
+                    patients: Optional[List[str]] = None, *args, **kwargs) -> 'BulkExportClient':
         """
         Create a builder for a patient-level export.
-
+        
         :param spark: The SparkSession instance
         :param fhir_endpoint_url: The URL of the FHIR server to export from
         :param output_dir: The directory to write the output files to
@@ -317,21 +292,19 @@ class BulkExportClient:
             for patient in patients:
                 ref = jvm.au.csiro.fhir.model.Reference.of(patient)
                 builder.withPatient(ref)
-        cls._configure_builder(
-            jvm, builder, fhir_endpoint_url, output_dir, *args, **kwargs
-        )
+        cls._configure_builder(jvm, builder, fhir_endpoint_url, output_dir, *args, **kwargs)
         return cls(builder.build())
 
     @classmethod
-    def _create_builder(
-        cls, spark: SparkSession, factory_f: Callable[[JavaObject], JavaObject]
-    ) -> Tuple[JavaObject, JVMView]:
+    def _create_builder(cls,
+                        spark: SparkSession,
+                        factory_f: Callable[[JavaObject], JavaObject]) -> Tuple[
+        JavaObject, JVMView]:
+
         jvm: JVMView = spark._jvm
         client_class = jvm.au.csiro.fhir.export.BulkExportClient
         builder: JavaObject = factory_f(client_class)
         builder = builder.withFileStoreFactory(
-            jvm.au.csiro.filestore.hdfs.HdfsFileStoreFactory(
-                spark._jsc.sc().hadoopConfiguration()
-            )
+            jvm.au.csiro.filestore.hdfs.HdfsFileStoreFactory(spark._jsc.sc().hadoopConfiguration())
         )
         return (builder, jvm)

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/coding.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/context.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -15,15 +15,15 @@
 
 # noinspection PyPackageRequirements
 
-from typing import TYPE_CHECKING, Optional, Sequence
-
 from py4j.java_gateway import JavaObject
 from pyspark.sql import DataFrame, SparkSession
+from typing import Optional, Sequence, TYPE_CHECKING
 
 from pathling._version import (
-    __delta_version__,
     __java_version__,
     __scala_version__,
+    __delta_version__,
+    __hadoop_version__,
 )
 from pathling.fhir import MimeType
 
@@ -193,7 +193,7 @@ class PathlingContext:
                 SparkSession.builder.config(
                     "spark.jars.packages",
                     f"au.csiro.pathling:library-runtime:{__java_version__},"
-                    f"io.delta:delta-spark_{__scala_version__}:{__delta_version__},",
+                    f"io.delta:delta-spark_{__scala_version__}:{__delta_version__},"
                 )
                 .config(
                     "spark.sql.extensions", "io.delta.sql.DeltaSparkSessionExtension"
@@ -208,9 +208,7 @@ class PathlingContext:
             if enable_remote_debugging:
                 suspend_option = "y" if debug_suspend else "n"
                 debug_options = f"-agentlib:jdwp=transport=dt_socket,server=y,suspend={suspend_option},address={debug_port}"
-                spark_builder = spark_builder.config(
-                    "spark.driver.extraJavaOptions", debug_options
-                )
+                spark_builder = spark_builder.config("spark.driver.extraJavaOptions", debug_options)
 
             return spark_builder.getOrCreate()
 
@@ -372,6 +370,7 @@ class PathlingContext:
             )
         )
 
+
     @property
     def read(self) -> "DataSources":
         """

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/core.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -13,7 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-from typing import Any, Callable, Optional, Sequence, Tuple, Union
+from typing import Any, Callable, Sequence, Tuple, Optional, Union
 
 from py4j.java_collections import SetConverter
 from py4j.java_gateway import JavaObject

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/datasink.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -13,57 +13,14 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-from dataclasses import dataclass
-from typing import TYPE_CHECKING, Callable, List, Optional
+from typing import Callable, Optional
 
 from pathling.core import SparkConversionsMixin, StringMapper
-
+from typing import TYPE_CHECKING
 if TYPE_CHECKING:
     from pathling.datasource import DataSource
 
