Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/20265#discussion_r161426568
--- Diff:
sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/OrcReadBenchmark.scala ---
@@ -483,6 +484,64 @@ object OrcReadBenchmark {
}
}
+ def filterPushDownBenchmark(values: Int, width: Int): Unit = {
+ val benchmark = new Benchmark(s"Filter Pushdown", values)
+
+ withTempPath { dir =>
+ withTempTable("t1", "nativeOrcTable", "hiveOrcTable") {
+ import spark.implicits._
+ val selectExpr = (1 to width).map(i => s"CAST(value AS STRING)
c$i")
+ val whereExpr = (1 to width).map(i => s"NOT c$i LIKE
'%not%exist%'").mkString(" AND ")
--- End diff --
I mean `LIKE '%not%exist%'` will not be optimized by `LikeSimplification`.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
