Skip to content

[SPARK-38899][SQL]DS V2 supports push down datetime functions #36663

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
chenzhx wants to merge 10 commits into from
Closed

[SPARK-38899][SQL]DS V2 supports push down datetime functions #36663

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
aa2fc5c
[SPARK-38899][SQL]DS V2 supports push down datetime functions
chenzhx May 25, 2022
778adb6
Update code
chenzhx Jun 30, 2022
f87296c
Update code
chenzhx Jul 1, 2022
fb7c63f
Update code
chenzhx Jul 1, 2022
3117c32
Update code
chenzhx Jul 1, 2022
0b13a5e
Update code
chenzhx Jul 2, 2022
0e135cd
Update code
chenzhx Jul 2, 2022
a3cfef1
Update code
chenzhx Jul 5, 2022
ea0e7c2
Update code
chenzhx Jul 5, 2022
2600d7f
Update code
chenzhx Jul 5, 2022
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
Prev Previous commit
Next Next commit
Update code
  • Loading branch information
@chenzhx
chenzhx committed Jul 2, 2022
commit 0b13a5e28d0af2d24a55695c8360bb7ee03995e3
6 changes: 4 additions & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/catalyst/util/V2ExpressionBuilder.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -377,13 +377,15 @@ class V2ExpressionBuilder(e: Expression, isPredicate: Boolean = false) {
generateExpression(child).map(v => new V2Extract("QUARTER", v))
case Year(child) =>
generateExpression(child).map(v => new V2Extract("YEAR", v))
// translate the DayOfWeek function in Spark using ISO standards
// DayOfWeek uses 1 = Sunday, 2 = Monday, ... and ISO standard is Monday=1, ...,
// so we use the formula ((ISO_standard % 7) + 1) to do translation.
case DayOfWeek(child) =>
generateExpression(child).map(v => new GeneralScalarExpression("+",
Array[V2Expression](new GeneralScalarExpression("%",
Array[V2Expression](new V2Extract("DAY_OF_WEEK", v), LiteralValue(7, IntegerType))),
LiteralValue(1, IntegerType))))
// translate the WeekDay function in Spark using ISO standards
// WeekDay uses 0 = Monday, 1 = Tuesday, ... and ISO standard is Monday=1, ...,
// so we use the formula (ISO_standard - 1) to do translation.
case WeekDay(child) =>
generateExpression(child).map(v => new GeneralScalarExpression("-",
Array[V2Expression](new V2Extract("DAY_OF_WEEK", v), LiteralValue(1, IntegerType))))
Expand Down
7 changes: 4 additions & 3 deletions sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,9 @@ package org.apache.spark.sql.jdbc

import java.sql.{Connection, DriverManager}
import java.util.Properties

import scala.util.control.NonFatal

import org.apache.spark.{SparkConf, SparkException}
import org.apache.spark.sql.{AnalysisException, DataFrame, ExplainSuiteHelper, QueryTest, Row}
import org.apache.spark.sql.catalyst.InternalRow
Expand All @@ -29,10 +31,9 @@ import org.apache.spark.sql.connector.{IntegralAverage, StrLen}
import org.apache.spark.sql.connector.catalog.functions.{ScalarFunction, UnboundFunction}
import org.apache.spark.sql.connector.expressions.Expression
import org.apache.spark.sql.connector.expressions.aggregate.{AggregateFunc, UserDefinedAggregateFunc}
import org.apache.spark.sql.execution.SimpleMode
import org.apache.spark.sql.execution.datasources.v2.{DataSourceV2ScanRelation, V1ScanWrapper}
import org.apache.spark.sql.execution.datasources.v2.jdbc.JDBCTableCatalog
import org.apache.spark.sql.functions.{abs, acos, asin, atan, atan2, avg, ceil, coalesce, cos, cosh, cot, count, count_distinct, degrees, exp, floor, lit, log10, not, pow, radians, round, signum, sin, sinh, sqrt, sum, tan, tanh, udf, when, log => logarithm}
import org.apache.spark.sql.functions.{abs, acos, asin, atan, atan2, avg, ceil, coalesce, cos, cosh, cot, count, count_distinct, degrees, exp, floor, lit, log => logarithm, log10, not, pow, radians, round, signum, sin, sinh, sqrt, sum, tan, tanh, udf, when}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SharedSparkSession
import org.apache.spark.sql.types.{DataType, IntegerType, StringType}
Expand Down Expand Up @@ -209,7 +210,7 @@ class JDBCV2Suite extends QueryTest with SharedSparkSession with ExplainSuiteHel
private def checkPushedInfo(df: DataFrame, expectedPlanFragment: String*): Unit = {
df.queryExecution.optimizedPlan.collect {
case _: DataSourceV2ScanRelation =>
checkKeywordsExistsInExplain(df, SimpleMode, expectedPlanFragment: _*)
checkKeywordsExistsInExplain(df, expectedPlanFragment: _*)
}
}

Expand Down