Merge pull request #1198 from romainx/fix_spark_java11

Fix spark installation for Java 11 and Arrow

Author: romainx

all-spark-notebook/test/data/issue_1168.ipynb

@@ -0,0 +1,72 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is a test for the issue [#1168](https://github.com/jupyter/docker-stacks/issues/1168)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pyspark.sql import SparkSession\n",
+    "from pyspark.sql.functions import pandas_udf\n",
+    "\n",
+    "# Spark session & context\n",
+    "spark = SparkSession.builder.master('local').getOrCreate()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+---+---+\n",
+      "| id|age|\n",
+      "+---+---+\n",
+      "|  1| 21|\n",
+      "+---+---+\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = spark.createDataFrame([(1, 21), (2, 30)], (\"id\", \"age\"))\n",
+    "def filter_func(iterator):\n",
+    "    for pdf in iterator:\n",
+    "        yield pdf[pdf.id == 1]\n",
+    "\n",
+    "df.mapInPandas(filter_func, df.schema).show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

all-spark-notebook/test/test_spark_notebooks.py

@@ -12,7 +12,7 @@
 @pytest.mark.parametrize(
     "test_file",
     # TODO: add local_sparklyr
-    ["local_pyspark", "local_spylon", "local_sparkR"],
+    ["local_pyspark", "local_spylon", "local_sparkR", "issue_1168"],
 )
 def test_nbconvert(container, test_file):
     """Check if Spark notebooks can be executed"""

pyspark-notebook/Dockerfile

@@ -49,6 +49,12 @@ RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" spark && \
     mkdir -p /usr/local/bin/before-notebook.d && \
     ln -s "${SPARK_HOME}/sbin/spark-config.sh" /usr/local/bin/before-notebook.d/spark-config.sh
 
+# Fix Spark installation for Java 11 and Apache Arrow library
+# see: https://github.com/apache/spark/pull/27356, https://spark.apache.org/docs/latest/#downloading
+RUN cp -p "$SPARK_HOME/conf/spark-defaults.conf.template" "$SPARK_HOME/conf/spark-defaults.conf" && \
+    echo 'spark.driver.extraJavaOptions="-Dio.netty.tryReflectionSetAccessible=true"' >> $SPARK_HOME/conf/spark-defaults.conf && \
+    echo 'spark.executor.extraJavaOptions="-Dio.netty.tryReflectionSetAccessible=true"' >> $SPARK_HOME/conf/spark-defaults.conf
+
 USER $NB_UID
 
 # Install pyarrow