Bumped version of Apache Spark to 3.5.5 to prevent 404 error

+ Fixed version of repo in dist files

Author: Genarito

Dockerfile

@@ -44,7 +44,7 @@ ENV PATH=$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH
 RUN mkdir -p ${HADOOP_VERSION}/logs
 
 # Install Spark
-ENV SPARK_VERSION=3.5.4
+ENV SPARK_VERSION=3.5.5
 RUN wget https://dlcdn.apache.org/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop3.tgz \
     && tar -xzf spark-${SPARK_VERSION}-bin-hadoop3.tgz -C /opt/ \
     && rm spark-${SPARK_VERSION}-bin-hadoop3.tgz

README.md

@@ -31,7 +31,7 @@ This repository is inspired by and uses several scripts taken from [Rubenafo's r
 
 - ✅ Ready to deploy in a Docker Swarm cluster: all the networking and port configuration issues have been fixed so you can scale your cluster to as many worker nodes as you need.
 - ⚡️ Hadoop, HDFS, Spark, Scala and PySpark ready to use: all the tools are available inside the container globally so you don't have to fight with environment variables and executable paths.
-- 🌟 New technology: our image offers Hadoop 3.4.0, Spark 3.5.4 and Python 3.12.6
+- 🌟 New technology: our image offers Hadoop 3.4.0, Spark 3.5.5 and Python 3.12.6
 - ⚙️ Less configuration: we have removed some settings to keep the minimum possible configuration, this way you prevent errors, unexpected behaviors and get the freedom to set parameters via environment variables and have an agile development that does not require rebuilding the Docker image. 
 - 🐍 Python dependencies: we include the most used Python dependencies like Pandas, Numpy and Scipy to be able to work on datasets and perform mathematical operations (you can remove them if you don't need them!)
 

docker-compose.yml

@@ -1,7 +1,7 @@
 services:
   # Master
   master-node:
-    image: "jwaresolutions/big-data-cluster:0.5.0"
+    image: "jwaresolutions/big-data-cluster:1.0.1"
     container_name: "master-node"
     restart: "always"
     command: bash -c "/home/big_data/spark-cmd.sh start master-node"
@@ -18,7 +18,7 @@ services:
 
   # Workers
   worker:
-    image: "jwaresolutions/big-data-cluster:0.5.0"
+    image: "jwaresolutions/big-data-cluster:1.0.1"
     restart: "always"
     command: bash -c "/home/big_data/spark-cmd.sh start"
     deploy:

docker-compose_cluster.yml

@@ -1,7 +1,7 @@
 services:
   # Master
   master-node:
-    image: "jwaresolutions/big-data-cluster:0.5.0"
+    image: "jwaresolutions/big-data-cluster:1.0.1"
     command: bash -c "/home/big_data/spark-cmd.sh start master-node"
     ports:
       - target: 8080
@@ -32,7 +32,7 @@ services:
 
   # Workers
   worker:
-    image: "jwaresolutions/big-data-cluster:0.5.0"
+    image: "jwaresolutions/big-data-cluster:1.0.1"
     command: bash -c "/home/big_data/spark-cmd.sh start"
     depends_on:
       - "master-node"

toy-cluster.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-imageName="jwaresolutions/big-data-cluster:0.5.0"
+imageName="jwaresolutions/big-data-cluster:1.0.1"
 
 # Bring the services up
 function startServices {

version.txt

@@ -1 +1 @@
-1.0.0
+1.0.1