commit fe4eee0af3ca205deb76cd792b64a202c565ea2b
author sychen <sychen@ctrip.com> Wed Apr 24 08:48:50 2024 -0700
committer Dongjoon Hyun <dongjoon@apache.org> Wed Apr 24 08:48:50 2024 -0700
tree 6e870aec056857074bb348e3e9458223cdeb4034
parent 67b24baf3d044d743c8a0368be99d639e4487da0

ORC-1699: Fix SparkBenchmark in Parquet format according to SPARK-40918

### What changes were proposed in this pull request?
This PR aims to fix SparkBenchmark in Parquet format according to SPARK-40918.

### Why are the changes needed?
Similar to [ORC-1578](https://issues.apache.org/jira/browse/ORC-1578), there are similar problems when reading parquet format files in SparkBenchmark.

```java
java.lang.IllegalArgumentException: OPTION_RETURNING_BATCH should always be set for ParquetFileFormat. To workaround this issue, set spark.sql.parquet.enableVectorizedReader=false.
	at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.$anonfun$buildReaderWithPartitionValues$1(ParquetFileFormat.scala:192)
	at scala.collection.immutable.Map$EmptyMap$.getOrElse(Map.scala:110)
	at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.buildReaderWithPartitionValues(ParquetFileFormat.scala:191)
	at org.apache.orc.bench.spark.SparkBenchmark.pushDown(SparkBenchmark.java:314)
	at org.apache.orc.bench.spark.jmh_generated.SparkBenchmark_pushDown_jmhTest.pushDown_avgt_jmhStub(SparkBenchmark_pushDown_jmhTest.java:219)
```

### How was this patch tested?
local test

### Was this patch authored or co-authored using generative AI tooling?
No

Closes #1908 from cxzl25/ORC-1699.

Authored-by: sychen <sychen@ctrip.com>
Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>

java/bench/spark/src/java/org/apache/orc/bench/spark/SparkBenchmark.java

diff --git a/java/bench/spark/src/java/org/apache/orc/bench/spark/SparkBenchmark.java b/java/bench/spark/src/java/org/apache/orc/bench/spark/SparkBenchmark.java
index 1285875..90eceee 100644
--- a/java/bench/spark/src/java/org/apache/orc/bench/spark/SparkBenchmark.java
+++ b/java/bench/spark/src/java/org/apache/orc/bench/spark/SparkBenchmark.java
@@ -195,6 +195,9 @@
       case "orc":
         options.add(new Tuple2<>("returning_batch", "true")); // SPARK-40918
         break;
+      case "parquet":
+        options.add(new Tuple2<>("returning_batch", "true")); // SPARK-40918
+        break;
       default:
         break;
     }
@@ -228,6 +231,9 @@
       case "orc":
         options.add(new Tuple2<>("returning_batch", "true")); // SPARK-40918
         break;
+      case "parquet":
+        options.add(new Tuple2<>("returning_batch", "true")); // SPARK-40918
+        break;
       default:
         break;
     }
@@ -303,6 +309,9 @@
       case "orc":
         options.add(new Tuple2<>("returning_batch", "true")); // SPARK-40918
         break;
+      case "parquet":
+        options.add(new Tuple2<>("returning_batch", "true")); // SPARK-40918
+        break;
       default:
         break;
     }