AngersZhuuuu commented on a change in pull request #29085:
URL: https://github.com/apache/spark/pull/29085#discussion_r454866402
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/BaseScriptTransformationExec.scala
##########
@@ -87,17 +90,60 @@ trait BaseScriptTransformationExec extends UnaryExecNode {
}
}
}
+
+ def wrapper(data: String, dt: DataType): Any = {
+ dt match {
+ case StringType => data
+ case ByteType => JavaUtils.stringToBytes(data)
+ case IntegerType => data.toInt
+ case ShortType => data.toShort
+ case LongType => data.toLong
+ case FloatType => data.toFloat
+ case DoubleType => data.toDouble
+ case dt: DecimalType => BigDecimal(data)
+ case DateType if conf.datetimeJava8ApiEnabled =>
+ DateTimeUtils.stringToDate(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.daysToLocalDate).orNull
+ case DateType =>
+ DateTimeUtils.stringToDate(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.toJavaDate).orNull
+ case TimestampType if conf.datetimeJava8ApiEnabled =>
+ DateTimeUtils.stringToTimestamp(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.microsToInstant).orNull
+ case TimestampType =>
+ DateTimeUtils.stringToTimestamp(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.toJavaTimestamp).orNull
+ case CalendarIntervalType =>
IntervalUtils.stringToInterval(UTF8String.fromString(data))
+ case dataType: DataType => data
+ }
+ }
}
-abstract class BaseScriptTransformationWriterThread(
- iter: Iterator[InternalRow],
- inputSchema: Seq[DataType],
- ioSchema: BaseScriptTransformIOSchema,
- outputStream: OutputStream,
- proc: Process,
- stderrBuffer: CircularBuffer,
- taskContext: TaskContext,
- conf: Configuration) extends Thread with Logging {
+abstract class BaseScriptTransformationWriterThread extends Thread with
Logging {
+
+ def iter: Iterator[InternalRow]
+
+ def inputSchema: Seq[DataType]
+
+ def ioSchema: BaseScriptTransformIOSchema
+
+ def outputStream: OutputStream
+
+ def proc: Process
+
+ def stderrBuffer: CircularBuffer
+
+ def taskContext: TaskContext
+
+ def conf: Configuration
Review comment:
Not need, without blank line looks better.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
