[GitHub] [hudi] xushiyan commented on a change in pull request #1746: [HUDI-996] Add SharedResources for functional tests

[GitBox <gi...@apache.org>]

xushiyan commented on a change in pull request #1746:
URL: https://github.com/apache/hudi/pull/1746#discussion_r442573109



##########
File path: hudi-utilities/src/test/java/org/apache/hudi/utilities/testutils/SharedResources.java
##########
@@ -0,0 +1,106 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you 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.
+ */
+
+package org.apache.hudi.utilities.testutils;
+
+import org.apache.hudi.client.HoodieWriteClient;
+import org.apache.hudi.common.testutils.minicluster.HdfsTestService;
+
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.DistributedFileSystem;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+import org.apache.spark.sql.SparkSession;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.io.TempDir;
+
+public class SharedResources implements SparkProvider, DFSProvider {
+
+  private static transient SparkSession spark;
+  private static transient SQLContext sqlContext;
+  private static transient JavaSparkContext jsc;
+
+  private static transient HdfsTestService hdfsTestService;
+  private static transient MiniDFSCluster dfsCluster;
+  private static transient DistributedFileSystem dfs;
+
+  @TempDir
+  protected static java.nio.file.Path sharedTempDir;
+
+  protected boolean initialized = false;
+
+  @Override
+  public SparkSession spark() {
+    return spark;
+  }
+
+  @Override
+  public SQLContext sqlContext() {
+    return sqlContext;
+  }
+
+  @Override
+  public JavaSparkContext jsc() {
+    return jsc;
+  }
+
+  @Override
+  public MiniDFSCluster dfsCluster() {
+    return dfsCluster;
+  }
+
+  @Override
+  public DistributedFileSystem dfs() {
+    return dfs;
+  }
+
+  @Override
+  public Path dfsBasePath() {
+    return dfs.getWorkingDirectory();
+  }
+
+  @BeforeEach
+  public synchronized void runBeforeEach() throws Exception {
+    initialized = spark != null && hdfsTestService != null;
+    if (!initialized) {
+      spark = SparkSession.builder()
+          .config(HoodieWriteClient.registerClasses(conf()))
+          .getOrCreate();
+      sqlContext = spark.sqlContext();
+      jsc = new JavaSparkContext(spark.sparkContext());

Review comment:
       @prashantwason Thanks for checking. The instantiation is guarded by checking `spark != null && hdfsTestService != null;` which are static, so only the first subclass (a test class) will initialize `spark`, `hdfsTestService`, `jsc`, etc for 1 run of the same test suite, which encompass multiple test classes. 




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org