-
Notifications
You must be signed in to change notification settings - Fork 232
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.
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
Port whole parsePartitions method from Spark3.3 to Gpu side #6048
Merged
tgravescs
merged 6 commits into
NVIDIA:branch-22.08
from
wjxiz1992:port-parse-partitions-from-spark330
Jul 26, 2022
Merged
Changes from all commits
Commits
Show all changes
6 commits
Select commit
Hold shift + click to select a range
1cabb07
port whole parsePartitions method from Spark3.3 to Gpu side
wjxiz1992 dc53319
apply to other Spark versions
wjxiz1992 e041304
reduce duplicated code
wjxiz1992 8bbf530
add shim
wjxiz1992 1a4e9fb
add copyrights
wjxiz1992 dfef07b
refine shim and comments
wjxiz1992 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
31 changes: 31 additions & 0 deletions
31
...main/311until320-all/scala/org/apache/spark/sql/types/shims/PartitionValueCastShims.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,31 @@ | ||
/* | ||
* Copyright (c) 2022, NVIDIA CORPORATION. | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.types.shims | ||
|
||
import java.time.ZoneId | ||
|
||
import org.apache.spark.sql.types.DataType | ||
|
||
object PartitionValueCastShims { | ||
// AnyTimestamp, TimestampNTZTtpe and AnsiIntervalType types are not defined before Spark 3.2.0 | ||
// return false between 311 until 320 | ||
def isSupportedType(dt: DataType): Boolean = false | ||
|
||
def castTo(desiredType: DataType, value: String, zoneId: ZoneId): Any = { | ||
throw new IllegalArgumentException(s"Unexpected type $desiredType") | ||
} | ||
} |
44 changes: 44 additions & 0 deletions
44
...main/320until330-all/scala/org/apache/spark/sql/types/shims/PartitionValueCastShims.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,44 @@ | ||
/* | ||
* Copyright (c) 2022, NVIDIA CORPORATION. | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.types.shims | ||
|
||
import java.time.ZoneId | ||
|
||
import scala.util.Try | ||
|
||
import org.apache.spark.sql.catalyst.catalog.ExternalCatalogUtils.unescapePathName | ||
import org.apache.spark.sql.catalyst.expressions.{Cast, Literal} | ||
import org.apache.spark.sql.types.{AnyTimestampType, DataType, DateType} | ||
|
||
object PartitionValueCastShims { | ||
def isSupportedType(dt: DataType): Boolean = dt match { | ||
// Timestamp types | ||
case dt if AnyTimestampType.acceptsType(dt) => true | ||
case _ => false | ||
} | ||
|
||
// Only for TimestampType and TimestampNTZType | ||
def castTo(desiredType: DataType, value: String, zoneId: ZoneId): Any = desiredType match { | ||
// Copied from org/apache/spark/sql/execution/datasources/PartitionUtils.scala | ||
case dt if AnyTimestampType.acceptsType(desiredType) => | ||
Try { | ||
Cast(Literal(unescapePathName(value)), dt, Some(zoneId.getId)).eval() | ||
}.getOrElse { | ||
Cast(Cast(Literal(value), DateType, Some(zoneId.getId)), dt).eval() | ||
} | ||
} | ||
} |
38 changes: 38 additions & 0 deletions
38
...plugin/src/main/330+/scala/org/apache/spark/sql/types/shims/PartitionValueCastShims.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,38 @@ | ||
/* | ||
* Copyright (c) 2022, NVIDIA CORPORATION. | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.types.shims | ||
|
||
import java.time.ZoneId | ||
|
||
import org.apache.spark.sql.catalyst.catalog.ExternalCatalogUtils.unescapePathName | ||
import org.apache.spark.sql.catalyst.expressions.{Cast, Literal} | ||
import org.apache.spark.sql.types.{AnsiIntervalType, DataType} | ||
|
||
object PartitionValueCastShims { | ||
def isSupportedType(dt: DataType): Boolean = dt match { | ||
// AnsiIntervalType | ||
case it: AnsiIntervalType => true | ||
case _ => false | ||
} | ||
|
||
// Only for AnsiIntervalType | ||
def castTo(desiredType: DataType, value: String, zoneId: ZoneId): Any = desiredType match { | ||
// Copied from org/apache/spark/sql/execution/datasources/PartitionUtils.scala | ||
case it: AnsiIntervalType => | ||
Cast(Literal(unescapePathName(value)), it).eval() | ||
