From 4ad5153f5449319a7e82c9013ccff4494ab58ef1 Mon Sep 17 00:00:00 2001 From: Liang-Chi Hsieh Date: Fri, 27 Feb 2015 11:06:47 +0800 Subject: [SPARK-6037][SQL] Avoiding duplicate Parquet schema merging `FilteringParquetRowInputFormat` manually merges Parquet schemas before computing splits. However, it is duplicate because the schemas are already merged in `ParquetRelation2`. We don't need to re-merge them at `InputFormat`. Author: Liang-Chi Hsieh Closes #4786 from viirya/dup_parquet_schemas_merge and squashes the following commits: ef78a5a [Liang-Chi Hsieh] Avoiding duplicate Parquet schema merging. --- .../spark/sql/parquet/ParquetTableOperations.scala | 23 +++++++--------------- 1 file changed, 7 insertions(+), 16 deletions(-) (limited to 'sql') diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala index 9061d3f5fe..4e4f647767 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala @@ -434,22 +434,13 @@ private[parquet] class FilteringParquetRowInputFormat return splits } - Option(globalMetaData.getKeyValueMetaData.get(RowReadSupport.SPARK_METADATA_KEY)).foreach { - schemas => - val mergedSchema = schemas - .map(DataType.fromJson(_).asInstanceOf[StructType]) - .reduce(_ merge _) - .json - - val mergedMetadata = globalMetaData - .getKeyValueMetaData - .updated(RowReadSupport.SPARK_METADATA_KEY, setAsJavaSet(Set(mergedSchema))) - - globalMetaData = new GlobalMetaData( - globalMetaData.getSchema, - mergedMetadata, - globalMetaData.getCreatedBy) - } + val metadata = configuration.get(RowWriteSupport.SPARK_ROW_SCHEMA) + val mergedMetadata = globalMetaData + .getKeyValueMetaData + .updated(RowReadSupport.SPARK_METADATA_KEY, setAsJavaSet(Set(metadata))) + + globalMetaData = new GlobalMetaData(globalMetaData.getSchema, + mergedMetadata, globalMetaData.getCreatedBy) val readContext = getReadSupport(configuration).init( new InitContext(configuration, -- cgit v1.2.3