Github user ash211 commented on a diff in the pull request:
https://github.com/apache/spark/pull/17680#discussion_r112531312
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala
---
@@ -536,4 +537,43 @@ class ParquetFilterSuite extends QueryTest with
ParquetTest with SharedSQLContex
// scalastyle:on nonascii
}
}
+
+ test("SPARK-20364: Predicate pushdown for columns with a '.' in them") {
+ import testImplicits._
+
+ Seq(true, false).foreach { vectorized =>
+ withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key ->
vectorized.toString) {
+ withTempPath { path =>
+ Seq(Some(1),
None).toDF("col.dots").write.parquet(path.getAbsolutePath)
+
assert(spark.read.parquet(path.getAbsolutePath).where("`col.dots` > 0").count()
== 1)
+ }
+
+ withTempPath { path =>
+ Seq(Some(1L),
None).toDF("col.dots").write.parquet(path.getAbsolutePath)
+
assert(spark.read.parquet(path.getAbsolutePath).where("`col.dots` >=
1L").count() == 1)
+ }
+
+ withTempPath { path =>
+ Seq(Some(1.0F),
None).toDF("col.dots").write.parquet(path.getAbsolutePath)
+
assert(spark.read.parquet(path.getAbsolutePath).where("`col.dots` <
2.0").count() == 1)
+ }
+
+ withTempPath { path =>
+ Seq(Some(1.0D),
None).toDF("col.dots").write.parquet(path.getAbsolutePath)
+
assert(spark.read.parquet(path.getAbsolutePath).where("`col.dots` <=
1.0D").count() == 1)
+ }
+
+ withTempPath { path =>
+ Seq(true,
false).toDF("col.dots").write.parquet(path.getAbsolutePath)
+
assert(spark.read.parquet(path.getAbsolutePath).where("`col.dots` ==
true").count() == 1)
+ }
+
+ withTempPath { path =>
+ Seq("apple",
null).toDF("col.dots").write.parquet(path.getAbsolutePath)
+ assert(
+ spark.read.parquet(path.getAbsolutePath).where("`col.dots` IS
NOT NULL").count() == 1)
--- End diff --
thanks for adding the additional test below
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