} | ||
} |
222 changes: 222 additions & 0 deletions
222
sql-plugin/src/main/scala/org/apache/spark/sql/catalyst/util/rapids/DateFormatter.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,222 @@ | ||
/* | ||
* Copyright (c) 2022, NVIDIA CORPORATION. | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package org.apache.spark.sql.catalyst.util.rapids | ||
|
||
import java.text.SimpleDateFormat | ||
import java.time.LocalDate | ||
import java.util.{Date, Locale} | ||
|
||
import org.apache.commons.lang3.time.FastDateFormat | ||
|
||
import org.apache.spark.sql.catalyst.util.{DateTimeFormatterHelper, DateTimeUtils, LegacyDateFormats} | ||
import org.apache.spark.sql.catalyst.util.DateTimeUtils._ | ||
import org.apache.spark.sql.internal.SQLConf | ||
import org.apache.spark.sql.internal.SQLConf.LegacyBehaviorPolicy._ | ||
|
||
// Copied from org/apache/spark/sql/catalyst/util/DateFormatter | ||
// for https://github.com/NVIDIA/spark-rapids/issues/6026 | ||
// It can be removed when Spark3.3 is the least supported Spark version | ||
sealed trait DateFormatter extends Serializable { | ||
def parse(s: String): Int // returns days since epoch | ||
|
||
def format(days: Int): String | ||
def format(date: Date): String | ||
def format(localDate: LocalDate): String | ||
|
||
def validatePatternString(): Unit | ||
} | ||
|
||
class Iso8601DateFormatter( | ||
pattern: String, | ||
locale: Locale, | ||
legacyFormat: LegacyDateFormats.LegacyDateFormat, | ||
isParsing: Boolean) | ||
extends DateFormatter with DateTimeFormatterHelper { | ||
|
||
@transient | ||
private lazy val formatter = getOrCreateFormatter(pattern, locale, isParsing) | ||
|
||
@transient | ||
protected lazy val legacyFormatter = | ||
DateFormatter.getLegacyFormatter(pattern, locale, legacyFormat) | ||
|
||
override def parse(s: String): Int = { | ||
try { | ||
val localDate = toLocalDate(formatter.parse(s)) | ||
localDateToDays(localDate) | ||
} catch checkParsedDiff(s, legacyFormatter.parse) | ||
} | ||
|
||
override def format(localDate: LocalDate): String = { | ||
try { | ||
localDate.format(formatter) | ||
} catch checkFormattedDiff(toJavaDate(localDateToDays(localDate)), | ||
(d: Date) => format(d)) | ||
} | ||
|
||
override def format(days: Int): String = { | ||
format(LocalDate.ofEpochDay(days)) | ||
} | ||
|
||
override def format(date: Date): String = { | ||
legacyFormatter.format(date) | ||
} | ||
|
||
override def validatePatternString(): Unit = { | ||
try { | ||
formatter | ||
} catch checkLegacyFormatter(pattern, legacyFormatter.validatePatternString) | ||
() | ||
} | ||
} | ||
|
||
/** | ||
* The formatter for dates which doesn't require users to specify a pattern. While formatting, | ||
* it uses the default pattern [[DateFormatter.defaultPattern]]. In parsing, it follows the CAST | ||
* logic in conversion of strings to Catalyst's DateType. | ||
* | ||
* @param locale The locale overrides the system locale and is used in formatting. | ||
* @param legacyFormat Defines the formatter used for legacy dates. | ||
* @param isParsing Whether the formatter is used for parsing (`true`) or for formatting (`false`). | ||
*/ | ||
class DefaultDateFormatter( | ||
locale: Locale, | ||
legacyFormat: LegacyDateFormats.LegacyDateFormat, | ||
isParsing: Boolean) | ||
extends Iso8601DateFormatter(DateFormatter.defaultPattern, locale, legacyFormat, isParsing) { | ||
|
||
} | ||
|
||
trait LegacyDateFormatter extends DateFormatter { | ||
def parseToDate(s: String): Date | ||
|
||
override def parse(s: String): Int = { | ||
fromJavaDate(new java.sql.Date(parseToDate(s).getTime)) | ||
} | ||
|
||
override def format(days: Int): String = { | ||
format(DateTimeUtils.toJavaDate(days)) | ||
} | ||
|
||
override def format(localDate: LocalDate): String = { | ||
format(localDateToDays(localDate)) | ||
} | ||
} | ||
|
||
/** | ||
* The legacy formatter is based on Apache Commons FastDateFormat. The formatter uses the default | ||
* JVM time zone intentionally for compatibility with Spark 2.4 and earlier versions. | ||