 
-@dataclass
-class FileInformation:
-    """
-    Information about a file created by a write operation.
-
-    :param fhir_resource_type: The FHIR resource type code for this file.
-    :param absolute_url: The absolute URL or path to the file.
-    """
-
-    fhir_resource_type: str
-    absolute_url: str
-
-
-@dataclass
-class WriteDetails:
-    """
-    Details about files created or modified by a write operation.
-
-    :param file_infos: A list of file information objects describing each file written.
-    """
-
-    file_infos: List[FileInformation]
-
-
-def _convert_write_details(java_result) -> WriteDetails:
-    """
-    Convert a Java WriteDetails object to a Python WriteDetails dataclass.
-
-    :param java_result: The Java WriteDetails object from the library API.
-    :returns: A Python WriteDetails dataclass with the converted data.
-    """
-    java_file_infos = java_result.fileInfos()
-    file_infos = [
-        FileInformation(
-            fhir_resource_type=fi.fhirResourceType(),
-            absolute_url=fi.absoluteUrl(),
-        )
-        for fi in java_file_infos
-    ]
-    return WriteDetails(file_infos=file_infos)
-
-
 class SaveMode:
     """
     Constants that represent the different save modes.
@@ -100,7 +57,7 @@ class DataSinks(SparkConversionsMixin):
         path: str,
         save_mode: Optional[str] = SaveMode.ERROR,
         file_name_mapper: Callable[[str], str] = None,
-    ) -> WriteDetails:
+    ) -> None:
         """
         Writes the data to a directory of NDJSON files. The files will be named using the resource
         type and the ".ndjson" extension.
@@ -113,20 +70,16 @@ class DataSinks(SparkConversionsMixin):
             - "error" will raise an error if the file already exists.
         :param file_name_mapper: An optional function that can be used to customise the mapping of
         the resource type to the file name.
-        :returns: Details about the files that were written.
         """
         if file_name_mapper:
             wrapped_mapper = StringMapper(
                 self.spark._jvm._gateway_client, file_name_mapper
             )
-            result = self._datasinks.saveMode(save_mode).ndjson(path, wrapped_mapper)
+            self._datasinks.saveMode(save_mode).ndjson(path, wrapped_mapper)
         else:
-            result = self._datasinks.saveMode(save_mode).ndjson(path)
-        return _convert_write_details(result)
+            self._datasinks.saveMode(save_mode).ndjson(path)
 
-    def parquet(
-        self, path: str, save_mode: Optional[str] = SaveMode.ERROR
-    ) -> WriteDetails:
+    def parquet(self, path: str, save_mode: Optional[str] = SaveMode.ERROR) -> None:
         """
         Writes the data to a directory of Parquet files.
 
@@ -136,14 +89,12 @@ class DataSinks(SparkConversionsMixin):
             - "append" will append the new data to the existing data.
             - "ignore" will only save the data if the file does not already exist.
             - "error" will raise an error if the file already exists.
-        :returns: Details about the files that were written.
         """
-        result = self._datasinks.saveMode(save_mode).parquet(path)
-        return _convert_write_details(result)
+        self._datasinks.saveMode(save_mode).parquet(path)
 
     def delta(
         self, path: str, save_mode: Optional[str] = SaveMode.OVERWRITE
-    ) -> WriteDetails:
+    ) -> None:
         """
         Writes the data to a directory of Delta files.
 
@@ -151,16 +102,14 @@ class DataSinks(SparkConversionsMixin):
         :param save_mode: The save mode to use when writing the data - "overwrite" will
         overwrite any existing data, "merge" will merge the new data with the existing data based
         on resource ID.
-        :returns: Details about the files that were written.
         """
-        result = self._datasinks.saveMode(save_mode).delta(path)
-        return _convert_write_details(result)
+        self._datasinks.saveMode(save_mode).delta(path)
 
     def tables(
         self,
         schema: Optional[str] = None,
         save_mode: Optional[str] = SaveMode.OVERWRITE,
-    ) -> WriteDetails:
+    ) -> None:
         """
         Writes the data to a set of tables in the Spark catalog.
 
