From 885b46410afdde5c909b856616d6c6420aa271a7 Mon Sep 17 00:00:00 2001 From: Jason Lowe Date: Tue, 23 Mar 2021 21:54:09 -0500 Subject: [PATCH] Fix unknown column name error when filtering ORC file with no names Signed-off-by: Jason Lowe --- .../src/main/scala/com/nvidia/spark/rapids/GpuOrcScan.scala | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuOrcScan.scala b/sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuOrcScan.scala index ef24236b860..7f8b5853c15 100644 --- a/sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuOrcScan.scala +++ b/sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuOrcScan.scala @@ -840,7 +840,8 @@ class GpuOrcPartitionReader( if (debugDumpPrefix != null) { dumpOrcData(dataBuffer, dataSize) } - val includedColumns = ctx.updatedReadSchema.getFieldNames.asScala + val fieldNames = ctx.updatedReadSchema.getFieldNames.asScala.toArray + val includedColumns = requestedMapping.map(_.map(fieldNames(_))).getOrElse(fieldNames) val parseOpts = ORCOptions.builder() .withTimeUnit(DType.TIMESTAMP_MICROSECONDS) .withNumPyTypes(false)