diff --git a/docs/using/specifics.md b/docs/using/specifics.md index af6e4219..7536f692 100644 --- a/docs/using/specifics.md +++ b/docs/using/specifics.md @@ -12,7 +12,7 @@ This page provides details about features specific to one or more images. You can build a `pyspark-notebook` image (and also the downstream `all-spark-notebook` image) with a different version of Spark by overriding the default value of the following arguments at build time. -* Spark distribution is defined by the combination of the Spark and the Hadoop version and verified by the package checksum, see [Download Apache Spark](https://spark.apache.org/downloads.html) for more information. At this time the build will only work with the set of versions available on the Apache Spark download page, so it will not work with the archived versions. +* Spark distribution is defined by the combination of the Spark and the Hadoop version and verified by the package checksum, see [Download Apache Spark](https://spark.apache.org/downloads.html) and the [archive repo](https://archive.apache.org/dist/spark/) for more information. * `spark_version`: The Spark version to install (`3.0.0`). * `hadoop_version`: The Hadoop version (`3.2`). * `spark_checksum`: The package checksum (`BFE4540...`). diff --git a/pyspark-notebook/Dockerfile b/pyspark-notebook/Dockerfile index bf2f601b..9f09e161 100644 --- a/pyspark-notebook/Dockerfile +++ b/pyspark-notebook/Dockerfile @@ -29,10 +29,7 @@ RUN apt-get -y update && \ # Spark installation WORKDIR /tmp -# Using the preferred mirror to download Spark -# 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'])") && \ +RUN wget -q "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \ echo "${spark_checksum} *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"