peter-toth commented on a change in pull request #29737:
URL: https://github.com/apache/spark/pull/29737#discussion_r489386143
##########
File path:
sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/HiveOrcQuerySuite.scala
##########
@@ -316,4 +317,24 @@ class HiveOrcQuerySuite extends OrcQueryTest with
TestHiveSingleton {
}
}
}
+
+ test("SPARK-32864: Support ORC forced positional evolution") {
+ Seq("native", "hive").foreach { orcImpl =>
+ withSQLConf(SQLConf.ORC_IMPLEMENTATION.key -> orcImpl,
+ OrcConf.FORCE_POSITIONAL_EVOLUTION.getAttribute -> "true") {
+ withTempPath { f =>
+ val path = f.getCanonicalPath
+ Seq(1 -> 2).toDF("c1", "c2").write.orc(path)
+ checkAnswer(spark.read.orc(path), Row(1, 2))
+
+ withSQLConf(HiveUtils.CONVERT_METASTORE_ORC.key -> "true") { //
default since 2.3.0
+ withTable("t") {
+ sql(s"CREATE EXTERNAL TABLE t(c3 INT, c4 INT) STORED AS ORC
LOCATION '$path'")
+ checkAnswer(spark.table("t"), Row(1, 2))
Review comment:
Thanks. I've extended the test with that case.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala
##########
@@ -142,11 +142,12 @@ object OrcUtils extends Logging {
reader: Reader,
conf: Configuration): Option[(Array[Int], Boolean)] = {
val orcFieldNames = reader.getSchema.getFieldNames.asScala
+ val forcePositionalEvolution =
OrcConf.FORCE_POSITIONAL_EVOLUTION.getBoolean(conf)
if (orcFieldNames.isEmpty) {
// SPARK-8501: Some old empty ORC files always have an empty schema
stored in their footer.
None
} else {
- if (orcFieldNames.forall(_.startsWith("_col"))) {
+ if (forcePositionalEvolution ||
orcFieldNames.forall(_.startsWith("_col"))) {
// This is a ORC file written by Hive, no field names in the physical
schema, assume the
Review comment:
Done.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
