Test Spark 3.5.2

.github/workflows/data/clickhouse/matrix.yml

@@ -11,7 +11,7 @@ min: &min
 max: &max
   clickhouse-image: clickhouse/clickhouse-server
   clickhouse-version: 24.6.3.70-alpine
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/core/matrix.yml

@@ -6,7 +6,7 @@ min: &min
   os: ubuntu-latest
 
 max: &max
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/hdfs/matrix.yml

@@ -8,7 +8,7 @@ min: &min
 
 max: &max
   hadoop-version: hadoop3-hdfs
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/hive/matrix.yml

@@ -6,7 +6,7 @@ min: &min
   os: ubuntu-latest
 
 max: &max
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/kafka/matrix.yml

@@ -12,7 +12,7 @@ min: &min
 max: &max
   kafka-version: 3.7.1
   pydantic-version: 2
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   python-version: '3.12'
   java-version: 20
   os: ubuntu-latest

.github/workflows/data/local-fs/matrix.yml

@@ -20,8 +20,8 @@ min_excel: &min_excel
   os: ubuntu-latest
 
 max: &max
-  # Excel package currently has no release for 3.5.1
-  spark-version: 3.5.0
+  # Excel package currently has no release for 3.5.2
+  spark-version: 3.5.1
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/mongodb/matrix.yml

@@ -9,7 +9,7 @@ min: &min
 
 max: &max
   mongodb-version: 7.0.12
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/mssql/matrix.yml

@@ -8,7 +8,7 @@ min: &min
 
 max: &max
   mssql-version: 2022-CU14-ubuntu-22.04
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/mysql/matrix.yml

@@ -10,7 +10,7 @@ min: &min
 
 max: &max
   mysql-version: 9.0.1
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/oracle/matrix.yml

@@ -12,7 +12,7 @@ max: &max
   oracle-image: gvenzl/oracle-free
   oracle-version: 23.4-slim-faststart
   db-name: FREEPDB1
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/postgres/matrix.yml

@@ -9,7 +9,7 @@ min: &min
 
 max: &max
   postgres-version: 16.3-alpine
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/s3/matrix.yml

@@ -10,7 +10,7 @@ min: &min
 
 max: &max
   minio-version: 2024.7.26
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

.github/workflows/data/teradata/matrix.yml

@@ -1,5 +1,5 @@
 max: &max
-  spark-version: 3.5.1
+  spark-version: 3.5.2
   pydantic-version: 2
   python-version: '3.12'
   java-version: 20

CONTRIBUTING.rst

@@ -71,7 +71,7 @@ Create virtualenv and install dependencies:
         -r requirements/tests/postgres.txt \
         -r requirements/tests/oracle.txt \
         -r requirements/tests/pydantic-2.txt \
-        -r requirements/tests/spark-3.5.1.txt
+        -r requirements/tests/spark-3.5.2.txt
 
     # TODO: remove after https://github.com/zqmillet/sphinx-plantuml/pull/4
     pip install sphinx-plantuml --no-deps

README.rst

@@ -184,7 +184,7 @@ Compatibility matrix
 +--------------------------------------------------------------+-------------+-------------+-------+
 | `3.4.x <https://spark.apache.org/docs/3.4.3/#downloading>`_  | 3.7 - 3.12  | 8u362 - 20  | 2.12  |
 +--------------------------------------------------------------+-------------+-------------+-------+
-| `3.5.x <https://spark.apache.org/docs/3.5.1/#downloading>`_  | 3.8 - 3.12  | 8u371 - 20  | 2.12  |
+| `3.5.x <https://spark.apache.org/docs/3.5.2/#downloading>`_  | 3.8 - 3.12  | 8u371 - 20  | 2.12  |
 +--------------------------------------------------------------+-------------+-------------+-------+
 
 .. _pyspark-install:
@@ -199,7 +199,7 @@ or install PySpark explicitly:
 
 .. code:: bash
 
-    pip install onetl pyspark==3.5.1  # install a specific PySpark version
+    pip install onetl pyspark==3.5.2  # install a specific PySpark version
 
 or inject PySpark to ``sys.path`` in some other way BEFORE creating a class instance.
 **Otherwise connection object cannot be created.**
@@ -540,7 +540,7 @@ Read files directly from S3 path, convert them to dataframe, transform it and th
     setup_logging()
 
