Jonathancui123 commented on code in PR #36871:
URL: https://github.com/apache/spark/pull/36871#discussion_r906232351
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala:
##########
@@ -197,34 +199,50 @@ class UnivocityParser(
Decimal(decimalParser(datum), dt.precision, dt.scale)
}
- case _: TimestampType => (d: String) =>
+ case _: DateType => (d: String) =>
nullSafeDatum(d, name, nullable, options) { datum =>
try {
- timestampFormatter.parse(datum)
+ dateFormatter.parse(datum)
} catch {
case NonFatal(e) =>
// If fails to parse, then tries the way used in 2.0 and 1.x for
backwards
// compatibility.
val str =
DateTimeUtils.cleanLegacyTimestampStr(UTF8String.fromString(datum))
- DateTimeUtils.stringToTimestamp(str,
options.zoneId).getOrElse(throw e)
+ DateTimeUtils.stringToDate(str).getOrElse(throw e)
}
}
- case _: TimestampNTZType => (d: String) =>
- nullSafeDatum(d, name, nullable, options) { datum =>
- timestampNTZFormatter.parseWithoutTimeZone(datum, false)
- }
-
- case _: DateType => (d: String) =>
+ case _: TimestampType => (d: String) =>
nullSafeDatum(d, name, nullable, options) { datum =>
try {
- dateFormatter.parse(datum)
+ timestampFormatter.parse(datum)
} catch {
case NonFatal(e) =>
// If fails to parse, then tries the way used in 2.0 and 1.x for
backwards
// compatibility.
val str =
DateTimeUtils.cleanLegacyTimestampStr(UTF8String.fromString(datum))
- DateTimeUtils.stringToDate(str).getOrElse(throw e)
+ DateTimeUtils.stringToTimestamp(str, options.zoneId).getOrElse {
+ // There may be date type entries in timestamp column due to
schema inference
+ if (options.inferDate) {
+ daysToMicros(dateFormatter.parse(datum), options.zoneId)
Review Comment:
@bersprockets Thanks for the suggestion! Do you know what is the advantage
of allowing Legacy Formatter? i.e. what is a date format that the legacy
formatter can handle but the current formatter cannot?
I'm wondering if there will be a sufficient population of users who want to
infer date in schema and also use legacy date formats
cc: @Yaohua628
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
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
