Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions aws_spark/Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -5,11 +5,17 @@ FROM ${BASE_IMAGE}
ARG HADOOP_AWS_VERSION=3.2.1
ARG AWS_JAVA_SDK_VERSION=1.11.874
ARG TFRECORD_VERSION=0.3.0
ARG GCS_CONNECTOR_VERSION=2.0.1
ARG BQ_CONNECTOR_VERSION=0.18.1

USER root
# Add HADOOP_AWS_JAR and AWS_JAVA_SDK
ADD https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/${HADOOP_AWS_VERSION}/hadoop-aws-${HADOOP_AWS_VERSION}.jar /opt/spark/jars
ADD https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-bundle/${AWS_JAVA_SDK_VERSION}/aws-java-sdk-bundle-${AWS_JAVA_SDK_VERSION}.jar /opt/spark/jars
ADD https://repo1.maven.org/maven2/com/linkedin/sparktfrecord/spark-tfrecord_2.12/${TFRECORD_VERSION}/spark-tfrecord_2.12-${TFRECORD_VERSION}.jar /opt/spark/jars
ADD https://storage.googleapis.com/hadoop-lib/gcs/gcs-connector-hadoop2-${GCS_CONNECTOR_VERSION}.jar /opt/spark/jars
ADD https://repo1.maven.org/maven2/com/google/cloud/spark/spark-bigquery-with-dependencies_2.12/${BQ_CONNECTOR_VERSION}/spark-bigquery-with-dependencies_2.12-${BQ_CONNECTOR_VERSION}.jar /opt/spark/jars



ENTRYPOINT [ "/opt/entrypoint.sh" ]