Skip to content

GH-41011: [C++][Compute] Fix the issue that comparison function could not handle decimal arguments with different scales#47459

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

Merged
zanmato1984 merged 4 commits into from
Sep 4, 2025
Merged

GH-41011: [C++][Compute] Fix the issue that comparison function could not handle decimal arguments with different scales #47459

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
62eab1d
Fix the issue that comparison function could not handle decimal argum…
zanmato1984 Aug 29, 2025
d3aee89
Merge remote-tracking branch 'apache/main' into fix/gh-41011
zanmato1984 Sep 3, 2025
f2c4c91
Update cpp/src/arrow/compute/expression_test.cc
zanmato1984 Sep 3, 2025
530b929
Address comment: add cases for different precisions same scale
zanmato1984 Sep 3, 2025
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
81 changes: 81 additions & 0 deletions cpp/src/arrow/compute/expression_test.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -740,6 +740,11 @@ TEST(Expression, BindWithDecimalDivision) {
}

TEST(Expression, BindWithImplicitCasts) {
auto exciting_schema = schema(

@zanmato1984zanmato1984Sep 3, 2025

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

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

Get excited one more time! @pitrou

@pitroupitrouSep 3, 2025

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

My head spins.

{field("i64", int64()), field("dec128_3_2", decimal128(3, 2)),
field("dec128_4_2", decimal128(4, 2)), field("dec128_5_3", decimal128(5, 3)),
field("dec256_3_2", decimal256(3, 2)), field("dec256_4_2", decimal256(4, 2)),
field("dec256_5_3", decimal256(5, 3))});
for (auto cmp : {equal, not_equal, less, less_equal, greater, greater_equal}) {
// cast arguments to common numeric type
ExpectBindsTo(cmp(field_ref("i64"), field_ref("i32")),
Expand DownExpand Up@@ -800,6 +805,82 @@ TEST(Expression, BindWithImplicitCasts) {
ExpectBindsTo(cmp(field_ref("i32"), literal(std::make_shared<DoubleScalar>(10.0))),
cmp(cast(field_ref("i32"), float32()),
literal(std::make_shared<FloatScalar>(10.0f))));

// decimal int
ExpectBindsTo(cmp(field_ref("dec128_3_2"), field_ref("i64")),
cmp(field_ref("dec128_3_2"), cast(field_ref("i64"), decimal128(21, 2))),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(cmp(field_ref("i64"), field_ref("dec128_3_2")),
cmp(cast(field_ref("i64"), decimal128(21, 2)), field_ref("dec128_3_2")),
/*bound_out=*/nullptr, *exciting_schema);

// decimal decimal with different widths different precisions but same scale
ExpectBindsTo(
cmp(field_ref("dec128_3_2"), field_ref("dec256_4_2")),
cmp(cast(field_ref("dec128_3_2"), decimal256(3, 2)), field_ref("dec256_4_2")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(
cmp(field_ref("dec256_4_2"), field_ref("dec128_3_2")),
cmp(field_ref("dec256_4_2"), cast(field_ref("dec128_3_2"), decimal256(3, 2))),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(
cmp(field_ref("dec128_4_2"), field_ref("dec256_3_2")),
cmp(cast(field_ref("dec128_4_2"), decimal256(4, 2)), field_ref("dec256_3_2")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(
cmp(field_ref("dec256_3_2"), field_ref("dec128_4_2")),
cmp(field_ref("dec256_3_2"), cast(field_ref("dec128_4_2"), decimal256(4, 2))),
/*bound_out=*/nullptr, *exciting_schema);

// decimal decimal with different widths different scales
ExpectBindsTo(
cmp(field_ref("dec128_3_2"), field_ref("dec256_5_3")),
cmp(cast(field_ref("dec128_3_2"), decimal256(4, 3)), field_ref("dec256_5_3")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(
cmp(field_ref("dec256_5_3"), field_ref("dec128_3_2")),
cmp(field_ref("dec256_5_3"), cast(field_ref("dec128_3_2"), decimal256(4, 3))),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(cmp(field_ref("dec128_5_3"), field_ref("dec256_3_2")),
cmp(cast(field_ref("dec128_5_3"), decimal256(5, 3)),
cast(field_ref("dec256_3_2"), decimal256(4, 3))),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(cmp(field_ref("dec256_3_2"), field_ref("dec128_5_3")),
cmp(cast(field_ref("dec256_3_2"), decimal256(4, 3)),
cast(field_ref("dec128_5_3"), decimal256(5, 3))),
/*bound_out=*/nullptr, *exciting_schema);

// decimal decimal with same width same precision but different scales (no cast)
ExpectBindsTo(cmp(field_ref("dec128_3_2"), field_ref("dec128_4_2")),
cmp(field_ref("dec128_3_2"), field_ref("dec128_4_2")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(cmp(field_ref("dec128_4_2"), field_ref("dec128_3_2")),
cmp(field_ref("dec128_4_2"), field_ref("dec128_3_2")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(cmp(field_ref("dec256_3_2"), field_ref("dec256_4_2")),
cmp(field_ref("dec256_3_2"), field_ref("dec256_4_2")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(cmp(field_ref("dec256_4_2"), field_ref("dec256_3_2")),
cmp(field_ref("dec256_4_2"), field_ref("dec256_3_2")),
/*bound_out=*/nullptr, *exciting_schema);

// decimal decimal with same width but different scales
ExpectBindsTo(
cmp(field_ref("dec128_3_2"), field_ref("dec128_5_3")),
cmp(cast(field_ref("dec128_3_2"), decimal128(4, 3)), field_ref("dec128_5_3")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(
cmp(field_ref("dec128_5_3"), field_ref("dec128_3_2")),
cmp(field_ref("dec128_5_3"), cast(field_ref("dec128_3_2"), decimal128(4, 3))),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(
cmp(field_ref("dec256_3_2"), field_ref("dec256_5_3")),
cmp(cast(field_ref("dec256_3_2"), decimal256(4, 3)), field_ref("dec256_5_3")),
/*bound_out=*/nullptr, *exciting_schema);
ExpectBindsTo(
cmp(field_ref("dec256_5_3"), field_ref("dec256_3_2")),
cmp(field_ref("dec256_5_3"), cast(field_ref("dec256_3_2"), decimal256(4, 3))),
/*bound_out=*/nullptr, *exciting_schema);
}

compute::SetLookupOptions in_a{ArrayFromJSON(utf8(), R"(["a"])")};
Expand Down
4 changes: 2 additions & 2 deletions cpp/src/arrow/compute/kernels/scalar_compare.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -436,8 +436,8 @@ std::shared_ptr<ScalarFunction> MakeCompareFunction(std::string name, FunctionDo

for (const auto id : {Type::DECIMAL128, Type::DECIMAL256}) {
auto exec = GenerateDecimal<applicator::ScalarBinaryEqualTypes, BooleanType, Op>(id);
DCHECK_OK(
func->AddKernel({InputType(id), InputType(id)}, boolean(), std::move(exec)));
DCHECK_OK(func->AddKernel({InputType(id), InputType(id)}, boolean(), std::move(exec),

@zanmato1984zanmato1984Aug 29, 2025•
edited
Loading

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

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

Yep, the fix is as simple as this. Thanks to #47297.

/*init=*/nullptr, DecimalsHaveSameScale()));
}

{
Expand Down
Loading