[SPARK-43066][SQL] Add test for dropDuplicates in JavaDatasetSuite

### What changes were proposed in this pull request?

This PR proposes to add test for dropDuplicates in JavaDatasetSuite.

### Why are the changes needed?

The API dropDuplicates wasn't tested by Java test suite. It'd be better to have a sanity check to verify inter-op between Scala and Java works well.

### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?

CI will verify.

Closes apache#40702 from HeartSaVioR/SPARK-43066.

Authored-by: Jungtaek Lim <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>

sql/core/src/test/java/test/org/apache/spark/sql/JavaDatasetSuite.java

@@ -23,6 +23,7 @@
 import java.sql.Timestamp;
 import java.time.*;
 import java.util.*;
+import java.util.stream.Collectors;
 import javax.annotation.Nonnull;
 
 import org.apache.spark.api.java.Optional;
@@ -535,6 +536,76 @@ public void testJoin() {
       joined.collectAsList());
   }
 
+  private static final Comparator<Tuple2<String, Integer>> comparatorStringAndIntTuple =
+      new Comparator<Tuple2<String, Integer>>() {
+        @Override
+        public int compare(Tuple2<String, Integer> o1, Tuple2<String, Integer> o2) {
+          if (o1._1.compareTo(o2._1) != 0) {
+            return o1._1.compareTo(o2._1);
+          }
+          return o1._2.compareTo(o2._2);
+        }
+
+        @Override
+        public boolean equals(Object obj) {
+          return super.equals(obj);
+        }
+      };
+
+  private void assertEqualsUnorderly(
+      List<Tuple2<String, Integer>> expected,
+      List<Tuple2<String, Integer>> actual) {
+    Assert.assertEquals(
+        expected.stream().sorted(comparatorStringAndIntTuple).collect(Collectors.toList()),
+        actual.stream().sorted(comparatorStringAndIntTuple).collect(Collectors.toList())
+    );
+  }
+
+  @Test
+  public void testDropDuplicates() {
+    List<Tuple2<String, Integer>> data = Arrays.asList(
+        new Tuple2<>("a", 1), new Tuple2<>("a", 2),
+        new Tuple2<>("b", 1), new Tuple2<>("a", 1)
+    );
+    Dataset<Tuple2<String, Integer>> ds = spark.createDataset(data,
+        Encoders.tuple(Encoders.STRING(), Encoders.INT()));
+
+    assertEqualsUnorderly(
+        Arrays.asList(tuple2("a", 1), tuple2("a", 2), tuple2("b", 1)),
+        ds.dropDuplicates().collectAsList()
+    );
+
+    assertEqualsUnorderly(
+        Arrays.asList(tuple2("a", 1), tuple2("b", 1)),
+        ds.dropDuplicates("_1").collectAsList()
+    );
+
+    assertEqualsUnorderly(
+        Arrays.asList(tuple2("a", 1), tuple2("b", 1)),
+        ds.dropDuplicates(new String[] { "_1" }).collectAsList()
+    );
+
+    assertEqualsUnorderly(
+        Arrays.asList(tuple2("a", 1), tuple2("a", 2)),
+        ds.dropDuplicates("_2").collectAsList()
+    );
+
+    assertEqualsUnorderly(
+        Arrays.asList(tuple2("a", 1), tuple2("a", 2)),
+        ds.dropDuplicates(new String[] { "_2" }).collectAsList()
+    );
+
+    assertEqualsUnorderly(
+        Arrays.asList(tuple2("a", 1), tuple2("a", 2), tuple2("b", 1)),
+        ds.dropDuplicates("_1", "_2").collectAsList()
+    );
+
+    assertEqualsUnorderly(
+        Arrays.asList(tuple2("a", 1), tuple2("a", 2), tuple2("b", 1)),
+        ds.dropDuplicates(new String[] { "_1", "_2" }).collectAsList()
+    );
+  }
+
   @Test
   public void testTupleEncoder() {
     Encoder<Tuple2<Integer, String>> encoder2 = Encoders.tuple(Encoders.INT(), Encoders.STRING());