bersprockets commented on code in PR #36871:
URL: https://github.com/apache/spark/pull/36871#discussion_r905348742
##########
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:
>We do not use the legacy DateFormatter here to avoid parsing timestamps
with invalid suffixes.
I think you could still make it work, but you would need a new extension of
`LegacySimpleDateFormatter` (maybe `LegacyStrictSimpleDateFormatter`), with an
override like this:
```
def parseToDate(s: String): Date = {
val pp = new ParsePosition(0)
val res = sdf.parse(s, pp)
if (s.length != pp.getIndex) {
throw new RuntimeException(s"$s is not a date")
}
res
}
```
`2001-09-08-randomtext` would not parse, neither would `2022-01-02
12:56:33`, but `2022-01-02` would (assuming a format of `yyyy-MM-dd`).
I assume it would be slow (but I have not tested it).
Maybe not worth the extra code.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
