Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
23 commits
Select commit Hold shift + click to select a range
768b3e9
impl map_from_entries
Dec 14, 2025
c68c342
Revert "impl map_from_entries"
Dec 16, 2025
d887555
Merge branch 'apache:main' into main
kazantsev-maksim Dec 16, 2025
231aa90
Merge branch 'apache:main' into main
kazantsev-maksim Dec 17, 2025
9500bbb
Merge branch 'apache:main' into main
kazantsev-maksim Dec 24, 2025
9577481
Merge branch 'apache:main' into main
kazantsev-maksim Dec 28, 2025
3791557
Merge branch 'apache:main' into main
kazantsev-maksim Jan 2, 2026
7c2f082
Merge branch 'apache:main' into main
kazantsev-maksim Jan 3, 2026
609a605
Merge branch 'apache:main' into main
kazantsev-maksim Jan 6, 2026
a151b2c
Merge branch 'apache:main' into main
kazantsev-maksim Jan 7, 2026
ad3e7f5
Merge branch 'apache:main' into main
kazantsev-maksim Jan 10, 2026
ea92e4b
Merge branch 'apache:main' into main
kazantsev-maksim Jan 14, 2026
8dfeca3
Merge branch 'apache:main' into main
kazantsev-maksim Jan 17, 2026
559741e
Merge branch 'apache:main' into main
kazantsev-maksim Jan 20, 2026
ebda14e
Merge branch 'apache:main' into main
kazantsev-maksim Jan 21, 2026
408152e
Merge branch 'apache:main' into main
kazantsev-maksim Jan 23, 2026
d7857b2
Merge branch 'apache:main' into main
kazantsev-maksim Jan 24, 2026
aef41be
Merge branch 'apache:main' into main
kazantsev-maksim Jan 29, 2026
5ac1c58
Merge branch 'apache:main' into main
kazantsev-maksim Jan 30, 2026
9ae8e23
Merge branch 'apache:main' into main
kazantsev-maksim Feb 1, 2026
55aa1fe
Fix empty key processing for map_from_arrays func
Feb 1, 2026
faffcbc
Fix fmt
Feb 2, 2026
d82900a
Fix PR issues
Feb 3, 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
33 changes: 29 additions & 4 deletions spark/src/main/scala/org/apache/comet/serde/maps.scala
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ package org.apache.comet.serde
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.types.{ArrayType, MapType}

import org.apache.comet.serde.QueryPlanSerde.{exprToProtoInternal, optExprWithInfo, scalarFunctionExprToProto, scalarFunctionExprToProtoWithReturnType}
import org.apache.comet.serde.QueryPlanSerde.{createUnaryExpr, exprToProtoInternal, optExprWithInfo, scalarFunctionExprToProto}

object CometMapKeys extends CometExpressionSerde[MapKeys] {

Expand Down Expand Up @@ -84,8 +84,33 @@ object CometMapFromArrays extends CometExpressionSerde[MapFromArrays] {
val keyType = expr.left.dataType.asInstanceOf[ArrayType].elementType
val valueType = expr.right.dataType.asInstanceOf[ArrayType].elementType
val returnType = MapType(keyType = keyType, valueType = valueType)
val mapFromArraysExpr =
scalarFunctionExprToProtoWithReturnType("map", returnType, false, keysExpr, valuesExpr)
optExprWithInfo(mapFromArraysExpr, expr, expr.children: _*)
for {
isNotNullExprProto <- keyIsNotNullExpr(expr, inputs, binding)
mapFromArraysExprProto <- scalarFunctionExprToProto("map", keysExpr, valuesExpr)
nullLiteralExprProto <- exprToProtoInternal(Literal(null, returnType), inputs, binding)
} yield {
val caseWhenExprProto = ExprOuterClass.CaseWhen
.newBuilder()
.addWhen(isNotNullExprProto)
.addThen(mapFromArraysExprProto)
.setElseExpr(nullLiteralExprProto)
.build()
ExprOuterClass.Expr
.newBuilder()
.setCaseWhen(caseWhenExprProto)
.build()
}
}

private def keyIsNotNullExpr(
expr: MapFromArrays,
inputs: Seq[Attribute],
binding: Boolean): Option[ExprOuterClass.Expr] = {
createUnaryExpr(
expr,
expr.left,
inputs,
binding,
(builder, keyExpr) => builder.setIsNotNull(keyExpr))
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,7 @@ INSERT INTO test_map_from_arrays VALUES (array('a', 'b', 'c'), array(1, 2, 3)),
query spark_answer_only
SELECT map_from_arrays(k, v) FROM test_map_from_arrays WHERE k IS NOT NULL

-- Comet bug: map_from_arrays(NULL, NULL) causes native crash "map key cannot be null"
-- https://github.com/apache/datafusion-comet/issues/3327
query ignore(https://github.com/apache/datafusion-comet/issues/3327)
query
SELECT map_from_arrays(k, v) FROM test_map_from_arrays WHERE k IS NULL
Copy link
Member

Choose a reason for hiding this comment

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

Could you also add tests where v is NULL?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I think it will be the same behavior: in the original data, value == null when key == null.

statement
INSERT INTO test_map_from_arrays VALUES (array('a', 'b', 'c'), array(1, 2, 3)), (array(), array()), (NULL, NULL)


-- literal arguments
Expand Down