Spark and Hadoop versions updated, openjdk:11-jre-slim as base image,

faster downloads

Author: haron

docker/Dockerfile

@@ -1,24 +1,26 @@
-# base image
-FROM openjdk:11
+FROM openjdk:11-jre-slim
 
 # define spark and hadoop versions
-ENV SPARK_VERSION=3.2.0
-ENV HADOOP_VERSION=3.3.1
+ENV SPARK_VERSION=3.3.2
+ENV HADOOP_VERSION=3.3.4
+
+RUN apt-get -qq update \
+    && apt-get -y install curl procps python3
 
 # download and install hadoop
 RUN mkdir -p /opt && \
     cd /opt && \
-    curl http://archive.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz | \
+    curl -f https://dlcdn.apache.org/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz | \
         tar -zx hadoop-${HADOOP_VERSION}/lib/native && \
     ln -s hadoop-${HADOOP_VERSION} hadoop && \
     echo Hadoop ${HADOOP_VERSION} native libraries installed in /opt/hadoop/lib/native
 
 # download and install spark
 RUN mkdir -p /opt && \
     cd /opt && \
-    curl http://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop2.7.tgz | \
+    curl -f https://dlcdn.apache.org/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop3.tgz | \
         tar -zx && \
-    ln -s spark-${SPARK_VERSION}-bin-hadoop2.7 spark && \
+    ln -s spark-${SPARK_VERSION}-bin-hadoop3 spark && \
     echo Spark ${SPARK_VERSION} installed in /opt
 
 # add scripts and update spark default config