Skip to content

[SPARK-58931][SQL] Reject negative randstr length during analysis #58200

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
uros-b wants to merge 3 commits into from
Closed

[SPARK-58931][SQL] Reject negative randstr length during analysis #58200

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dfdc052
Initial commit
uros-b Aug 21, 2026
b46f09b
Address review
uros-b Aug 24, 2026
6428246
Document non-negative length in randstr description
uros-b Aug 24, 2026
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
14 changes: 13 additions & 1 deletion ...catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/randomExpressions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ import org.apache.spark.SparkException
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.analysis.{TypeCheckResult, UnresolvedSeed}
import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.DataTypeMismatch
import org.apache.spark.sql.catalyst.expressions.ExpectsInputTypes.{toSQLExpr, toSQLId}
import org.apache.spark.sql.catalyst.expressions.ExpectsInputTypes.{toSQLExpr, toSQLId, toSQLValue}
import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, CodeGenerator, ExprCode, FalseLiteral}
import org.apache.spark.sql.catalyst.expressions.codegen.Block._
import org.apache.spark.sql.catalyst.trees.{BinaryLike, TernaryLike, UnaryLike}
Expand Down Expand Up @@ -425,6 +425,18 @@ case class RandStr(
"inputExpr" -> toSQLExpr(expr)))
}
}
if (result == TypeCheckResult.TypeCheckSuccess) {
val lengthValue = length.eval()
// randstr(NULL, 0) is valid (treated as 0), so only reject a negative length.
if (lengthValue != null && lengthValue.asInstanceOf[Int] < 0) {
Comment thread
uros-b marked this conversation as resolved.
result = DataTypeMismatch(
errorSubClass = "VALUE_OUT_OF_RANGE",
messageParameters = Map(
"exprName" -> toSQLId("length"),
"valueRange" -> s"[0, ${Int.MaxValue}]",
"currentValue" -> toSQLValue(lengthValue, IntegerType)))
}
}
result
}

Expand Down
19 changes: 18 additions & 1 deletion sql/core/src/test/resources/sql-tests/analyzer-results/random.sql.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -709,7 +709,24 @@ org.apache.spark.sql.AnalysisException
-- !query
SELECT randstr(-1, 0) AS result
-- !query analysis
[Analyzer test output redacted due to nondeterminism]
org.apache.spark.sql.catalyst.ExtendedAnalysisException
{
"errorClass" : "DATATYPE_MISMATCH.VALUE_OUT_OF_RANGE",
"sqlState" : "42K09",
"messageParameters" : {
"currentValue" : "-1",
"exprName" : "`length`",
"sqlExpr" : "\"randstr(-1, 0)\"",
"valueRange" : "[0, 2147483647]"
},
"queryContext" : [ {
"objectType" : "",
"objectName" : "",
"startIndex" : 8,
"stopIndex" : 21,
"fragment" : "randstr(-1, 0)"
} ]
}


-- !query
Expand Down
22 changes: 15 additions & 7 deletions sql/core/src/test/resources/sql-tests/results/random.sql.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -857,15 +857,23 @@ SELECT randstr(-1, 0) AS result
-- !query schema
struct<>
-- !query output
org.apache.spark.SparkRuntimeException
org.apache.spark.sql.catalyst.ExtendedAnalysisException
{
"errorClass" : "INVALID_PARAMETER_VALUE.LENGTH",
"sqlState" : "22023",
"errorClass" : "DATATYPE_MISMATCH.VALUE_OUT_OF_RANGE",
"sqlState" : "42K09",
"messageParameters" : {
"functionName" : "`randstr`",
"length" : "-1",
"parameter" : "`length`"
}
"currentValue" : "-1",
"exprName" : "`length`",
"sqlExpr" : "\"randstr(-1, 0)\"",
"valueRange" : "[0, 2147483647]"
},
"queryContext" : [ {
"objectType" : "",
"objectName" : "",
"startIndex" : 8,
"stopIndex" : 21,
"fragment" : "randstr(-1, 0)"
} ]
}


Expand Down
17 changes: 17 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/DataFrameFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -499,6 +499,23 @@ class DataFrameFunctionsSuite extends SharedSparkSession {
callSitePattern = "",
startIndex = 0,
stopIndex = 0))
expr = randstr(lit(-1), lit(0))
checkError(
intercept[AnalysisException](df.select(expr)),
condition = "DATATYPE_MISMATCH.VALUE_OUT_OF_RANGE",
parameters = Map(
"sqlExpr" -> "\"randstr(-1, 0)\"",
"exprName" -> "`length`",
"valueRange" -> "[0, 2147483647]",
"currentValue" -> "-1"),
context = ExpectedContext(
contextType = QueryContextType.DataFrame,
fragment = "randstr",
objectType = "",
objectName = "",
callSitePattern = "",
startIndex = 0,
stopIndex = 0))
}

test("uniform function") {
Expand Down