Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/22622#discussion_r222911529 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcSourceSuite.scala --- @@ -115,6 +116,69 @@ abstract class OrcSuite extends OrcTest with BeforeAndAfterAll { } } + protected def testSelectiveDictionaryEncoding(isSelective: Boolean) { + val tableName = "orcTable" + + withTempDir { dir => + withTable(tableName) { + val sqlStatement = orcImp match { + case "native" => + s""" + |CREATE TABLE $tableName (zipcode STRING, uniqColumn STRING, value DOUBLE) + |USING ORC + |OPTIONS ( + | path '${dir.toURI}', + | orc.dictionary.key.threshold '1.0', + | orc.column.encoding.direct 'uniqColumn' --- End diff -- I am fine either way. However, our current doc does not explain we are passing the data source specific options to the underlying data source: https://spark.apache.org/docs/latest/sql-programming-guide.html#manually-specifying-options Could you help improve it?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org