     # Initialize new SparkSession with Hadoop AWS libraries and Postgres driver loaded
-    maven_packages = SparkS3.get_packages(spark_version="3.5.1") + Postgres.get_packages()
+    maven_packages = SparkS3.get_packages(spark_version="3.5.2") + Postgres.get_packages()
     spark = (
         SparkSession.builder.appName("spark_app_onetl_demo")
         .config("spark.jars.packages", ",".join(maven_packages))

docker-compose.yml

@@ -9,7 +9,7 @@ services:
       context: .
       target: base
       args:
-        SPARK_VERSION: 3.5.1
+        SPARK_VERSION: 3.5.2
     env_file: .env.docker
     volumes:
       - ./:/app/

docker/Dockerfile

@@ -44,7 +44,7 @@ ENV PATH=${ONETL_USER_HOME}/.local/bin:${PATH}
 COPY --chown=onetl:onetl ./run_tests.sh ./pytest_runner.sh ./combine_coverage.sh /app/
 RUN chmod +x /app/run_tests.sh /app/pytest_runner.sh /app/combine_coverage.sh
 
-ARG SPARK_VERSION=3.5.1
+ARG SPARK_VERSION=3.5.2
 # Spark is heavy, and version change is quite rare
 COPY --chown=onetl:onetl ./requirements/tests/spark-${SPARK_VERSION}.txt /app/requirements/tests/
 RUN pip install -r /app/requirements/tests/spark-${SPARK_VERSION}.txt

docs/changelog/next_release/306.feature.rst

@@ -0,0 +1 @@
+Update ``Excel`` package from ``0.20.3`` to ``0.20.4``, to include Spark 3.5.1 support.

docs/connection/db_connection/clickhouse/types.rst

@@ -106,8 +106,8 @@ References
 Here you can find source code with type conversions:
 
 * `Clickhouse -> JDBC <https://github.com/ClickHouse/clickhouse-java/blob/0.3.2/clickhouse-jdbc/src/main/java/com/clickhouse/jdbc/JdbcTypeMapping.java#L39-L176>`_
-* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala#L307>`_
-* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala#L141-L164>`_
+* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala#L307>`_
+* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala#L141-L164>`_
 * `JDBC -> Clickhouse <https://github.com/ClickHouse/clickhouse-java/blob/0.3.2/clickhouse-jdbc/src/main/java/com/clickhouse/jdbc/JdbcTypeMapping.java#L185-L311>`_
 
 Supported types

docs/connection/db_connection/mssql/types.rst

@@ -101,8 +101,8 @@ References
 Here you can find source code with type conversions:
 
 * `MSSQL -> JDBC <https://github.com/microsoft/mssql-jdbc/blob/v12.2.0/src/main/java/com/microsoft/sqlserver/jdbc/SQLServerResultSetMetaData.java#L117-L170>`_
-* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala#L102-L119>`_
-* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala#L121-L130>`_
+* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala#L117-L134>`_
+* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MsSqlServerDialect.scala#L136-L145>`_
 * `JDBC -> MSSQL <https://github.com/microsoft/mssql-jdbc/blob/v12.2.0/src/main/java/com/microsoft/sqlserver/jdbc/DataTypes.java#L625-L676>`_
 
 Supported types

docs/connection/db_connection/mysql/types.rst

@@ -97,8 +97,8 @@ References
 Here you can find source code with type conversions:
 
 * `MySQL -> JDBC <https://github.com/mysql/mysql-connector-j/blob/8.0.33/src/main/core-api/java/com/mysql/cj/MysqlType.java#L44-L623>`_
-* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala#L89-L106>`_
-* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala#L182-L188>`_
+* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala#L104-L132>`_
+* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala#L204-L211>`_
 * `JDBC -> MySQL <https://github.com/mysql/mysql-connector-j/blob/8.0.33/src/main/core-api/java/com/mysql/cj/MysqlType.java#L625-L867>`_
 
 Supported types

docs/connection/db_connection/oracle/types.rst

@@ -101,8 +101,8 @@ See `List of Oracle types <https://docs.oracle.com/en/database/oracle/oracle-dat
 
 Here you can find source code with type conversions:
 
-* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala#L83-L109>`_
-* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala#L111-L123>`_
+* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala#L83-L109>`_
+* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala#L111-L123>`_
 
