From 26d7af9119a73d851c86314b4a207c0bfe437082 Mon Sep 17 00:00:00 2001
From: Liang-Chi Hsieh <simonh@tw.ibm.com>
Date: Mon, 11 Apr 2016 19:06:38 -0700
Subject: [PATCH] [SPARK-14520][SQL] Use correct return type in
VectorizedParquetInputFormat
## What changes were proposed in this pull request?
JIRA: https://issues.apache.org/jira/browse/SPARK-14520
`VectorizedParquetInputFormat` inherits `ParquetInputFormat` and overrides `createRecordReader`. However, its overridden `createRecordReader` returns a `ParquetRecordReader`. It should return a `RecordReader`. Otherwise, `ClassCastException` will be thrown.
## How was this patch tested?
Existing tests.
Author: Liang-Chi Hsieh <simonh@tw.ibm.com>
Closes #12292 from viirya/fix-vectorized-input-format.
---
.../sql/execution/datasources/parquet/ParquetRelation.scala | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRelation.scala
index ca6803b737..bcb2b2de13 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRelation.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRelation.scala
@@ -476,8 +476,8 @@ private[sql] class DefaultSource
final class VectorizedParquetInputFormat extends ParquetInputFormat[InternalRow] {
override def createRecordReader(
inputSplit: InputSplit,
- taskAttemptContext: TaskAttemptContext): ParquetRecordReader[InternalRow] = {
- new VectorizedParquetRecordReader().asInstanceOf[ParquetRecordReader[InternalRow]]
+ taskAttemptContext: TaskAttemptContext): RecordReader[Void, InternalRow] = {
+ new VectorizedParquetRecordReader().asInstanceOf[RecordReader[Void, InternalRow]]
}
}
--
GitLab