Merge branch 'main' into main

Author: jochenchrist

CHANGELOG.md

@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Unreleased
 
+
+## [0.10.39] - 2025-11-20
+
+### Added
+- 
+- Oracle DB: Client Directory for Connection Mode 'Thick' can now be specified in the `DATACONTRACT_ORACLE_CLIENT_DIR` environment variable (#949)
+
 ### Fixed
 
 - Import composite primary keys from open data contract spec

README.md

@@ -640,11 +640,15 @@ These environment variable specify the credentials used by the datacontract tool
 If you've started the database from a container, e.g. [oracle-free](https://hub.docker.com/r/gvenzl/oracle-free)
 this should match either `system` and what you specified as `ORACLE_PASSWORD` on the container or
 alternatively what you've specified under `APP_USER` and `APP_USER_PASSWORD`.
-
-| Environment Variable                             | Example    | Description                                  |
-|--------------------------------------------------|------------|----------------------------------------------|
-| `DATACONTRACT_ORACLE_USERNAME`                   | `system`   | Username                                     |
-| `DATACONTRACT_ORACLE_PASSWORD`                   | `0x162e53` | Password                                     |
+If you require thick mode to connect to the database, you need to have an Oracle Instant Client
+installed on the system and specify the path to the installation within the environment variable
+`DATACONTRACT_ORACLE_CLIENT_DIR`.
+
+| Environment Variable                             | Example            | Description                                |
+|--------------------------------------------------|--------------------|--------------------------------------------|
+| `DATACONTRACT_ORACLE_USERNAME`                   | `system`           | Username                                   |
+| `DATACONTRACT_ORACLE_PASSWORD`                   | `0x162e53`         | Password                                   |
+| `DATACONTRACT_ORACLE_CLIENT_DIR`                 | `C:\oracle\client` | Path to Oracle Instant Client installation |
 
 
 

datacontract/engines/soda/check_soda_execute.py

@@ -3,7 +3,7 @@
 import uuid
 
 from datacontract.engines.soda.connections.athena import to_athena_soda_configuration
-from datacontract.engines.soda.connections.oracle import to_oracle_soda_configuration
+from datacontract.engines.soda.connections.oracle import initialize_client_and_create_soda_configuration
 
 if typing.TYPE_CHECKING:
     from pyspark.sql import SparkSession
@@ -106,7 +106,7 @@ def check_soda_execute(
         scan.add_configuration_yaml_str(soda_configuration_str)
         scan.set_data_source_name(server.type)
     elif server.type == "oracle":
-        soda_configuration_str = to_oracle_soda_configuration(server)
+        soda_configuration_str = initialize_client_and_create_soda_configuration(server)
         scan.add_configuration_yaml_str(soda_configuration_str)
         scan.set_data_source_name(server.type)
     elif server.type == "trino":

datacontract/engines/soda/connections/oracle.py

@@ -5,6 +5,19 @@
 from datacontract.model.data_contract_specification import Server
 
 
+def initialize_client_and_create_soda_configuration(server: Server) -> str:
+    import oracledb
+    soda_config = to_oracle_soda_configuration(server)
+
+    oracle_client_dir = os.getenv("DATACONTRACT_ORACLE_CLIENT_DIR")
+    if oracle_client_dir is not None:
+        # Soda Core currently does not support thick mode natively, see https://github.com/sodadata/soda-core/issues/2036
+        #   but the oracledb client can be configured accordingly before Soda initializes as a work-around
+        oracledb.init_oracle_client(lib_dir=oracle_client_dir)
+
+    return soda_config
+
+
 def to_oracle_soda_configuration(server: Server) -> str:
     """Serialize server config to soda configuration.
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "datacontract-cli"
-version = "0.10.38"
+version = "0.10.39"
 description = "The datacontract CLI is an open source command-line tool for working with Data Contracts. It uses data contract YAML files to lint the data contract, connect to data sources and execute schema and quality tests, detect breaking changes, and export to different formats. The tool is written in Python. It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a Python library."
 license = "MIT"
 readme = "README.md"