Skip to content

[SPARK-34984][SQL] ANSI intervals formatting in hive results #32087

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-34984][SQL] ANSI intervals formatting in hive results #32087

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
d272cb3
Add tests
MaxGekk Apr 8, 2021
d993e76
Format ANSI intervals in Hive results
MaxGekk Apr 8, 2021
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
7 changes: 6 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,10 +19,11 @@ package org.apache.spark.sql.execution

import java.nio.charset.StandardCharsets
import java.sql.{Date, Timestamp}
import java.time.{Instant, LocalDate, ZoneOffset}
import java.time.{Duration, Instant, LocalDate, Period, ZoneOffset}

import org.apache.spark.sql.Row
import org.apache.spark.sql.catalyst.util.{DateFormatter, DateTimeUtils, TimestampFormatter}
import org.apache.spark.sql.catalyst.util.IntervalUtils.{durationToMicros, periodToMonths, toDayTimeIntervalString, toYearMonthIntervalString}
import org.apache.spark.sql.execution.command.{DescribeCommandBase, ExecutedCommandExec, ShowTablesCommand, ShowViewsCommand}
import org.apache.spark.sql.execution.datasources.v2.{DescribeTableExec, ShowTablesExec}
import org.apache.spark.sql.internal.SQLConf
Expand Down Expand Up @@ -117,6 +118,10 @@ object HiveResult {
struct.toSeq.zip(fields).map { case (v, t) =>
s""""${t.name}":${toHiveString((v, t.dataType), true, formatters)}"""
}.mkString("{", ",", "}")
case (period: Period, YearMonthIntervalType) =>
toYearMonthIntervalString(periodToMonths(period))
case (duration: Duration, DayTimeIntervalType) =>
toDayTimeIntervalString(durationToMicros(duration))
case (other, _: UserDefinedType[_]) => other.toString
}
}
18 changes: 18 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/HiveResultSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,8 @@

package org.apache.spark.sql.execution

import java.time.{Duration, Period}

import org.apache.spark.sql.catalyst.util.DateTimeTestUtils
import org.apache.spark.sql.connector.InMemoryTableCatalog
import org.apache.spark.sql.execution.HiveResult._
Expand Down Expand Up @@ -107,4 +109,20 @@ class HiveResultSuite extends SharedSparkSession {
}
}
}

test("SPARK-34984: year-month interval formatting in hive result") {
val df = Seq(Period.ofYears(-10).minusMonths(1)).toDF("i")
val plan1 = df.queryExecution.executedPlan
assert(hiveResultString(plan1) === Seq("INTERVAL '-10-1' YEAR TO MONTH"))
val plan2 = df.selectExpr("array(i)").queryExecution.executedPlan
assert(hiveResultString(plan2) === Seq("[INTERVAL '-10-1' YEAR TO MONTH]"))
}

test("SPARK-34984: day-time interval formatting in hive result") {
val df = Seq(Duration.ofDays(5).plusMillis(10)).toDF("i")
val plan1 = df.queryExecution.executedPlan
assert(hiveResultString(plan1) === Seq("INTERVAL '5 00:00:00.01' DAY TO SECOND"))
val plan2 = df.selectExpr("array(i)").queryExecution.executedPlan
assert(hiveResultString(plan2) === Seq("[INTERVAL '5 00:00:00.01' DAY TO SECOND]"))
}
}