@@ -168,10 +117,8 @@ class DataSinks(SparkConversionsMixin):
         :param save_mode: The save mode to use when writing the data - "overwrite" will
         overwrite any existing data, "merge" will merge the new data with the existing data based
         on resource ID.
-        :returns: Details about the files that were written.
         """
         if schema:
-            result = self._datasinks.saveMode(save_mode).tables(schema)
+            self._datasinks.saveMode(save_mode).tables(schema)
         else:
-            result = self._datasinks.saveMode(save_mode).tables()
-        return _convert_write_details(result)
+            self._datasinks.saveMode(save_mode).tables()

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/datasource.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -14,15 +14,16 @@
 #  limitations under the License.
 
 from datetime import datetime
-from json import dumps, loads
-from typing import TYPE_CHECKING, Callable, Dict, List, Optional, Sequence
+from typing import Dict, Sequence, Optional, Callable
+from typing import List, TYPE_CHECKING
 
-from py4j.java_collections import SetConverter
+from json import dumps, loads
 from py4j.java_gateway import JavaObject
+from py4j.java_collections import SetConverter
 from pyspark.sql import DataFrame
 
 from pathling import PathlingContext
-from pathling.core import SparkConversionsMixin, StringToStringSetMapper
+from pathling.core import StringToStringSetMapper, SparkConversionsMixin
 from pathling.fhir import MimeType
 from pathling.spark import Dfs
 
@@ -53,7 +54,7 @@ class DataSource(SparkConversionsMixin):
     def resource_types(self):
         """
         Returns a list of the resource types that are available in the data source.
-
+        
         :return: A list of strings representing the resource types.
         """
         return list(self._jds.getResourceTypes())
@@ -65,7 +66,6 @@ class DataSource(SparkConversionsMixin):
         """
         # Import here to avoid circular dependency
         from pathling.datasink import DataSinks
-
         return DataSinks(self)
 
     def view(
@@ -240,14 +240,14 @@ class DataSources(SparkConversionsMixin):
         type_filters: Optional[List[str]] = None,
         timeout: Optional[int] = None,
         max_concurrent_downloads: int = 10,
-        auth_config: Optional[Dict] = None,
+        auth_config: Optional[Dict] = None
     ) -> DataSource:
         """
-        Creates a data source from a FHIR Bulk Data Access API endpoint.
+        Creates a data source from a FHIR Bulk Data Access API endpoint. 
         Currently only supports bulk export in the ndjson format.
-
+        
         :param fhir_endpoint_url: The URL of the FHIR server to export from
-        :param output_dir: The directory to write the output files to.
+        :param output_dir: The directory to write the output files to. 
                 This should be a valid path in the Spark's filesystem.
                 If set to `None`, a temporary directory will be used instead.
         :param overwrite: Whether to overwrite the output directory if it already exists. Defaults to True.
@@ -277,9 +277,7 @@ class DataSources(SparkConversionsMixin):
         dfs = Dfs(self._pc.spark)
 
         # If `output_dir` is not provided, create a temporary directory
-        output_dir = output_dir or dfs.get_temp_dir_path(
-            prefix="tmp-bulk-export", qualified=True
-        )
+        output_dir = output_dir or dfs.get_temp_dir_path(prefix="tmp-bulk-export", qualified=True)
         # If `overwrite`, then ensure the output directory does not exist
         if overwrite and dfs.exists(output_dir):
             dfs.delete(output_dir, recursive=True)
@@ -303,7 +301,7 @@ class DataSources(SparkConversionsMixin):
                 output_extension=output_extension,
                 timeout=timeout,
                 max_concurrent_downloads=max_concurrent_downloads,
-                auth_config=auth_config,
+                auth_config=auth_config
             )
         elif patients is not None:
             client = BulkExportClient.for_patient(
@@ -320,7 +318,7 @@ class DataSources(SparkConversionsMixin):
                 output_extension=output_extension,
                 timeout=timeout,
                 max_concurrent_downloads=max_concurrent_downloads,
-                auth_config=auth_config,
+                auth_config=auth_config
             )
         else:
             client = BulkExportClient.for_system(
@@ -336,7 +334,7 @@ class DataSources(SparkConversionsMixin):
                 output_extension=output_extension,
                 timeout=timeout,
                 max_concurrent_downloads=max_concurrent_downloads,
-                auth_config=auth_config,
+                auth_config=auth_config
             )
 
