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-47415][SQL] Add collation support for Levenshtein expression #46788

Closed
wants to merge 4 commits into from
Closed

[SPARK-47415][SQL] Add collation support for Levenshtein expression #46788

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
0c90de1
Initial commit
uros-db May 29, 2024
7b6f4f1
Merge branch 'apache:master' into levenshtein
uros-db Jun 10, 2024
11008bb
Tests
uros-db Jun 10, 2024
5d4d06a
Update CollationStringExpressionsSuite.scala
uros-db Jun 10, 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 @@ -2240,8 +2240,8 @@ case class Levenshtein(
}

override def inputTypes: Seq[AbstractDataType] = threshold match {
case Some(_) => Seq(StringType, StringType, IntegerType)
case _ => Seq(StringType, StringType)
case Some(_) => Seq(StringTypeAnyCollation, StringTypeAnyCollation, IntegerType)
case _ => Seq(StringTypeAnyCollation, StringTypeAnyCollation)
}

override def children: Seq[Expression] = threshold match {
Expand Down
22 changes: 22 additions & 0 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 @@ -645,6 +645,28 @@ class CollationStringExpressionsSuite
})
}

test("Levenshtein string expression with collation") {
// Supported collations
case class LevenshteinTestCase(
left: String, right: String, collationName: String, threshold: Option[Int], result: Int
)
val testCases = Seq(
LevenshteinTestCase("kitten", "sitTing", "UTF8_BINARY", None, result = 4),
LevenshteinTestCase("kitten", "sitTing", "UTF8_BINARY_LCASE", None, result = 4),
LevenshteinTestCase("kitten", "sitTing", "UNICODE", Some(3), result = -1),
LevenshteinTestCase("kitten", "sitTing", "UNICODE_CI", Some(3), result = -1)
)
testCases.foreach(t => {
withSQLConf(SQLConf.DEFAULT_COLLATION.key -> t.collationName) {
val th = if (t.threshold.isDefined) s", ${t.threshold.get}" else ""
val query = s"select levenshtein('${t.left}', '${t.right}'$th)"
// Result & data type
checkAnswer(sql(query), Row(t.result))
assert(sql(query).schema.fields.head.dataType.sameType(IntegerType))
}
})
}

test("Support Left/Right/Substr with collation") {
case class SubstringTestCase(
method: String,
Expand Down