hazza/docker-stacks
1
0
Fork 0
mirror of https://github.com/jupyter/docker-stacks.git synced 2025-10-16 14:32:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix hadolint deviations

Browse Source
This commit is contained in:
Romain
2020-05-29 19:33:24 +02:00
parent 64c143d3cd
commit 7b48e43b74
8 changed files with 76 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
pyspark-notebook/Dockerfile
View File

@@ -1,28 +1,36 @@
# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.
ARG BASE_CONTAINER=jupyter/scipy-notebook
# hadolint ignore=DL3006
FROM $BASE_CONTAINER
LABEL maintainer="Jupyter Project <jupyter@googlegroups.com>"
# Fix DL4006
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
USER root
# Spark dependencies
ENV APACHE_SPARK_VERSION=2.4.5 \
HADOOP_VERSION=2.7
# hadolint ignore=DL3008
RUN apt-get -y update && \
apt-get install --no-install-recommends -y openjdk-8-jre-headless ca-certificates-java && \
rm -rf /var/lib/apt/lists/*
# Using the preferred mirror to download Spark
RUN cd /tmp && \
wget -q $(wget -qO- https://www.apache.org/dyn/closer.lua/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz\?as_json | \
WORKDIR /tmp
# TODO
# hadolint ignore=SC2046
RUN wget -q $(wget -qO- "https://www.apache.org/dyn/closer.lua/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz\?as_json" | \
python -c "import sys, json; content=json.load(sys.stdin); print(content['preferred']+content['path_info'])") && \
echo "2426a20c548bdfc07df288cd1d18d1da6b3189d0b78dee76fa034c52a4e02895f0ad460720c526f163ba63a17efae4764c46a1cd8f9b04c60f9937a554db85d2 *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \
tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz -C /usr/local --owner root --group root --no-same-owner && \
rm spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz
RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION} spark
tar xzf "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" -C /usr/local --owner root --group root --no-same-owner && \
rm "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"
WORKDIR /usr/local
RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" spark
# Configure Spark
ENV SPARK_HOME=/usr/local/spark
@@ -35,5 +43,7 @@ USER $NB_UID
# Install pyarrow
RUN conda install --quiet -y 'pyarrow' && \
conda clean --all -f -y && \
fix-permissions $CONDA_DIR && \
fix-permissions /home/$NB_USER
fix-permissions "${CONDA_DIR}" && \
fix-permissions "/home/${NB_USER}"
WORKDIR $HOME