Skip to content

[SPARK-31885][SQL][3.0] Fix filter push down for old millis timestamps to Parquet #28699

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 2 commits into from
Closed

[SPARK-31885][SQL][3.0] Fix filter push down for old millis timestamps to Parquet #28699

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1da8d92
[SPARK-31885][SQL] Fix filter push down for old millis timestamps to …
MaxGekk Jun 1, 2020
4ba7e05
Fix build failure
MaxGekk Jun 1, 2020
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
27 changes: 13 additions & 14 deletions ...re/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,13 @@ class ParquetFilters(
Binary.fromConstantByteArray(fixedLengthBytes, 0, numBytes)
}

private def timestampToMillis(v: Any): JLong = {
val timestamp = v.asInstanceOf[Timestamp]
val micros = DateTimeUtils.fromJavaTimestamp(timestamp)
val millis = DateTimeUtils.toMillis(micros)
Copy link
Member Author

@MaxGekk MaxGekk Jun 1, 2020

Choose a reason for hiding this comment

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

This line causes the problem.

millis.asInstanceOf[JLong]
}

private val makeEq:
PartialFunction[ParquetSchemaType, (Array[String], Any) => FilterPredicate] = {
case ParquetBooleanType =>
Expand Down Expand Up @@ -184,7 +191,7 @@ class ParquetFilters(
case ParquetTimestampMillisType if pushDownTimestamp =>
(n: Array[String], v: Any) => FilterApi.eq(
longColumn(n),
Option(v).map(_.asInstanceOf[Timestamp].getTime.asInstanceOf[JLong]).orNull)
Option(v).map(timestampToMillis).orNull)

case ParquetSchemaType(DECIMAL, INT32, _, _) if pushDownDecimal =>
(n: Array[String], v: Any) => FilterApi.eq(
Expand Down Expand Up @@ -235,7 +242,7 @@ class ParquetFilters(
case ParquetTimestampMillisType if pushDownTimestamp =>
(n: Array[String], v: Any) => FilterApi.notEq(
longColumn(n),
Option(v).map(_.asInstanceOf[Timestamp].getTime.asInstanceOf[JLong]).orNull)
Option(v).map(timestampToMillis).orNull)

case ParquetSchemaType(DECIMAL, INT32, _, _) if pushDownDecimal =>
(n: Array[String], v: Any) => FilterApi.notEq(
Expand Down Expand Up @@ -277,9 +284,7 @@ class ParquetFilters(
longColumn(n),
DateTimeUtils.fromJavaTimestamp(v.asInstanceOf[Timestamp]).asInstanceOf[JLong])
case ParquetTimestampMillisType if pushDownTimestamp =>
(n: Array[String], v: Any) => FilterApi.lt(
longColumn(n),
v.asInstanceOf[Timestamp].getTime.asInstanceOf[JLong])
(n: Array[String], v: Any) => FilterApi.lt(longColumn(n), timestampToMillis(v))

case ParquetSchemaType(DECIMAL, INT32, _, _) if pushDownDecimal =>
(n: Array[String], v: Any) =>
Expand Down Expand Up @@ -318,9 +323,7 @@ class ParquetFilters(
longColumn(n),
DateTimeUtils.fromJavaTimestamp(v.asInstanceOf[Timestamp]).asInstanceOf[JLong])
case ParquetTimestampMillisType if pushDownTimestamp =>
(n: Array[String], v: Any) => FilterApi.ltEq(
longColumn(n),
v.asInstanceOf[Timestamp].getTime.asInstanceOf[JLong])
(n: Array[String], v: Any) => FilterApi.ltEq(longColumn(n), timestampToMillis(v))