         # Perform the export

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/fhir.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/functions.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/spark.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -40,11 +40,11 @@ class Dfs:
     def get_temp_dir_path(self, prefix: str = "tmp-app", qualified=True) -> str:
         """
         Returns a unique path for a temporary directory in Spark's filesystem.
-
-        The path is constructed by appending a UUID to the base temporary directory,
+    
+        The path is constructed by appending a UUID to the base temporary directory, 
         ensuring uniqueness for each call.
         The directory itself is not created, only the path is returned.
-
+        
         :param prefix: String to insert between the base directory and the UUID (default: "tmp-app").
         :param qualified: If True, returns a fully qualified Hadoop path; if False, returns a raw path string.
         :return: String representing the unique temporary directory path.
@@ -54,14 +54,8 @@ class Dfs:
             raise ValueError("`hadoop.tmp.dir` must be set in Hadoop configuration.")
         uuid_suffix = str(uuid.uuid4())
         base_tmp_path = self._jvm.org.apache.hadoop.fs.Path(base_tmp_dir)
-        tmp_path = self._jvm.org.apache.hadoop.fs.Path(
-            base_tmp_path, f"{prefix}-{uuid_suffix}"
-        )
-        return (
-            self._fs.makeQualified(tmp_path).toString()
-            if qualified
-            else tmp_path.toString()
-        )
+        tmp_path = self._jvm.org.apache.hadoop.fs.Path(base_tmp_path, f"{prefix}-{uuid_suffix}")
+        return self._fs.makeQualified(tmp_path).toString() if qualified else tmp_path.toString()
 
     def exists(self, path: str) -> bool:
         """

{pathling-9.2.0 → pathling-9.2.0.dev0}/pathling/udfs.py

@@ -1,6 +1,6 @@
 #  Copyright © 2018-2025 Commonwealth Scientific and Industrial Research
 #  Organisation (CSIRO) ABN 41 687 119 230.
-#
+# 
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -13,12 +13,12 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-from typing import Any, Collection, Optional, Union
+from typing import Any, Optional, Union, Collection
 
 from py4j.java_gateway import JavaObject
 from pyspark import SparkContext
-from pyspark.sql.classic.column import _to_java_column
 from pyspark.sql.column import Column
+from pyspark.sql.classic.column import _to_java_column
 from pyspark.sql.functions import lit
 
 from pathling.coding import Coding
@@ -37,7 +37,7 @@ def _coding_to_java_column(coding: Optional[CodingArg]) -> JavaObject:
 
 
 def _ensure_collection(
-    collection_or_value: Optional[Union[Any, Collection[Any]]],
+    collection_or_value: Optional[Union[Any, Collection[Any]]]
 ) -> Optional[Collection[Any]]:
     return (
         collection_or_value

{pathling-9.2.0 → pathling-9.2.0.dev0}/pyproject.toml

@@ -54,7 +54,6 @@ dev = [
     "build==1.2.1",
     "pytest-cov==5.0.0",
     "http-server-mock==1.7",
-    "ruff>=0.8.0",
 ]
 
 [tool.hatch.version]
@@ -77,22 +76,3 @@ include = [
     "/README.md",
     "/LICENSE",
 ]
-
-[tool.ruff]
-target-version = "py39"
-line-length = 88
-
-[tool.ruff.lint]
-select = [
-    "E",  # pycodestyle errors
-    "W",  # pycodestyle warnings
-    "F",  # pyflakes
-    "I",  # isort (import sorting)
-]
-ignore = [
-    "E501",  # line too long - handled by formatter where possible
-]
-
-[tool.ruff.format]
-quote-style = "double"
-indent-style = "space"