hazza/docker-stacks
1
0
Fork 0
mirror of https://github.com/jupyter/docker-stacks.git synced 2025-10-12 04:22:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use curl instead of wget for Spark and Julia downloads (#1950)

Browse Source 
Co-authored-by: Bjørn Jørgensen <bjornjorgensen@users.noreply.github.com>
This commit is contained in:
Ayaz Salikhov
2023-08-03 13:18:01 +04:00
committed by GitHub
parent 1d9e4f99a5
commit e1bd309263
4 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
pyspark-notebook/Dockerfile
View File

@@ -36,9 +36,11 @@ 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 "${scala_version}" ]; then \
wget --progress=dot:giga -O "spark.tgz" "https://dlcdn.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"; \
curl --progress-bar --location --output "spark.tgz" \
"https://dlcdn.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"; \
else \
wget --progress=dot:giga -O "spark.tgz" "https://dlcdn.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz"; \
curl --progress-bar --location --output "spark.tgz" \
"https://dlcdn.apache.org/spark/spark-${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 && \