Skip to content

GH-51210: [C++] Initialize output_ on empty select_k inputs #51212

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

GH-51210: [C++] Initialize output_ on empty select_k inputs #51212

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
34 changes: 34 additions & 0 deletions cpp/src/arrow/compute/kernels/select_k_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -415,6 +415,21 @@ TYPED_TEST(TestSelectKWithChunkedArrayTyped, RandomValuesWithSlices) {
}
}

TEST_F(TestSelectKWithChunkedArray, EmptyChunkedArray) {
auto chunked_array = std::make_shared<ChunkedArray>(ArrayVector{}, uint8());
ASSERT_EQ(chunked_array->num_chunks(), 0);
ASSERT_EQ(chunked_array->length(), 0);

for (const auto& options :
{SelectKOptions::TopKDefault(3), SelectKOptions::BottomKDefault(3),
SelectKOptions::TopKDefault(0)}) {
ASSERT_OK_AND_ASSIGN(auto indices, SelectKUnstable(Datum(*chunked_array), options));
ASSERT_NE(indices, nullptr);
ValidateOutput(*indices);
ASSERT_EQ(indices->length(), 0);
}
}

TEST_F(TestSelectKWithChunkedArray, PartialSelectKNull) {
auto chunked_array = std::vector<std::string>{
"[null, 1]",
Expand Down Expand Up @@ -1103,6 +1118,25 @@ struct TestSelectKWithTable : public ::testing::Test {
}
};

TEST_F(TestSelectKWithTable, EmptyTable) {
auto schema = ::arrow::schema({
{field("a", uint8())},
{field("b", uint32())},
});
std::vector<std::string> input = {R"([])"};
auto table = TableFromJSON(schema, input);
ASSERT_EQ(table->num_rows(), 0);

for (const auto& options :
{SelectKOptions::TopKDefault(3, {"a"}), SelectKOptions::BottomKDefault(3, {"a"}),
SelectKOptions::TopKDefault(0, {"a"})}) {
ASSERT_OK_AND_ASSIGN(auto indices, SelectKUnstable(Datum(*table), options));
ASSERT_NE(indices, nullptr);
ValidateOutput(*indices);
ASSERT_EQ(indices->length(), 0);
}
}

TEST_F(TestSelectKWithTable, TopKOneColumnKey) {
auto schema = ::arrow::schema({
{field("a", uint8())},
Expand Down
6 changes: 6 additions & 0 deletions cpp/src/arrow/compute/kernels/vector_select_k.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -274,6 +274,9 @@ class ChunkedArraySelector : public TypeVisitor {

const auto num_chunks = chunked_array_.num_chunks();
if (num_chunks == 0) {
ARROW_ASSIGN_OR_RAISE(auto take_indices,
MakeMutableUInt64Array(0, ctx_->memory_pool()));
*output_ = Datum(take_indices);
return Status::OK();
}
if (k_ > chunked_array_.length()) {
Expand Down Expand Up @@ -624,6 +627,9 @@ class TableSelector : public TypeVisitor {

const auto num_rows = table_.num_rows();
if (num_rows == 0) {
ARROW_ASSIGN_OR_RAISE(auto take_indices,
MakeMutableUInt64Array(0, ctx_->memory_pool()));
*output_ = Datum(take_indices);
return Status::OK();
}
if (k_ > table_.num_rows()) {
Expand Down
Loading