 Numeric types
 ~~~~~~~~~~~~~

docs/connection/db_connection/postgres/types.rst

@@ -109,8 +109,8 @@ See `List of Postgres types <https://www.postgresql.org/docs/current/datatype.ht
 Here you can find source code with type conversions:
 
 * `Postgres <-> JDBC <https://github.com/pgjdbc/pgjdbc/blob/REL42.6.0/pgjdbc/src/main/java/org/postgresql/jdbc/TypeInfoCache.java#L78-L112>`_
-* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.0/sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala#L50-L106>`_
-* `Spark -> JDBC <https://github.com/apache/spark/blob/ce5ddad990373636e94071e7cef2f31021add07b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala#L116-L130>`_
+* `JDBC -> Spark <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala#L50-L106>`_
+* `Spark -> JDBC <https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/jdbc/PostgresDialect.scala#L116-L130>`_
 
 Numeric types
 ~~~~~~~~~~~~~

onetl/_metrics/extract.py

@@ -70,7 +70,7 @@ def extract_metrics_from_execution(execution: SparkListenerExecution) -> SparkCo
             disk_spilled_bytes += stage.metrics.disk_spilled_bytes
             result_size_bytes += stage.metrics.result_size_bytes
 
-    # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L467-L473
+    # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L467-L473
     input_file_count = (
         _get_int(execution.metrics, SparkSQLMetricNames.NUMBER_OF_FILES_READ)
         or _get_int(execution.metrics, SparkSQLMetricNames.STATIC_NUMBER_OF_FILES_READ)

onetl/_metrics/listener/base.py

@@ -16,7 +16,7 @@
 class BaseSparkListener:
     """Base no-op SparkListener implementation.
 
-    See `SparkListener <https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/SparkListener.html>`_ interface.
+    See `SparkListener <https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/SparkListener.html>`_ interface.
     """
 
     spark: SparkSession

onetl/_metrics/listener/execution.py

@@ -22,18 +22,18 @@ class SparkSQLMetricNames(str, Enum):  # noqa: WPS338
     # Metric names passed to SQLMetrics.createMetric(...)
     # But only those we're interested in.
 
-    # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L233C55-L233C87
+    # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L231
     NUMBER_OF_PARTITIONS_READ = "number of partitions read"
 
-    # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L225-L227
+    # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L225-L227
     NUMBER_OF_FILES_READ = "number of files read"
     SIZE_OF_FILES_READ = "size of files read"
 
-    # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L455-L456
+    # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/DataSourceScanExec.scala#L225-L227
     STATIC_NUMBER_OF_FILES_READ = "static number of files read"
     STATIC_SIZE_OF_FILES_READ = "static size of files read"
 
-    # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/BasicWriteStatsTracker.scala#L241-L246
+    # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/BasicWriteStatsTracker.scala#L241-L246
     NUMBER_OF_DYNAMIC_PART = "number of dynamic part"
     NUMBER_OF_WRITTEN_FILES = "number of written files"
 
@@ -62,11 +62,11 @@ def jobs(self) -> list[SparkListenerJob]:
         return result
 
     def on_execution_start(self, event):
-        # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLListener.scala#L44-L58
+        # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLListener.scala#L44-L58
         self.status = SparkListenerExecutionStatus.STARTED
 
     def on_execution_end(self, event):
-        # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLListener.scala#L61-L83
+        # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLListener.scala#L61-L83
         for job in self._jobs.values():
             if job.status == SparkListenerJobStatus.FAILED:
                 self.status = SparkListenerExecutionStatus.FAILED

onetl/_metrics/listener/job.py

@@ -38,8 +38,8 @@ def stages(self) -> list[SparkListenerStage]:
 
     @classmethod
     def create(cls, event):
-        # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/SparkListenerJobSubmitted.html
-        # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/SparkListenerJobCompleted.html
+        # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/SparkListenerJobSubmitted.html
+        # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/SparkListenerJobCompleted.html
         result = cls(
             id=event.jobId(),
             description=event.properties().get("spark.job.description"),

onetl/_metrics/listener/listener.py

@@ -73,7 +73,7 @@ def onExecutionEnd(self, event):
 
             # Get execution metrics from SQLAppStatusStore,
             # as SparkListenerSQLExecutionEnd event does not provide them:
-            # https://github.com/apache/spark/blob/v3.5.1/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusStore.scala
+            # https://github.com/apache/spark/blob/v3.5.2/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusStore.scala
             session_status_store = self.spark._jsparkSession.sharedState().statusStore()  # noqa: WPS437
             raw_execution = session_status_store.execution(execution.id).get()
             metrics = raw_execution.metrics()

onetl/_metrics/listener/stage.py

@@ -21,7 +21,7 @@ def __str__(self):
 
