Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/22708#discussion_r225749174
--- Diff:
sql/core/src/test/java/test/org/apache/spark/sql/JavaBeanWithArraySuite.java ---
@@ -0,0 +1,222 @@
+/*
+ * 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 test.org.apache.spark.sql;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collection;
+import java.util.Iterator;
+import java.util.List;
+
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoder;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.test.TestSparkSession;
+import org.apache.spark.sql.types.ArrayType;
+import org.apache.spark.sql.types.DataType;
+import org.apache.spark.sql.types.DataTypes;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+
+public class JavaBeanWithArraySuite {
+
+ private static final List<Record> RECORDS = new ArrayList<>();
+
+ static {
+ RECORDS.add(new Record(1,
+ Arrays.asList(new Interval(111, 211), new Interval(121,
221)),
+ Arrays.asList(11, 21, 31, 41)
+ ));
+ RECORDS.add(new Record(2,
+ Arrays.asList(new Interval(112, 212), new Interval(122,
222)),
+ Arrays.asList(12, 22, 32, 42)
+ ));
+ RECORDS.add(new Record(3,
+ Arrays.asList(new Interval(113, 213), new Interval(123,
223)),
+ Arrays.asList(13, 23, 33, 43)
+ ));
+ }
+
+ private TestSparkSession spark;
+
+ @Before
+ public void setUp() {
+ spark = new TestSparkSession();
+ }
+
+ @After
+ public void tearDown() {
+ spark.stop();
+ spark = null;
+ }
+
+ @Test
+ public void testBeanWithArrayFieldsDeserialization() {
+
+ StructType schema = createSchema();
+ Encoder<Record> encoder = Encoders.bean(Record.class);
+
+ Dataset<Record> dataset = spark
+ .read()
+ .format("json")
+ .schema(schema)
--- End diff --
I'm wondering if we can use the latest and neat approach in this PR. Then,
we can remove `createSchema()` here.
```scala
- .schema(schema)
+ .schema("id int, intervals array<struct<starttime: bigint, endtime:
bigint>>, values array<int>")
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
