hazza/docker-stacks
1
0
Fork 0
mirror of https://github.com/jupyter/docker-stacks.git synced 2025-10-17 15:02:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Change spark download url to https://dlcdn.apache.org (#1876)

Browse Source
This commit is contained in:
Ayaz Salikhov
2023-02-16 11:36:15 +04:00
committed by GitHub
parent ee64c2ac00
commit 55e224e35d
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
pyspark-notebook/Dockerfile
View File

@@ -33,10 +33,12 @@ RUN apt-get update --yes && \
# Spark installation
WORKDIR /tmp
# You need to use https://archive.apache.org/dist/ website if you want to download old Spark versions
# But it seems to be slower, that's why we use recommended site for download
RUN if [ -z "${scala_version}" ]; then \
wget -qO "spark.tgz" "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"; \
wget -qO "spark.tgz" "https://dlcdn.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"; \
else \
wget -qO "spark.tgz" "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz"; \
wget -qO "spark.tgz" "https://dlcdn.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz"; \
fi && \
echo "${spark_checksum} *spark.tgz" | sha512sum -c - && \
tar xzf "spark.tgz" -C /usr/local --owner root --group root --no-same-owner && \