Skip to content

[SPARK-40308][SQL] Allow non-foldable delimiter arguments to str_to_map function #37763

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
bersprockets wants to merge 3 commits into from
Closed

[SPARK-40308][SQL] Allow non-foldable delimiter arguments to str_to_map function #37763

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7ec631b
change and tests
bersprockets Aug 30, 2022
bbc4f35
Simplify
bersprockets Aug 31, 2022
da92fa0
Review feedback; Remove unused column in test
bersprockets Sep 3, 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
8 changes: 0 additions & 8 deletions ...atalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -547,14 +547,6 @@ case class StringToMap(text: Expression, pairDelim: Expression, keyValueDelim: E

override def dataType: DataType = MapType(StringType, StringType)

override def checkInputDataTypes(): TypeCheckResult = {
if (Seq(pairDelim, keyValueDelim).exists(! _.foldable)) {
TypeCheckResult.TypeCheckFailure(s"$prettyName's delimiters must be foldable.")
} else {
super.checkInputDataTypes()
}
}

private lazy val mapBuilder = new ArrayBasedMapBuilder(StringType, StringType)

override def nullSafeEval(
Expand Down
10 changes: 4 additions & 6 deletions sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ComplexTypeSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,6 +476,10 @@ class ComplexTypeSuite extends SparkFunSuite with ExpressionEvalHelper {
val m5 = Map("a" -> null)
checkEvaluation(new StringToMap(s5), m5)

val s6 = Literal("a=1&b=2&c=3")
val m6 = Map("a" -> "1", "b" -> "2", "c" -> "3")
checkEvaluation(new StringToMap(s6, NonFoldableLiteral("&"), NonFoldableLiteral("=")), m6)

checkExceptionInExpression[RuntimeException](
new StringToMap(Literal("a:1,b:2,a:3")), "Duplicate map key")
withSQLConf(SQLConf.MAP_KEY_DEDUP_POLICY.key -> SQLConf.MapKeyDedupPolicy.LAST_WIN.toString) {
Expand All @@ -492,12 +496,6 @@ class ComplexTypeSuite extends SparkFunSuite with ExpressionEvalHelper {
assert(StringToMap(Literal("a:1,b:2,c:3"), Literal(null), Literal(null))
.checkInputDataTypes().isFailure)
assert(new StringToMap(Literal(null), Literal(null)).checkInputDataTypes().isFailure)

assert(new StringToMap(Literal("a:1_b:2_c:3"), NonFoldableLiteral("_"))
.checkInputDataTypes().isFailure)
assert(
new StringToMap(Literal("a=1_b=2_c=3"), Literal("_"), NonFoldableLiteral("="))
.checkInputDataTypes().isFailure)
}

test("SPARK-22693: CreateNamedStruct should not use global variables") {
Expand Down
30 changes: 30 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -606,6 +606,36 @@ class StringFunctionsSuite extends QueryTest with SharedSparkSession {
Seq(Row(Map("a" -> "1", "b" -> "2", "c" -> "3")))
)

checkAnswer(

@bersprockets bersprockets Sep 1, 2022

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

Not really a test of my change, but it was a missing test (the case where a literal pair delimiter is given but no key/value delimiter is given).

df2.selectExpr("str_to_map(a, ',')"),
Seq(Row(Map("a" -> "1", "b" -> "2", "c" -> "3")))
)

val df3 = Seq(
("a=1&b=2", "&", "="),
("k#2%v#3", "%", "#")
).toDF("str", "delim1", "delim2")

checkAnswer(
df3.selectExpr("str_to_map(str, delim1, delim2)"),
Seq(
Row(Map("a" -> "1", "b" -> "2")),
Row(Map("k" -> "2", "v" -> "3"))
)
)

val df4 = Seq(
("a:1&b:2", "&"),
("k:2%v:3", "%")
).toDF("str", "delim1")

checkAnswer(
df4.selectExpr("str_to_map(str, delim1)"),
Seq(
Row(Map("a" -> "1", "b" -> "2")),
Row(Map("k" -> "2", "v" -> "3"))
)
)
}

test("SPARK-36148: check input data types of regexp_replace") {
Expand Down