Github user srowen commented on a diff in the pull request:

    https://github.com/apache/spark/pull/14118#discussion_r78913816
  
    --- Diff: 
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala
 ---
    @@ -232,66 +232,62 @@ private[csv] object CSVTypeCast {
           nullable: Boolean = true,
           options: CSVOptions = CSVOptions()): Any = {
     
    -    castType match {
    -      case _: ByteType => if (datum == options.nullValue && nullable) null 
else datum.toByte
    -      case _: ShortType => if (datum == options.nullValue && nullable) 
null else datum.toShort
    -      case _: IntegerType => if (datum == options.nullValue && nullable) 
null else datum.toInt
    -      case _: LongType => if (datum == options.nullValue && nullable) null 
else datum.toLong
    -      case _: FloatType =>
    -        if (datum == options.nullValue && nullable) {
    -          null
    -        } else if (datum == options.nanValue) {
    -          Float.NaN
    -        } else if (datum == options.negativeInf) {
    -          Float.NegativeInfinity
    -        } else if (datum == options.positiveInf) {
    -          Float.PositiveInfinity
    -        } else {
    -          Try(datum.toFloat)
    -            
.getOrElse(NumberFormat.getInstance(Locale.getDefault).parse(datum).floatValue())
    -        }
    -      case _: DoubleType =>
    -        if (datum == options.nullValue && nullable) {
    -          null
    -        } else if (datum == options.nanValue) {
    -          Double.NaN
    -        } else if (datum == options.negativeInf) {
    -          Double.NegativeInfinity
    -        } else if (datum == options.positiveInf) {
    -          Double.PositiveInfinity
    -        } else {
    -          Try(datum.toDouble)
    -            
.getOrElse(NumberFormat.getInstance(Locale.getDefault).parse(datum).doubleValue())
    -        }
    -      case _: BooleanType => datum.toBoolean
    -      case dt: DecimalType =>
    -        if (datum == options.nullValue && nullable) {
    -          null
    -        } else {
    -          val value = new BigDecimal(datum.replaceAll(",", ""))
    -          Decimal(value, dt.precision, dt.scale)
    -        }
    -      case _: TimestampType =>
    -        // This one will lose microseconds parts.
    -        // See https://issues.apache.org/jira/browse/SPARK-10681.
    -        Try(options.timestampFormat.parse(datum).getTime * 1000L)
    -          .getOrElse {
    -            // If it fails to parse, then tries the way used in 2.0 and 
1.x for backwards
    -            // compatibility.
    -            DateTimeUtils.stringToTime(datum).getTime  * 1000L
    +    if (datum == options.nullValue && nullable) {
    +      null
    +    } else {
    +      castType match {
    +        case _: ByteType => datum.toByte
    +        case _: ShortType => datum.toShort
    +        case _: IntegerType => datum.toInt
    +        case _: LongType => datum.toLong
    +        case _: FloatType =>
    +          if (datum == options.nanValue) {
    --- End diff --
    
    Can these nested if-else statements be a match statement? or is there some 
overhead to it that is too significant?


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to