Github user mallman commented on a diff in the pull request:
https://github.com/apache/spark/pull/22394#discussion_r217055207
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaPruningSuite.scala
---
@@ -245,28 +249,32 @@ class ParquetSchemaPruningSuite
checkAnswer(query.orderBy("id"), Row(1) :: Nil)
}
- private def testMixedCasePruning(testName: String)(testThunk: => Unit) {
- withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key -> "true",
- SQLConf.CASE_SENSITIVE.key -> "true") {
- test(s"Spark vectorized reader - case-sensitive parser - mixed-case
schema - $testName") {
- withMixedCaseData(testThunk)
+ private def testExactCasePruning(testName: String)(testThunk: => Unit) {
+ test(s"Spark vectorized reader - case-sensitive parser - mixed-case
schema - $testName") {
+ withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key -> "true",
+ SQLConf.CASE_SENSITIVE.key -> "true") {
+ withMixedCaseData(testThunk)
}
}
- withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key -> "false",
- SQLConf.CASE_SENSITIVE.key -> "false") {
- test(s"Parquet-mr reader - case-insensitive parser - mixed-case
schema - $testName") {
+ test(s"Parquet-mr reader - case-sensitive parser - mixed-case schema -
$testName") {
+ withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key -> "false",
+ SQLConf.CASE_SENSITIVE.key -> "true") {
withMixedCaseData(testThunk)
}
}
- withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key -> "true",
- SQLConf.CASE_SENSITIVE.key -> "false") {
- test(s"Spark vectorized reader - case-insensitive parser -
mixed-case schema - $testName") {
- withMixedCaseData(testThunk)
+ testMixedCasePruning(testName)(testThunk)
+ }
+
+ private def testMixedCasePruning(testName: String)(testThunk: => Unit) {
--- End diff --
Previously, this method ran `testThunk` with `SQLConf.CASE_SENSITIVE.key`
set to true and false. That was a mistake and incorrect. For example, the query
select col1, col2.b from mixedcase
will fail if `SQLConf.CASE_SENSITIVE.key` is set to true. That mistake was
causing 6 test cases to fail. Therefore, I moved the code that tests with a
case-sensitive parser out of `testMixedCasePruning` into `testExactCasePruning`
and included a call to `testMixedCasePruning` in `testExactCasePruning`.
I'll push a commit that refactors the method names and add code comments
that will make this clearer.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
