bersprockets commented on code in PR #36871:
URL: https://github.com/apache/spark/pull/36871#discussion_r906513077
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala:
##########
@@ -197,34 +198,46 @@ 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)
+ } else {
+ throw(e)
+ }
+ }
+ }
+ }
+
+ case _: TimestampNTZType => (d: String) =>
+ nullSafeDatum(d, name, nullable, options) { datum =>
+ try {
+ timestampNTZFormatter.parseWithoutTimeZone(datum, false)
+ } catch {
+ case NonFatal(e) if (options.inferDate) =>
+ daysToMicros(dateFormatter.parse(datum), options.zoneId)
Review Comment:
I think zoneId should probably be UTC for timestamp_ntz. Otherwise, you end
up with oddities like this:
```
scala> sql("set spark.sql.timestampType=TIMESTAMP_NTZ")
res0: org.apache.spark.sql.DataFrame = [key: string, value: string]
scala> val options = Map(
"inferSchema" -> "true",
"timestampFormat" -> "yyyy/MM/dd HH:mm:ss",
"timestampNTZFormat" -> "yyyy-MM-dd'T'HH:mm:ss",
"dateFormat" -> "yyyy-MM-dd",
"inferDate" -> "true")
options: scala.collection.immutable.Map[String,String] = Map(inferSchema ->
true, timestampFormat -> yyyy/MM/dd HH:mm:ss, timestampNTZFormat ->
yyyy-MM-dd'T'HH:mm:ss, dateFormat -> yyyy-MM-dd, inferDate -> true)
scala>
scala> val csvInput = Seq("2022-01-01T00:00:00", "2022-06-22").toDS()
csvInput: org.apache.spark.sql.Dataset[String] = [value: string]
scala> val df = spark.read.options(options).csv(csvInput)
df: org.apache.spark.sql.DataFrame = [_c0: timestamp_ntz]
scala> df.show(false)
+-------------------+
|_c0 |
+-------------------+
|2022-01-01 00:00:00|
|2022-06-22 07:00:00|
+-------------------+
scala>
```
Note `2022-06-22` becomes `2022-06-22 07:00:00`
--
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]
