Yohahaha commented on code in PR #10697:
URL:
https://github.com/apache/incubator-gluten/pull/10697#discussion_r2389631210
##########
backends-velox/src/test/scala/org/apache/gluten/execution/VeloxScanSuite.scala:
##########
@@ -207,4 +207,78 @@ class VeloxScanSuite extends
VeloxWholeStageTransformerSuite {
}
}
}
+
+ test("parquet index based schema evolution") {
+ withSQLConf(VeloxConfig.PARQUET_USE_COLUMN_NAMES.key -> "false") {
+ withTempDir {
+ dir =>
+ val path = dir.getCanonicalPath
+ spark
+ .range(2)
+ .selectExpr("id as a", "cast(id + 10 as string) as b")
+ .write
+ .mode("overwrite")
+ .parquet(path)
+
+ withTable("test") {
+ sql(s"""create table test (c long, d string, e float) using
parquet options
+ |(path '$path')""".stripMargin)
+ var df = sql("select c, d from test")
+ checkAnswer(df, Seq(Row(0L, "10"), Row(1L, "11")))
+
+ df = sql("select d from test")
+ checkAnswer(df, Seq(Row("10"), Row("11")))
+
+ df = sql("select c from test")
+ checkAnswer(df, Seq(Row(0L), Row(1L)))
+
+ df = sql("select d, c from test")
+ checkAnswer(df, Seq(Row("10", 0L), Row("11", 1L)))
+
+ df = sql("select c, d, e from test")
+ checkAnswer(df, Seq(Row(0L, "10", null), Row(1L, "11", null)))
+
+ df = sql("select e, d, c from test")
+ checkAnswer(df, Seq(Row(null, "10", 0L), Row(null, "11", 1L)))
+ }
+ }
+ }
+ }
+
+ test("ORC index based schema evolution") {
+ withSQLConf(VeloxConfig.ORC_USE_COLUMN_NAMES.key -> "false") {
+ withTempDir {
+ dir =>
+ val path = dir.getCanonicalPath
+ spark
+ .range(2)
+ .selectExpr("id as a", "cast(id + 10 as string) as b")
+ .write
+ .mode("overwrite")
+ .orc(path)
+
+ withTable("test") {
+ sql(s"""create table test (c long, d string, e float) using orc
options
+ |(path '$path')""".stripMargin)
+ var df = sql("select c, d from test")
+ checkAnswer(df, Seq(Row(0L, "10"), Row(1L, "11")))
Review Comment:
> Unfortunately, I tried and it doesn't work because this compares against
Vanilla Spark and Vanilla Spark doesn't support this out of the box (see the
discussion with Rui above).
does vanilla spark need any extra configs?
users always expects gluten's behavior align with spark, if not, I think we
need rethinking this feature. @rui-mo
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
