Skip to content

[SPARK-16216][SQL][FOLLOWUP] Enable timestamp type tests for JSON and verify all unsupported types in CSV #14829

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
HyukjinKwon wants to merge 5 commits into from
Closed

[SPARK-16216][SQL][FOLLOWUP] Enable timestamp type tests for JSON and verify all unsupported types in CSV #14829

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2f10a99
Clean up CSV and enable JSON types for timestamp
HyukjinKwon Aug 26, 2016
0f83127
Add mistakenly removed case
HyukjinKwon Aug 26, 2016
831268d
Revert the change for cleaning up CSV schema verification
HyukjinKwon Aug 26, 2016
948b456
Adds the test for UDF and make whitelist
HyukjinKwon Aug 26, 2016
1baacf2
Remove the command back
HyukjinKwon Aug 26, 2016
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
17 changes: 11 additions & 6 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,13 +186,18 @@ class CSVFileFormat extends TextBasedFileFormat with DataSourceRegister {
}

private def verifySchema(schema: StructType): Unit = {
schema.foreach { field =>
field.dataType match {
case _: ArrayType | _: MapType | _: StructType =>
throw new UnsupportedOperationException(
s"CSV data source does not support ${field.dataType.simpleString} data type.")
def verifyType(dataType: DataType): Unit = dataType match {
case ByteType | ShortType | IntegerType | LongType | FloatType |
DoubleType | BooleanType | _: DecimalType | TimestampType |
DateType | StringType =>

case udt: UserDefinedType[_] => verifyType(udt.sqlType)
Copy link
Member Author

@HyukjinKwon HyukjinKwon Aug 26, 2016

Choose a reason for hiding this comment

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

Meaning adding cases here for unsupported types.


case _ =>
}
throw new UnsupportedOperationException(
s"CSV data source does not support ${dataType.simpleString} data type.")
}

schema.foreach(field => verifyType(field.dataType))
}
}
1 change: 1 addition & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -290,6 +290,7 @@ private[csv] object CSVTypeCast {
DateTimeUtils.millisToDays(DateTimeUtils.stringToTime(datum).getTime)
}
case _: StringType => UTF8String.fromString(datum)
case udt: UserDefinedType[_] => castTo(datum, udt.sqlType, nullable, options)
case _ => throw new RuntimeException(s"Unsupported type: ${castType.typeName}")
}
}
Expand Down
16 changes: 14 additions & 2 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,7 @@ import org.apache.hadoop.io.SequenceFile.CompressionType
import org.apache.hadoop.io.compress.GzipCodec

import org.apache.spark.SparkException
import org.apache.spark.sql.{DataFrame, QueryTest, Row}
import org.apache.spark.sql.catalyst.util.DateTimeUtils
import org.apache.spark.sql.{DataFrame, QueryTest, Row, UDT}
import org.apache.spark.sql.test.{SharedSQLContext, SQLTestUtils}
import org.apache.spark.sql.types._

Expand Down Expand Up @@ -681,6 +680,19 @@ class CSVSuite extends QueryTest with SharedSQLContext with SQLTestUtils {
Seq((1, Array("Tesla", "Chevy", "Ford"))).toDF("id", "brands").write.csv(csvDir)
}.getMessage
assert(msg.contains("CSV data source does not support array<string> data type"))

msg = intercept[UnsupportedOperationException] {
Seq((1, new UDT.MyDenseVector(Array(0.25, 2.25, 4.25)))).toDF("id", "vectors")
.write.csv(csvDir)
}.getMessage
assert(msg.contains("CSV data source does not support array<double> data type"))

msg = intercept[SparkException] {
val schema = StructType(StructField("a", new UDT.MyDenseVectorUDT(), true) :: Nil)
spark.range(1).write.csv(csvDir)
spark.read.schema(schema).csv(csvDir).collect()
}.getCause.getMessage
assert(msg.contains("Unsupported type: array"))
}
}

Expand Down
4 changes: 0 additions & 4 deletions sql/hive/src/test/scala/org/apache/spark/sql/sources/JsonHadoopFsRelationSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,10 +32,6 @@ class JsonHadoopFsRelationSuite extends HadoopFsRelationTest {
override protected def supportsDataType(dataType: DataType): Boolean = dataType match {
case _: NullType => false
case _: BinaryType => false
// `TimestampType` is disabled because `DatatypeConverter.parseDateTime()`
// in `DateTimeUtils` parses the formatted string wrongly when the date is
// too early. (e.g. "1600-07-13T08:36:32.847").
case _: TimestampType => false
case _: CalendarIntervalType => false
case _ => true
}
Expand Down