case ParquetSchemaType(DECIMAL, INT32, _, _) if pushDownDecimal =>
(n: Array[String], v: Any) =>
Expand Down Expand Up @@ -359,9 +362,7 @@ class ParquetFilters(
longColumn(n),
DateTimeUtils.fromJavaTimestamp(v.asInstanceOf[Timestamp]).asInstanceOf[JLong])
case ParquetTimestampMillisType if pushDownTimestamp =>
(n: Array[String], v: Any) => FilterApi.gt(
longColumn(n),
v.asInstanceOf[Timestamp].getTime.asInstanceOf[JLong])
(n: Array[String], v: Any) => FilterApi.gt(longColumn(n), timestampToMillis(v))

case ParquetSchemaType(DECIMAL, INT32, _, _) if pushDownDecimal =>
(n: Array[String], v: Any) =>
Expand Down Expand Up @@ -400,9 +401,7 @@ class ParquetFilters(
longColumn(n),
DateTimeUtils.fromJavaTimestamp(v.asInstanceOf[Timestamp]).asInstanceOf[JLong])
case ParquetTimestampMillisType if pushDownTimestamp =>
(n: Array[String], v: Any) => FilterApi.gtEq(
longColumn(n),
v.asInstanceOf[Timestamp].getTime.asInstanceOf[JLong])
(n: Array[String], v: Any) => FilterApi.gtEq(longColumn(n), timestampToMillis(v))

case ParquetSchemaType(DECIMAL, INT32, _, _) if pushDownDecimal =>
(n: Array[String], v: Any) =>
Expand Down
16 changes: 9 additions & 7 deletions ...rc/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -589,19 +589,21 @@ abstract class ParquetFilterSuite extends QueryTest with ParquetTest with Shared

test("filter pushdown - timestamp") {
// spark.sql.parquet.outputTimestampType = TIMESTAMP_MILLIS
val millisData = Seq(Timestamp.valueOf("2018-06-14 08:28:53.123"),
Timestamp.valueOf("2018-06-15 08:28:53.123"),
Timestamp.valueOf("2018-06-16 08:28:53.123"),
Timestamp.valueOf("2018-06-17 08:28:53.123"))
val millisData = Seq(
Timestamp.valueOf("1000-06-14 08:28:53.123"),
Timestamp.valueOf("1582-06-15 08:28:53.001"),
Timestamp.valueOf("1900-06-16 08:28:53.0"),
Timestamp.valueOf("2018-06-17 08:28:53.999"))
withSQLConf(SQLConf.PARQUET_OUTPUT_TIMESTAMP_TYPE.key ->
ParquetOutputTimestampType.TIMESTAMP_MILLIS.toString) {
testTimestampPushdown(millisData)
}

// spark.sql.parquet.outputTimestampType = TIMESTAMP_MICROS
val microsData = Seq(Timestamp.valueOf("2018-06-14 08:28:53.123456"),
Timestamp.valueOf("2018-06-15 08:28:53.123456"),
Timestamp.valueOf("2018-06-16 08:28:53.123456"),
val microsData = Seq(
Timestamp.valueOf("1000-06-14 08:28:53.123456"),
Timestamp.valueOf("1582-06-15 08:28:53.123456"),
Timestamp.valueOf("1900-06-16 08:28:53.123456"),
Timestamp.valueOf("2018-06-17 08:28:53.123456"))
withSQLConf(SQLConf.PARQUET_OUTPUT_TIMESTAMP_TYPE.key ->
ParquetOutputTimestampType.TIMESTAMP_MICROS.toString) {
Expand Down
4 changes: 3 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,9 @@ private[sql] trait ParquetTest extends FileBasedDataSourceTest {
protected def withParquetDataFrame(df: DataFrame, testVectorized: Boolean = true)
(f: DataFrame => Unit): Unit = {
withTempPath { file =>
df.write.format(dataSourceName).save(file.getCanonicalPath)
withSQLConf(SQLConf.LEGACY_PARQUET_REBASE_MODE_IN_WRITE.key -> "CORRECTED") {
df.write.format(dataSourceName).save(file.getCanonicalPath)
}
readFile(file.getCanonicalPath, testVectorized)(f)
}
}
Expand Down