* | ||
* Note: Using of the default JVM time zone makes the formatter compatible with the legacy | ||
* `DateTimeUtils` methods `toJavaDate` and `fromJavaDate` that are based on the default | ||
* JVM time zone too. | ||
* | ||
* @param pattern `java.text.SimpleDateFormat` compatible pattern. | ||
* @param locale The locale overrides the system locale and is used in parsing/formatting. | ||
*/ | ||
class LegacyFastDateFormatter(pattern: String, locale: Locale) extends LegacyDateFormatter { | ||
@transient | ||
private lazy val fdf = FastDateFormat.getInstance(pattern, locale) | ||
override def parseToDate(s: String): Date = fdf.parse(s) | ||
override def format(d: Date): String = fdf.format(d) | ||
override def validatePatternString(): Unit = fdf | ||
} | ||
|
||
// scalastyle:off line.size.limit | ||
/** | ||
* The legacy formatter is based on `java.text.SimpleDateFormat`. The formatter uses the default | ||
* JVM time zone intentionally for compatibility with Spark 2.4 and earlier versions. | ||
* | ||
* Note: Using of the default JVM time zone makes the formatter compatible with the legacy | ||
* `DateTimeUtils` methods `toJavaDate` and `fromJavaDate` that are based on the default | ||
* JVM time zone too. | ||
* | ||
* @param pattern The pattern describing the date and time format. | ||
* See <a href="https://docs.oracle.com/javase/7/docs/api/java/text/SimpleDateFormat.html"> | ||
* Date and Time Patterns</a> | ||
* @param locale The locale whose date format symbols should be used. It overrides the system | ||
* locale in parsing/formatting. | ||
*/ | ||
// scalastyle:on line.size.limit | ||
class LegacySimpleDateFormatter(pattern: String, locale: Locale) extends LegacyDateFormatter { | ||
@transient | ||
private lazy val sdf = new SimpleDateFormat(pattern, locale) | ||
override def parseToDate(s: String): Date = sdf.parse(s) | ||
override def format(d: Date): String = sdf.format(d) | ||
override def validatePatternString(): Unit = sdf | ||
|
||
} | ||
|
||
object DateFormatter { | ||
import LegacyDateFormats._ | ||
|
||
val defaultLocale: Locale = Locale.US | ||
|
||
val defaultPattern: String = "yyyy-MM-dd" | ||
|
||
private def getFormatter( | ||
format: Option[String], | ||
locale: Locale = defaultLocale, | ||
legacyFormat: LegacyDateFormat = LENIENT_SIMPLE_DATE_FORMAT, | ||
isParsing: Boolean): DateFormatter = { | ||
if (SQLConf.get.legacyTimeParserPolicy == LEGACY) { | ||
getLegacyFormatter(format.getOrElse(defaultPattern), locale, legacyFormat) | ||
} else { | ||
val df = format | ||
.map(new Iso8601DateFormatter(_, locale, legacyFormat, isParsing)) | ||
.getOrElse(new DefaultDateFormatter(locale, legacyFormat, isParsing)) | ||
df.validatePatternString() | ||
df | ||
} | ||
} | ||
|
||
def getLegacyFormatter( | ||
pattern: String, | ||
locale: Locale, | ||
legacyFormat: LegacyDateFormat): DateFormatter = { | ||
legacyFormat match { | ||
case FAST_DATE_FORMAT => | ||
new LegacyFastDateFormatter(pattern, locale) | ||
case SIMPLE_DATE_FORMAT | LENIENT_SIMPLE_DATE_FORMAT => | ||
new LegacySimpleDateFormatter(pattern, locale) | ||
} | ||
} | ||
|
||
def apply( | ||
format: Option[String], | ||
locale: Locale, | ||
legacyFormat: LegacyDateFormat, | ||
isParsing: Boolean): DateFormatter = { | ||
getFormatter(format, locale, legacyFormat, isParsing) | ||
} | ||
|
||
def apply( | ||
format: String, | ||
locale: Locale, | ||
legacyFormat: LegacyDateFormat, | ||
isParsing: Boolean): DateFormatter = { | ||
getFormatter(Some(format), locale, legacyFormat, isParsing) | ||
} | ||
|
||
def apply(format: String, isParsing: Boolean = false): DateFormatter = { | ||
getFormatter(Some(format), isParsing = isParsing) | ||
} | ||
|
||
def apply(): DateFormatter = { | ||
getFormatter(None, isParsing = false) | ||
} | ||
} |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why doesn't the 330 shim have the AnyTimestampType checks?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
https://github.com/apache/spark/blob/master/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala