From 4207754cc67633956b80e213875f6f5c3c2c0952 Mon Sep 17 00:00:00 2001 From: Dongjoon Hyun Date: Sun, 21 Jan 2018 17:58:48 -0800 Subject: [PATCH] [MINOR] Fix wrong comments on org.apache.spark.sql.parquet.row.attributes --- .../sql/execution/datasources/parquet/ParquetFileFormat.scala | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala index 45bedf70f975c..f53a97ba45a26 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala @@ -108,8 +108,7 @@ class ParquetFileFormat ParquetOutputFormat.setWriteSupportClass(job, classOf[ParquetWriteSupport]) - // We want to clear this temporary metadata from saving into Parquet file. - // This metadata is only useful for detecting optional columns when pushdowning filters. + // This metadata is useful for keeping UDTs like Vector/Matrix. ParquetWriteSupport.setSchema(dataSchema, conf) // Sets flags for `ParquetWriteSupport`, which converts Catalyst schema to Parquet