Skip to content

[SPARK-26546][SQL] Caching of java.time.format.DateTimeFormatter #23462

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
MaxGekk wants to merge 11 commits into from
Closed

[SPARK-26546][SQL] Caching of java.time.format.DateTimeFormatter #23462

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
aa3c146
Added a cache for DateTimeFormatter
MaxGekk Jan 5, 2019
f08c71e
Use computeIfAbsent
MaxGekk Jan 6, 2019
61038ea
Using Google's cache
MaxGekk Jan 7, 2019
68ec759
Unwrap the original exception
MaxGekk Jan 7, 2019
5c2d99d
Avoid Callable
MaxGekk Jan 8, 2019
2a67f44
Less settings for the cache
MaxGekk Jan 8, 2019
0ea07db
Moving getOrCreateFormatter to the DateTimeFormatterHelper trait
MaxGekk Jan 8, 2019
b7413a4
Removing exception handling
MaxGekk Jan 8, 2019
0737991
Removing unused import
MaxGekk Jan 8, 2019
545a710
Adding protected to getOrCreateFormatter
MaxGekk Jan 9, 2019
c68778c
Added a comment for getOrCreateFormatter
MaxGekk Jan 9, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateFormatter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ class Iso8601DateFormatter(
locale: Locale) extends DateFormatter with DateTimeFormatterHelper {

@transient
private lazy val formatter = buildFormatter(pattern, locale)
private lazy val formatter = DateTimeFormatterHelper.getFormatter(pattern, locale)
private val UTC = ZoneId.of("UTC")

private def toInstant(s: String): Instant = {
Expand Down
46 changes: 36 additions & 10 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeFormatterHelper.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,10 +22,34 @@ import java.time.chrono.IsoChronology
import java.time.format.{DateTimeFormatter, DateTimeFormatterBuilder, ResolverStyle}
import java.time.temporal.{ChronoField, TemporalAccessor, TemporalQueries}
import java.util.Locale
import java.util.concurrent.{Callable, TimeUnit}

import com.google.common.cache.CacheBuilder
import com.google.common.util.concurrent.{ExecutionError, UncheckedExecutionException}

trait DateTimeFormatterHelper {
protected def toInstantWithZoneId(temporalAccessor: TemporalAccessor, zoneId: ZoneId): Instant = {
val localTime = if (temporalAccessor.query(TemporalQueries.localTime) == null) {
LocalTime.ofNanoOfDay(0)
} else {
LocalTime.from(temporalAccessor)
}
val localDate = LocalDate.from(temporalAccessor)
val localDateTime = LocalDateTime.of(localDate, localTime)
val zonedDateTime = ZonedDateTime.of(localDateTime, zoneId)
Instant.from(zonedDateTime)
}
}

object DateTimeFormatterHelper {
private val cache = CacheBuilder.newBuilder()
.initialCapacity(8)
.maximumSize(128)
.expireAfterAccess(1, TimeUnit.HOURS)
Copy link
Contributor

@cloud-fan cloud-fan Jan 8, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we really need the expire policy?

Copy link
Member

@srowen srowen Jan 8, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agree, I think it has to make a thread to deal with it and it's not worth it. Min size doesn't really matter either.

.build[(String, Locale), DateTimeFormatter]()


protected def buildFormatter(pattern: String, locale: Locale): DateTimeFormatter = {
private def buildFormatter(pattern: String, locale: Locale): DateTimeFormatter = {
new DateTimeFormatterBuilder()
.parseCaseInsensitive()
.appendPattern(pattern)
Expand All @@ -39,15 +63,17 @@ trait DateTimeFormatterHelper {
.withResolverStyle(ResolverStyle.STRICT)
}

protected def toInstantWithZoneId(temporalAccessor: TemporalAccessor, zoneId: ZoneId): Instant = {
val localTime = if (temporalAccessor.query(TemporalQueries.localTime) == null) {
LocalTime.ofNanoOfDay(0)
} else {
LocalTime.from(temporalAccessor)
def getFormatter(pattern: String, locale: Locale): DateTimeFormatter = {
try {
cache.get(
(pattern, locale),
new Callable[DateTimeFormatter]() {
override def call = buildFormatter(pattern, locale)
})
} catch {
// Cache.get() may wrap the original exception.
case e @ (_: UncheckedExecutionException | _: ExecutionError) =>
throw e.getCause
}
val localDate = LocalDate.from(temporalAccessor)
val localDateTime = LocalDateTime.of(localDate, localTime)
val zonedDateTime = ZonedDateTime.of(localDateTime, zoneId)
Instant.from(zonedDateTime)
}
}
2 changes: 1 addition & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/TimestampFormatter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ class Iso8601TimestampFormatter(
timeZone: TimeZone,
locale: Locale) extends TimestampFormatter with DateTimeFormatterHelper {
@transient
private lazy val formatter = buildFormatter(pattern, locale)
private lazy val formatter = DateTimeFormatterHelper.getFormatter(pattern, locale)

private def toInstant(s: String): Instant = {
val temporalAccessor = formatter.parse(s)
Expand Down