 @dataclass
 class SparkListenerStage:
-    # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/StageInfo.html
+    # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/StageInfo.html
     id: int
     status: SparkListenerStageStatus = SparkListenerStageStatus.PENDING
     metrics: SparkListenerTaskMetrics = field(default_factory=SparkListenerTaskMetrics, repr=False, init=False)
@@ -39,11 +39,11 @@ def create(cls, stage_info):
         return cls(id=stage_info.stageId())
 
     def on_stage_start(self, event):
-        # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/SparkListenerStageSubmitted.html
+        # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/SparkListenerStageSubmitted.html
         self.status = SparkListenerStageStatus.ACTIVE
 
     def on_stage_end(self, event):
-        # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/SparkListenerStageCompleted.html
+        # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/SparkListenerStageCompleted.html
         stage_info = event.stageInfo()
         if stage_info.failureReason().isDefined():
             self.status = SparkListenerStageStatus.FAILED

onetl/_metrics/listener/task.py

@@ -81,14 +81,14 @@ class SparkListenerTask:
 
     @classmethod
     def create(cls, task_info):
-        # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/TaskInfo.html
+        # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/TaskInfo.html
         return cls(id=task_info.taskId())
 
     def on_task_start(self, event):
-        # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/SparkListenerTaskStart.html
+        # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/SparkListenerTaskStart.html
         self.status = SparkListenerTaskStatus(event.taskInfo().status())
 
     def on_task_end(self, event):
-        # https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/scheduler/SparkListenerTaskEnd.html
+        # https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/scheduler/SparkListenerTaskEnd.html
         self.status = SparkListenerTaskStatus(event.taskInfo().status())
         self.metrics = SparkListenerTaskMetrics.create(event.taskMetrics())

onetl/_util/spark.py

@@ -143,7 +143,7 @@ def estimate_dataframe_size(spark_session: SparkSession, df: DataFrame) -> int:
     """
     Estimate in-memory DataFrame size in bytes. If cannot be estimated, return 0.
 
-    Using Spark's `SizeEstimator <https://spark.apache.org/docs/3.5.1/api/java/org/apache/spark/util/SizeEstimator.html>`_.
+    Using Spark's `SizeEstimator <https://spark.apache.org/docs/3.5.2/api/java/org/apache/spark/util/SizeEstimator.html>`_.
     """
     try:
         size_estimator = spark_session._jvm.org.apache.spark.util.SizeEstimator  # type: ignore[union-attr]

onetl/connection/db_connection/kafka/connection.py

@@ -332,7 +332,7 @@ def write_df_to_target(
         write_options.update(options.dict(by_alias=True, exclude_none=True, exclude={"if_exists"}))
         write_options["topic"] = target
 
-        # As of Apache Spark version 3.5.0, the mode 'error' is not functioning as expected.
+        # As of Apache Spark version 3.5.2, the mode 'error' is not functioning as expected.
         # This issue has been reported and can be tracked at:
         # https://issues.apache.org/jira/browse/SPARK-44774
         mode = options.if_exists
@@ -418,7 +418,7 @@ def get_packages(
             from onetl.connection import Kafka
 
             Kafka.get_packages(spark_version="3.2.4")
-            Kafka.get_packages(spark_version="3.2.4", scala_version="2.13")
+            Kafka.get_packages(spark_version="3.2.4", scala_version="2.12")
 
         """
 

onetl/connection/file_df_connection/spark_s3/connection.py

@@ -133,7 +133,7 @@ class SparkS3(SparkFileDFConnection):
         from pyspark.sql import SparkSession
 
         # Create Spark session with Hadoop AWS libraries loaded
-        maven_packages = SparkS3.get_packages(spark_version="3.5.0")
+        maven_packages = SparkS3.get_packages(spark_version="3.5.2")
         # Some dependencies are not used, but downloading takes a lot of time. Skipping them.
         excluded_packages = [
             "com.google.cloud.bigdataoss:gcs-connector",
@@ -236,8 +236,8 @@ def get_packages(
 
             from onetl.connection import SparkS3
 
-            SparkS3.get_packages(spark_version="3.5.0")
-            SparkS3.get_packages(spark_version="3.5.0", scala_version="2.12")
+            SparkS3.get_packages(spark_version="3.5.2")
+            SparkS3.get_packages(spark_version="3.5.2", scala_version="2.12")
 
         """