Skip to content

[SPARK-40775][SQL] Fix duplicate description entries for V2 file scans #38229

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

[SPARK-40775][SQL] Fix duplicate description entries for V2 file scans #38229

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d6656c2
Let FileScan build description from metadata
Kimahriman Oct 8, 2022
4c5a183
Fix tests
Kimahriman Oct 8, 2022
ae9b783
Remove description from AvroScan
Kimahriman Oct 31, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,10 +70,6 @@ case class AvroScan(

override def hashCode(): Int = super.hashCode()

override def description(): String = {
super.description() + ", PushedFilters: " + pushedFilters.mkString("[", ", ", "]")
}

override def getMetaData(): Map[String, String] = {
super.getMetaData() ++ Map("PushedFilters" -> seqToString(pushedFilters))
}
Expand Down
4 changes: 0 additions & 4 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,10 +91,6 @@ case class CSVScan(

override def hashCode(): Int = super.hashCode()

override def description(): String = {
super.description() + ", PushedFilters: " + pushedFilters.mkString("[", ", ", "]")
}

override def getMetaData(): Map[String, String] = {
super.getMetaData() ++ Map("PushedFilters" -> seqToString(pushedFilters))
}
Expand Down
4 changes: 2 additions & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,7 @@ case class JsonScan(

override def hashCode(): Int = super.hashCode()

override def description(): String = {
super.description() + ", PushedFilters: " + pushedFilters.mkString("[", ", ", "]")
override def getMetaData(): Map[String, String] = {
super.getMetaData() ++ Map("PushedFilters" -> pushedFilters.mkString("[", ", ", "]"))
Comment on lines -94 to +95
Copy link
Contributor Author

@Kimahriman Kimahriman Oct 13, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure why JSON was different than the others but made it the same by just providing metadata. Updated related UT below to accommodate.

}
}
6 changes: 0 additions & 6 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,12 +92,6 @@ case class OrcScan(
("[]", "[]")
}

override def description(): String = {
super.description() + ", PushedFilters: " + seqToString(pushedFilters) +
", PushedAggregation: " + pushedAggregationsStr +
", PushedGroupBy: " + pushedGroupByStr
}

override def getMetaData(): Map[String, String] = {
super.getMetaData() ++ Map("PushedFilters" -> seqToString(pushedFilters)) ++
Map("PushedAggregation" -> pushedAggregationsStr) ++
Expand Down
6 changes: 0 additions & 6 deletions ...re/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,12 +127,6 @@ case class ParquetScan(
("[]", "[]")
}

override def description(): String = {
super.description() + ", PushedFilters: " + seqToString(pushedFilters) +
", PushedAggregation: " + pushedAggregationsStr +
", PushedGroupBy: " + pushedGroupByStr
}

override def getMetaData(): Map[String, String] = {
super.getMetaData() ++ Map("PushedFilters" -> seqToString(pushedFilters)) ++
Map("PushedAggregation" -> pushedAggregationsStr) ++
Expand Down
19 changes: 5 additions & 14 deletions sql/core/src/test/scala/org/apache/spark/sql/ExplainSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -462,27 +462,18 @@ class ExplainSuite extends ExplainSuiteHelper with DisableAdaptiveExecutionSuite
withTempDir { dir =>
Seq("parquet", "orc", "csv", "json").foreach { fmt =>
val basePath = dir.getCanonicalPath + "/" + fmt
val pushFilterMaps = Map (
"parquet" ->
"|PushedFilters: \\[IsNotNull\\(value\\), GreaterThan\\(value,2\\)\\]",
"orc" ->
"|PushedFilters: \\[IsNotNull\\(value\\), GreaterThan\\(value,2\\)\\]",
"csv" ->
"|PushedFilters: \\[IsNotNull\\(value\\), GreaterThan\\(value,2\\)\\]",
"json" ->
"|remove_marker"
)
val expected_plan_fragment1 =

val expectedPlanFragment =
s"""
|\\(1\\) BatchScan $fmt file:$basePath
|Output \\[2\\]: \\[value#x, id#x\\]
|DataFilters: \\[isnotnull\\(value#x\\), \\(value#x > 2\\)\\]
|Format: $fmt
|Location: InMemoryFileIndex\\([0-9]+ paths\\)\\[.*\\]
|PartitionFilters: \\[isnotnull\\(id#x\\), \\(id#x > 1\\)\\]
${pushFilterMaps.get(fmt).get}
|PushedFilters: \\[IsNotNull\\(value\\), GreaterThan\\(value,2\\)\\]
|ReadSchema: struct\\<value:int\\>
|""".stripMargin.replaceAll("\nremove_marker", "").trim
|""".stripMargin.trim

spark.range(10)
.select(col("id"), col("id").as("value"))
Expand All @@ -500,7 +491,7 @@ class ExplainSuite extends ExplainSuiteHelper with DisableAdaptiveExecutionSuite
.format(fmt)
.load(basePath).where($"id" > 1 && $"value" > 2)
val normalizedOutput = getNormalizedExplain(df, FormattedMode)
assert(expected_plan_fragment1.r.findAllMatchIn(normalizedOutput).length == 1)
assert(expectedPlanFragment.r.findAllMatchIn(normalizedOutput).length == 1)
}
}
}
Expand Down
3 changes: 2 additions & 1 deletion ...t/scala/org/apache/spark/sql/execution/datasources/FileSourceAggregatePushDownSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,7 +347,8 @@ trait FileSourceAggregatePushDownSuite
spark.read.format(format).load(file.getCanonicalPath).createOrReplaceTempView("test")
Seq("false", "true").foreach { enableVectorizedReader =>
withSQLConf(aggPushDownEnabledKey -> "true",
vectorizedReaderEnabledKey -> enableVectorizedReader) {
vectorizedReaderEnabledKey -> enableVectorizedReader,
SQLConf.MAX_METADATA_STRING_LENGTH.key -> "1000") {
Copy link
Contributor Author

@Kimahriman Kimahriman Oct 13, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The overridden description part wasn't limited in chars, but the metadata version is, so just bump up the max size to make sure the full string can be found


val testMinWithAllTypes = sql("SELECT min(StringCol), min(BooleanCol), min(ByteCol), " +
"min(BinaryCol), min(ShortCol), min(IntegerCol), min(LongCol), min(FloatCol), " +
Expand Down