Spark->3.3,Hadoop->3,Scala->2.13,Java->17

Author: Bidek56

pyspark-notebook/Dockerfile

@@ -15,10 +15,11 @@ USER root
 # Spark dependencies
 # Default values can be overridden at build time
 # (ARGS are in lower case to distinguish them from ENV)
-ARG spark_version="3.2.1"
-ARG hadoop_version="3.2"
-ARG spark_checksum="145ADACF189FECF05FBA3A69841D2804DD66546B11D14FC181AC49D89F3CB5E4FECD9B25F56F0AF767155419CD430838FB651992AEB37D3A6F91E7E009D1F9AE"
-ARG openjdk_version="11"
+ARG spark_version="3.3.0"
+ARG hadoop_version="3"
+ARG scala_version="2.13"
+ARG spark_checksum="4c09dac70e22bf1d5b7b2cabc1dd92aba13237f52a5b682c67982266fc7a0f5e0f964edff9bc76adbd8cb444eb1a00fdc59516147f99e4e2ce068420ff4881f0"
+ARG openjdk_version="17"
 
 ENV APACHE_SPARK_VERSION="${spark_version}" \
     HADOOP_VERSION="${hadoop_version}"
@@ -31,10 +32,10 @@ RUN apt-get update --yes && \
 
 # Spark installation
 WORKDIR /tmp
-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"
+RUN wget -q "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz" && \
+    echo "${spark_checksum} *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz" | sha512sum -c - && \
+    tar xzf "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz" -C /usr/local --owner root --group root --no-same-owner && \
+    rm "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}.tgz"
 
 WORKDIR /usr/local
 
@@ -43,7 +44,7 @@ ENV SPARK_HOME=/usr/local/spark
 ENV SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info" \
     PATH="${PATH}:${SPARK_HOME}/bin"
 
-RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" spark && \
+RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}-scala${scala_version}" spark && \
     # Add a link in the before_notebook hook in order to source automatically PYTHONPATH
     mkdir -p /usr/local/bin/before-notebook.d && \
     ln -s "${SPARK_HOME}/sbin/spark-config.sh" /usr/local/bin/before-notebook.d/spark-config.sh

tests/all-spark-notebook/test_spark_notebooks.py

@@ -38,8 +38,8 @@ def test_nbconvert(container: TrackedContainer, test_file: str) -> None:
         command=["start.sh", "bash", "-c", command],
     )
     warnings = TrackedContainer.get_warnings(logs)
-    # Some Spark warnings
-    assert len(warnings) == 5
+    # No Spark warnings
+    assert len(warnings) == 0
 
     expected_file = f"{output_dir}/{test_file}.md"
     assert expected_file in logs, f"Expected file {expected_file} not generated"

tests/pyspark-notebook/test_spark.py

@@ -16,7 +16,8 @@ def test_spark_shell(container: TrackedContainer) -> None:
         command=["start.sh", "bash", "-c", 'spark-shell <<< "1+1"'],
     )
     warnings = TrackedContainer.get_warnings(logs)
-    # Some Spark warnings
-    assert len(warnings) == 5
+
+    # Should not see any Spark warnings
+    assert len(warnings) == 0
 
     assert "res0: Int = 2" in logs, "spark-shell does not work"