Skip to content

GH-51231: [C++][Acero] Keep input nullability information for direct field projections #51691

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

Open
FadyYosry77 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

GH-51231: [C++][Acero] Keep input nullability information for direct field projections #51691

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
24 changes: 24 additions & 0 deletions cpp/src/arrow/acero/plan_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -757,6 +757,30 @@ TEST(ExecPlanExecution, DeclarationToSchema) {
AssertSchemaEqual(expected_out_schema, actual_out_schema);
}

TEST(ExecPlanExecution, ProjectPreservesDirectFieldNullability) {
auto input_schema = schema({field("r", int64(), false), field("n", int64(), true)});
Declaration source(
"exec_batch_source",
ExecBatchSourceNodeOptions(input_schema, std::vector<compute::ExecBatch>{}));

auto direct = Declaration::Sequence(
{source,
{"project", ProjectNodeOptions({field_ref("r"), field_ref("n")}, {"r", "n"})}});
ASSERT_OK_AND_ASSIGN(auto direct_schema, DeclarationToSchema(direct));
AssertSchemaEqual(input_schema, direct_schema);

auto reordered = Declaration::Sequence(
{source,
{"project",
ProjectNodeOptions({field_ref("n"), field_ref("r"),
call("add", {field_ref("r"), literal(int64_t{1})})},
{"n", "renamed", "computed"})}});
ASSERT_OK_AND_ASSIGN(auto reordered_schema, DeclarationToSchema(reordered));
AssertSchemaEqual(schema({field("n", int64(), true), field("renamed", int64(), false),
field("computed", int64(), true)}),
reordered_schema);
}

TEST(ExecPlanExecution, DeclarationToReader) {
auto basic_data = MakeBasicBatches();
auto plan = Declaration::Sequence(
Expand Down
16 changes: 13 additions & 3 deletions cpp/src/arrow/acero/project_node.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,14 +67,24 @@ class ProjectNode : public MapNode {
" doesn't match size of expressions " +
std::to_string(exprs.size())));
}
const auto& input_schema = *inputs[0]->output_schema();
FieldVector fields(exprs.size());
int i = 0;
for (auto& expr : exprs) {
if (!expr.IsBound()) {
ARROW_ASSIGN_OR_RAISE(expr, expr.Bind(*inputs[0]->output_schema(),
plan->query_context()->exec_context()));
ARROW_ASSIGN_OR_RAISE(
expr, expr.Bind(input_schema, plan->query_context()->exec_context()));
}
fields[i] = field(std::move(names[i]), expr.type()->GetSharedPtr());
bool nullable = true;
if (const auto* parameter = expr.parameter()) {
if (parameter->indices.size() == 1) {
int index = parameter->indices[0];
if (index >= 0 && index < input_schema.num_fields()) {
nullable = input_schema.field(index)->nullable();
}
}
}
fields[i] = field(std::move(names[i]), expr.type()->GetSharedPtr(), nullable);
++i;
}
return plan->EmplaceNode<ProjectNode>(plan, std::move(inputs),
Expand Down
Loading