Add spark3-hudi image

.github/workflows/ci.yml

@@ -20,6 +20,8 @@ jobs:
             test: spark3-iceberg
           - image: spark3-delta
             test: spark3-delta
+          - image: spark3-hudi
+            test: spark3-hudi
           - image: kerberos
             test: kerberos
           - image: gpdb-6

etc/compose/spark3-hudi/docker-compose.yml

@@ -0,0 +1,4 @@
+version: '2.0'
+services:
+  spark:
+    image: testing/spark3-hudi:latest

testing/spark3-hudi/Dockerfile

@@ -0,0 +1,53 @@
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+FROM testing/centos7-oj11:unlabelled
+
+ARG SPARK_VERSION=3.2.1
+ARG HADOOP_VERSION=3.2
+ARG HUDI_VERSION=0.11.1
+ARG SCALA_VERSION=2.12
+
+ARG SPARK_ARTIFACT="spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}"
+
+ENV SPARK_HOME=/spark
+
+RUN set -xeu; \
+    wget -nv "https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/${SPARK_ARTIFACT}.tgz"; \
+    tar -xf ${SPARK_ARTIFACT}.tgz; \
+    rm ${SPARK_ARTIFACT}.tgz; \
+    ln -sn /${SPARK_ARTIFACT} ${SPARK_HOME}
+
+WORKDIR ${SPARK_HOME}/jars
+
+# install AWS SDK so we can access S3; the version must match the hadoop-* jars which are part of SPARK distribution
+RUN wget -nv "https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/3.3.1/hadoop-aws-3.3.1.jar"
+RUN wget -nv "https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-bundle/1.12.48/aws-java-sdk-bundle-1.12.48.jar"
+
+# install Hudi
+RUN wget -nv "https://repo1.maven.org/maven2/org/apache/hudi/hudi-spark3-bundle_${SCALA_VERSION}/${HUDI_VERSION}/hudi-spark3-bundle_${SCALA_VERSION}-${HUDI_VERSION}.jar"
+
+# Create Hive user to match Hive container
+RUN adduser hive
+
+ENV PATH="${SPARK_HOME}/bin:${PATH}"
+
+EXPOSE 10213
+
+HEALTHCHECK --interval=10s --timeout=5s --start-period=10s \
+    CMD curl -f http://localhost:10213/
+CMD spark-submit \
+   --master "local[*]" \
+   --class org.apache.spark.sql.hive.thriftserver.HiveThriftServer2 \
+   --name "Thrift JDBC/ODBC Server" \
+   --conf spark.hive.server2.thrift.port=10213 \
+   spark-internal