AngersZhuuuu commented on a change in pull request #29085:
URL: https://github.com/apache/spark/pull/29085#discussion_r458612159
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/BaseScriptTransformationExec.scala
##########
@@ -87,17 +178,69 @@ trait BaseScriptTransformationExec extends UnaryExecNode {
}
}
}
+
+ private lazy val fieldWriters: Seq[String => Any] = output.map { attr =>
+ val converter =
CatalystTypeConverters.createToCatalystConverter(attr.dataType)
+ attr.dataType match {
+ case StringType => wrapperConvertException(data => data, converter)
+ case BooleanType => wrapperConvertException(data => data.toBoolean,
converter)
+ case ByteType => wrapperConvertException(data => data.toByte, converter)
+ case BinaryType => wrapperConvertException(data => data.getBytes,
converter)
+ case IntegerType => wrapperConvertException(data => data.toInt,
converter)
+ case ShortType => wrapperConvertException(data => data.toShort,
converter)
+ case LongType => wrapperConvertException(data => data.toLong, converter)
+ case FloatType => wrapperConvertException(data => data.toFloat,
converter)
+ case DoubleType => wrapperConvertException(data => data.toDouble,
converter)
+ case _: DecimalType => wrapperConvertException(data => BigDecimal(data),
converter)
+ case DateType if conf.datetimeJava8ApiEnabled =>
+ wrapperConvertException(data => DateTimeUtils.stringToDate(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.daysToLocalDate).orNull, converter)
+ case DateType => wrapperConvertException(data =>
DateTimeUtils.stringToDate(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.toJavaDate).orNull, converter)
+ case TimestampType if conf.datetimeJava8ApiEnabled =>
+ wrapperConvertException(data => DateTimeUtils.stringToTimestamp(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.microsToInstant).orNull, converter)
+ case TimestampType => wrapperConvertException(data =>
DateTimeUtils.stringToTimestamp(
+ UTF8String.fromString(data),
+ DateTimeUtils.getZoneId(conf.sessionLocalTimeZone))
+ .map(DateTimeUtils.toJavaTimestamp).orNull, converter)
+ case CalendarIntervalType => wrapperConvertException(
+ data => IntervalUtils.stringToInterval(UTF8String.fromString(data)),
+ converter)
+ case udt: UserDefinedType[_] =>
+ wrapperConvertException(data => udt.deserialize(data), converter)
+ case _ => wrapperConvertException(data => data, converter)
+ }
+ }
+
+ // Keep consistent with Hive `LazySimpleSerde`, when there is a type case
error, return null
+ private val wrapperConvertException: (String => Any, Any => Any) => String
=> Any =
+ (f: String => Any, converter: Any => Any) =>
+ (data: String) => converter {
+ try {
+ f(data)
+ } catch {
+ case _: Exception => null
Review comment:
Done
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]