Add docker image to the repo (#876)

I think it makes sense to have the Dockerfile
in the repository itself.

Resolves #739

Co-authored-by: Anders <[email protected]>
Co-authored-by: colin-rogers-dbt <[email protected]>

.changes/unreleased/Security-20230817-145626.yaml

@@ -0,0 +1,6 @@
+kind: Security
+body: Add docker image to the repo
+time: 2023-08-17T14:56:26.361208+02:00
+custom:
+  Author: Fokko
+  PR: "876"

docker-compose.yml

@@ -2,7 +2,7 @@ version: "3.7"
 services:
 
   dbt-spark3-thrift:
-    image: godatadriven/spark:3.1.1
+    build: docker/
     ports:
       - "10000:10000"
       - "4040:4040"
@@ -19,7 +19,7 @@ services:
       - WAIT_FOR=dbt-hive-metastore:5432
 
   dbt-hive-metastore:
-    image: postgres:9.6.17-alpine
+    image: postgres:9-alpine
     volumes:
       - ./.hive-metastore/:/var/lib/postgresql/data
     environment:

docker/Dockerfile

@@ -0,0 +1,30 @@
+ARG OPENJDK_VERSION=8
+FROM eclipse-temurin:${OPENJDK_VERSION}-jre
+
+ARG BUILD_DATE
+ARG SPARK_VERSION=3.3.2
+ARG HADOOP_VERSION=3
+
+LABEL org.label-schema.name="Apache Spark ${SPARK_VERSION}" \
+      org.label-schema.build-date=$BUILD_DATE \
+      org.label-schema.version=$SPARK_VERSION
+
+ENV SPARK_HOME /usr/spark
+ENV PATH="/usr/spark/bin:/usr/spark/sbin:${PATH}"
+
+RUN apt-get update && \
+    apt-get install -y wget netcat procps libpostgresql-jdbc-java && \
+    wget -q "http://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \
+    tar xzf "spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \
+    rm "spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \
+    mv "spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" /usr/spark && \
+    ln -s /usr/share/java/postgresql-jdbc4.jar /usr/spark/jars/postgresql-jdbc4.jar && \
+    apt-get remove -y wget && \
+    apt-get autoremove -y && \
+    apt-get clean
+
+COPY entrypoint.sh /scripts/
+RUN chmod +x /scripts/entrypoint.sh
+
+ENTRYPOINT ["/scripts/entrypoint.sh"]
+CMD ["--help"]

docker/entrypoint.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+if [ -n "$WAIT_FOR" ]; then
+  IFS=';' read -a HOSTPORT_ARRAY <<< "$WAIT_FOR"
+  for HOSTPORT in "${HOSTPORT_ARRAY[@]}"
+  do
+    WAIT_FOR_HOST=${HOSTPORT%:*}
+    WAIT_FOR_PORT=${HOSTPORT#*:}
+
+    echo Waiting for $WAIT_FOR_HOST to listen on $WAIT_FOR_PORT...
+    while ! nc -z $WAIT_FOR_HOST $WAIT_FOR_PORT; do echo sleeping; sleep 2; done
+  done
+fi
+
+exec spark-submit "$@"