Skip to content
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

Jump to bottom

[SPARK-47357][SQL] Add support for Upper, Lower, InitCap (all collations) #46008

Closed
wants to merge 4 commits into from
Closed

[SPARK-47357][SQL] Add support for Upper, Lower, InitCap (all collations) #46008

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
43a738f
Add support for Upper, Lower, InitCap
mihailom-db Apr 11, 2024
41f1f6b
Merge remote-tracking branch 'upstream/master' into SPARK-47357
mihailom-db Apr 12, 2024
7069f53
Fix imports
mihailom-db Apr 12, 2024
9f1f686
Refactor tests
mihailom-db Apr 15, 2024
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
4 changes: 2 additions & 2 deletions ...catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1810,8 +1810,8 @@ case class FormatString(children: Expression*) extends Expression with ImplicitC
case class InitCap(child: Expression)
extends UnaryExpression with ImplicitCastInputTypes with NullIntolerant {

override def inputTypes: Seq[DataType] = Seq(StringType)
override def dataType: DataType = StringType
override def inputTypes: Seq[AbstractDataType] = Seq(StringTypeAnyCollation)
override def dataType: DataType = child.dataType

override def nullSafeEval(string: Any): Any = {
// scalastyle:off caselocale
Expand Down
55 changes: 52 additions & 3 deletions sql/core/src/test/scala/org/apache/spark/sql/CollationStringExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,15 +20,13 @@ package org.apache.spark.sql
import scala.collection.immutable.Seq

import org.apache.spark.SparkConf
import org.apache.spark.sql.catalyst.expressions.ExpressionEvalHelper
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SharedSparkSession
import org.apache.spark.sql.types.{BooleanType, StringType}

class CollationStringExpressionsSuite
extends QueryTest
with SharedSparkSession
with ExpressionEvalHelper {
with SharedSparkSession {

test("Support ConcatWs string expression with collation") {
// Supported collations
Expand Down Expand Up @@ -163,6 +161,57 @@ class CollationStringExpressionsSuite
})
}

test("SPARK-47357: Support Upper string expression with collation") {
// Supported collations
case class UpperTestCase[R](s: String, c: String, result: R)
val testCases = Seq(
UpperTestCase("aBc", "UTF8_BINARY", "ABC"),
UpperTestCase("aBc", "UTF8_BINARY_LCASE", "ABC"),
UpperTestCase("aBc", "UNICODE", "ABC"),
UpperTestCase("aBc", "UNICODE_CI", "ABC")
)
testCases.foreach(t => {
val query = s"SELECT upper(collate('${t.s}', '${t.c}'))"
// Result & data type
checkAnswer(sql(query), Row(t.result))
assert(sql(query).schema.fields.head.dataType.sameType(StringType(t.c)))
})
}

test("SPARK-47357: Support Lower string expression with collation") {
// Supported collations
case class LowerTestCase[R](s: String, c: String, result: R)
val testCases = Seq(
LowerTestCase("aBc", "UTF8_BINARY", "abc"),
LowerTestCase("aBc", "UTF8_BINARY_LCASE", "abc"),
LowerTestCase("aBc", "UNICODE", "abc"),
LowerTestCase("aBc", "UNICODE_CI", "abc")
)
testCases.foreach(t => {
val query = s"SELECT lower(collate('${t.s}', '${t.c}'))"
// Result & data type
checkAnswer(sql(query), Row(t.result))
assert(sql(query).schema.fields.head.dataType.sameType(StringType(t.c)))
})
}

test("SPARK-47357: Support InitCap string expression with collation") {
// Supported collations
case class InitCapTestCase[R](s: String, c: String, result: R)
val testCases = Seq(
InitCapTestCase("aBc ABc", "UTF8_BINARY", "Abc Abc"),
InitCapTestCase("aBc ABc", "UTF8_BINARY_LCASE", "Abc Abc"),
InitCapTestCase("aBc ABc", "UNICODE", "Abc Abc"),
InitCapTestCase("aBc ABc", "UNICODE_CI", "Abc Abc")
)
testCases.foreach(t => {
val query = s"SELECT initcap(collate('${t.s}', '${t.c}'))"
// Result & data type
checkAnswer(sql(query), Row(t.result))
assert(sql(query).schema.fields.head.dataType.sameType(StringType(t.c)))
})
}

// TODO: Add more tests for other string expressions

}
Expand Down