Upgraded to use Spark 3.5.3 (#314)

Author: msmygit

Dockerfile

@@ -9,9 +9,9 @@ RUN mkdir -p /assets/ && cd /assets && \
     curl -OL https://downloads.datastax.com/enterprise/cqlsh-astra.tar.gz && \
     tar -xzf ./cqlsh-astra.tar.gz && \
     rm ./cqlsh-astra.tar.gz && \
-    curl -OL https://archive.apache.org/dist/spark/spark-3.5.2/spark-3.5.2-bin-hadoop3-scala2.13.tgz && \
-    tar -xzf ./spark-3.5.2-bin-hadoop3-scala2.13.tgz && \
-    rm ./spark-3.5.2-bin-hadoop3-scala2.13.tgz
+    curl -OL https://archive.apache.org/dist/spark/spark-3.5.3/spark-3.5.3-bin-hadoop3-scala2.13.tgz && \
+    tar -xzf ./spark-3.5.3-bin-hadoop3-scala2.13.tgz && \
+    rm ./spark-3.5.3-bin-hadoop3-scala2.13.tgz
 
 RUN apt-get update && apt-get install -y openssh-server vim python3 --no-install-recommends && \
     rm -rf /var/lib/apt/lists/* && \
@@ -44,7 +44,7 @@ RUN chmod +x ./get-latest-maven-version.sh && \
     rm -rf "$USER_HOME_DIR/.m2"
 
 # Add all migration tools to path
-ENV PATH="${PATH}:/assets/dsbulk/bin/:/assets/cqlsh-astra/bin/:/assets/spark-3.5.2-bin-hadoop3-scala2.13/bin/"
+ENV PATH="${PATH}:/assets/dsbulk/bin/:/assets/cqlsh-astra/bin/:/assets/spark-3.5.3-bin-hadoop3-scala2.13/bin/"
 
 EXPOSE 22
 

README.md

@@ -7,7 +7,7 @@
 
 Migrate and Validate Tables between Origin and Target Cassandra Clusters.
 
-> :warning: Please note this job has been tested with spark version [3.5.2](https://archive.apache.org/dist/spark/spark-3.5.2/)
+> :warning: Please note this job has been tested with spark version [3.5.3](https://archive.apache.org/dist/spark/spark-3.5.3/)
 
 ## Install as a Container
 - Get the latest image that includes all dependencies from [DockerHub](https://hub.docker.com/r/datastax/cassandra-data-migrator)
@@ -18,10 +18,10 @@ Migrate and Validate Tables between Origin and Target Cassandra Clusters.
 
 ### Prerequisite
 - Install **Java11** (minimum) as Spark binaries are compiled with it.
-- Install Spark version [`3.5.2`](https://archive.apache.org/dist/spark/spark-3.5.2/spark-3.5.2-bin-hadoop3-scala2.13.tgz) on a single VM (no cluster necessary) where you want to run this job. Spark can be installed by running the following: -
+- Install Spark version [`3.5.3`](https://archive.apache.org/dist/spark/spark-3.5.3/spark-3.5.3-bin-hadoop3-scala2.13.tgz) on a single VM (no cluster necessary) where you want to run this job. Spark can be installed by running the following: -
 ```
-wget https://archive.apache.org/dist/spark/spark-3.5.2/spark-3.5.2-bin-hadoop3-scala2.13.tgz
-tar -xvzf spark-3.5.2-bin-hadoop3-scala2.13.tgz
+wget https://archive.apache.org/dist/spark/spark-3.5.3/spark-3.5.3-bin-hadoop3-scala2.13.tgz
+tar -xvzf spark-3.5.3-bin-hadoop3-scala2.13.tgz
 ```
 
 > :warning: If the above Spark and Scala version is not properly installed, you'll then see a similar exception like below when running the CDM jobs,

RELEASE.md

@@ -1,4 +1,7 @@
 # Release Notes
+## [4.4.2] - 2024-10-TBD
+- Upgraded to use Spark `3.5.3`.
+
 ## [4.4.1] - 2024-09-20
 - Added two new codecs `STRING_BLOB` and `ASCII_BLOB` to allow migration from `TEXT` and `ASCII` fields to `BLOB` fields. These codecs can also be used to convert `BLOB` to `TEXT` or `ASCII`, but in such cases the `BLOB` value must be TEXT based in nature & fit within the applicable limits.
 

pom.xml

@@ -10,7 +10,7 @@
 		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
 		<scala.version>2.13.14</scala.version>
 		<scala.main.version>2.13</scala.main.version>
-		<spark.version>3.5.2</spark.version>
+		<spark.version>3.5.3</spark.version>
 		<connector.version>3.5.1</connector.version>
 		<cassandra.version>5.0-rc1</cassandra.version>
 		<junit.version>5.9.1</junit.version>