Merge pull request #1009 from romainx/spark_mirror

Use the preferred spark download mirror

Author: parente

pyspark-notebook/Dockerfile

@@ -15,8 +15,10 @@ 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 the file
 RUN cd /tmp && \
-    wget -q http://mirrors.ukfast.co.uk/sites/ftp.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
+    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